CN120342086B

CN120342086B - Power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system

Info

Publication number: CN120342086B
Application number: CN202510813842.7A
Authority: CN
Inventors: 陈晶晶
Original assignee: Fujian Jingli Information Technology Co ltd
Current assignee: Fujian Jingli Information Technology Co ltd
Priority date: 2025-06-18
Filing date: 2025-06-18
Publication date: 2025-09-16
Anticipated expiration: 2045-06-18
Also published as: CN120342086A

Abstract

The invention provides a power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system, which relates to the technical field of multi-module networks and comprises a multi-module, a detection module and a fault feature vector, wherein the multi-module is used for deploying a multi-module sensing unit at key monitoring points of power transmission and transformation equipment, collecting vibration, partial discharge, leakage current and environmental parameter signals, processing the signals through electromagnetic shielding shell encapsulation and built-in harmonic wave filter circuits to obtain original monitoring signal data, and the detection module is used for inputting the original monitoring signal data into a chaos enhanced weak signal detection device and extracting the fault feature vector through capturing a suction sub-phase diagram mutation and a time domain waveform threshold. According to the invention, through the multi-mode sensing and self-adaptive networking technology, the monitoring of the power transmission and transformation weak signals and the timely extraction of fault characteristics are realized, and the fault early warning accuracy and self-adaptive capacity are improved.

Description

Power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system

Technical Field

The invention relates to the technical field of multi-module networks, in particular to a power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system.

Background

In the power transmission and transformation construction engineering, the conventional technology has some limitations when facing weak signals in complex environments. For example, in the construction process of newly-built transformer substations in mountain areas, the problems of signal interruption or transmission delay easily occur in the traditional single-mode signal transmission technology due to complex terrain and insufficient coverage of base stations. When constructors use traditional monitoring equipment to record pouring data of a tower foundation in a key link of installing a high-voltage transmission tower, partial data transmission is incomplete due to unstable signals, and construction managers cannot acquire accurate construction progress and quality information in time.

In addition, conventional systems have disadvantages in terms of networking flexibility. In the construction scene of the transformer substation in the mountain area, when the construction area is enlarged or the equipment position is changed, the traditional fixed networking mode is difficult to adapt to the change rapidly. If a temporary cable laying monitoring point is newly added, a large number of lines are required to be laid again and complicated equipment debugging is required because the traditional system lacks self-adaptive networking capability, a large amount of time and labor cost are consumed, the new monitoring point cannot be accessed into the system in time, a monitoring blind area exists, and the whole construction process cannot be monitored comprehensively and in real time.

Disclosure of Invention

The technical problem to be solved by the invention is to provide the power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system, stable transmission and dynamic self-adaptive adjustment of networking topology in a weak signal environment are realized through multi-module cooperation, and the real-time performance of the whole flow monitoring of power transmission and transformation construction is improved.

In order to solve the technical problems, the technical scheme of the invention is as follows:

In a first aspect, a power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system includes:

The multimode module is used for deploying multimode sensing units at key monitoring points of power transmission and transformation equipment, collecting vibration, partial discharge, leakage current and environmental parameter signals, and processing the signals through electromagnetic shielding shell encapsulation and built-in harmonic wave filter circuits so as to obtain original monitoring signal data;

The detection module is used for inputting original monitoring signal data into the chaotic enhanced weak signal detection device, and extracting fault feature vectors by capturing the mutation of the attractor phase diagram and the time domain waveform threshold;

The transmission module is used for transmitting the fault feature vector through the wired and wireless dual-channel hot standby transmission device, and when the signal attenuation reaches a preset threshold value, the transmission device automatically switches the transmission channel and simultaneously triggers the relay node to perform gain compensation on the fault feature vector;

The planning module is used for planning a transmission path for the fault feature vector data by adopting a clustered multi-hop ad hoc network structure, and the cluster head nodes realize the automatic repair of the break points of the wireless mesh network based on a dynamic path finding strategy and transmit the fault feature vector data to the sink nodes;

the diagnosis module is used for carrying out space-time correlation fusion on the multi-source fault feature vectors according to the sink node, matching diagnosis results based on the pre-training fault mode library, dynamically adjusting sampling rate, transmission power and filtering parameters according to the diagnosis results, and generating an alarm event;

And the regulation and control module is used for automatically reconstructing the multi-module network topological structure based on fault diagnosis results and network state feedback, dynamically adjusting the working modes of each sensing unit and realizing the self-adaptive maintenance and adjustment of multi-module network monitoring.

Further, the original monitoring signal data is input into a chaos enhanced weak signal detection device, and fault feature vectors are extracted by capturing the mutation of the attractor phase diagram and the time domain waveform threshold, comprising:

Normalizing the original monitoring signal data to eliminate dimension differences among different sensor signals, obtaining unified standardized signal data, and inputting the standardized signal data serving as an external driving signal into a chaos detection structure of preset parameters;

Calculating dynamic stability indexes of the chaotic detection structure in real time, judging the change trend of the current state according to the dynamic stability indexes, and tracking the attractor track form formed in the state space;

When the attractor track is detected to be suddenly changed into a regular periodic state from a chaotic state, recording the time when state transition occurs, and simultaneously, analyzing the signal amplitude and frequency change conditions corresponding to the time before and after the transition time in the time domain waveform of the standardized signal;

identifying waveform segments meeting preset amplitude threshold and frequency change characteristics as signal segments with faults, and carrying out wavelet packet decomposition on the potential fault signal segments to obtain energy distribution conditions in different frequency bands;

and constructing a frequency domain energy distribution vector for representing signal characteristics based on the energy duty ratio of each frequency band, and taking the frequency domain energy distribution vector as a fault characteristic vector for reflecting the running state of the equipment.

Further, the fault feature vector is transmitted through a wired and wireless dual-channel hot standby transmission device, when the signal attenuation reaches a preset threshold value, the transmission device automatically switches the transmission channel and simultaneously triggers the relay node to perform gain compensation on the fault feature vector, and the method comprises the following steps:

If the main channel is a wireless channel, the received signal strength indication value is monitored, and when the quality index of the main channel is monitored to be smaller than a corresponding preset threshold value, the channel signal attenuation is judged to reach the preset threshold value, and a channel switching instruction and a gain compensation trigger signal are generated;

based on the channel switching instruction and the gain compensation trigger signal, the transmission device executes switching operation from the current main channel to the standby channel, and meanwhile, the gain compensation trigger signal activates a designated relay node on a transmission path to acquire a fault feature vector data packet which is interrupted to be transmitted due to the disconnection of the main channel;

And predicting the signal attenuation track of the current transmission link based on the signal attenuation data aiming at the fault characteristic vector data packet, and dynamically calculating a compensation gain value required for power amplification of the fault characteristic vector data packet according to the signal attenuation rate.

Further, for the fault feature vector data packet, predicting a signal attenuation track of the current transmission link based on the signal attenuation data, and dynamically calculating a compensation gain value required for power amplification of the fault feature vector data packet according to the signal attenuation rate, including:

Acquiring channel attenuation data and environmental interference characteristics of a current transmission link, and predicting the change trend of signal attenuation amplitude along with transmission time and distance based on the association relation between the time characteristics of the channel attenuation data and the environmental interference characteristics;

dynamically generating real-time signal attenuation rate predicted values of discrete position points in a transmission path by combining the signal attenuation change trend with the link impedance fluctuation parameters and the electromagnetic interference intensity instantaneous values acquired in real time;

Dividing a transmission path of a fault feature vector data packet into continuous sections according to attenuation rate mutation points according to real-time signal attenuation rate predicted value distribution, and calculating the corresponding theoretical signal attenuation degree at each sectional node;

Comparing the theoretical signal attenuation degree of the segmented nodes with the actual attenuation degree monitored by the sensor in real time, and obtaining attenuation degree deviation values at all nodes;

and dynamically generating a compensation gain value required for amplifying the power of the fault characteristic vector data packet according to the attenuation degree deviation and combining the influence degree proportion of the transmission distance of the corresponding section on the signal attenuation.

Further, for fault feature vector data, a clustered multi-hop ad hoc network architecture is adopted to plan a transmission path, and cluster head nodes realize break point autonomous repair of a wireless mesh network based on a dynamic path finding strategy and transmit the fault feature vector data to a sink node, comprising:

Receiving a fault characteristic vector data packet subjected to relay node gain compensation, and establishing a topological connection structure among nodes in a cluster in a clustered multi-hop ad hoc network based on node geographic position information and real-time link quality data required by data packet transmission to form an initial transmission path;

based on the topological connection structure, the cluster head node periodically detects the communication state of each neighbor node, updates a network routing table in real time according to the detection result, and performs performance evaluation on comprehensive signal strength and node residual energy aiming at each path recorded in the table;

when the communication state monitoring indicates that the breakpoint exists in the current transmission path, the cluster head node starts a dynamic path searching strategy to carry out autonomous repair;

After the path repair is completed, the cluster head nodes relay the fault characteristic vector data to the sink nodes through the repaired multi-hop paths.

Further, according to the sink node, performing space-time correlation fusion on the multi-source fault feature vector, matching the diagnosis result based on the pre-training fault mode library, dynamically adjusting the sampling rate, the transmission power and the filtering parameters according to the diagnosis result, and generating an alarm event, including:

the sink node extracts the time stamp and the equipment position label of each fault feature vector, and aligns signals from different equipment through a sliding time window based on the time stamp and the position label;

inputting the fusion feature vector into a pre-training fault mode library for similarity matching, obtaining equipment fault types and probability values according to matching results, and generating a deterministic diagnosis result when the probability values are larger than a preset diagnosis threshold value;

according to the diagnosis result, dynamically adjusting parameters, if the fault probability in the diagnosis result is greater than a preset probability threshold, increasing the signal sampling rate of related equipment, if the current link quality index is less than the preset quality threshold, increasing the node transmission power, and if a frequency band interference signal is detected in the fusion characteristic, adaptively enhancing the suppression parameters of the filter;

And monitoring voltage signals in the fusion characteristics in real time, and immediately triggering a hierarchical alarm event generation mechanism when the transient voltage abrupt change amplitude is monitored to be larger than a safety limit value.

Further, inputting the fusion feature vector into a pre-training fault mode library for similarity matching, obtaining a device fault type and a probability value according to a matching result, and generating a deterministic diagnosis result when the probability value is greater than a preset diagnosis threshold value, wherein the method comprises the following steps:

Aiming at each fault mode feature vector in the pre-training fault mode library, respectively calculating Euclidean distances between the feature vector and the fusion feature vector in a feature space, generating a distance measurement value set comprising distance values corresponding to all fault modes, and performing standardization processing on the distance measurement value set to obtain a standardized distance value set;

Inputting the standardized distance value set into a preset similarity converter, and dynamically generating a matching probability value of each fault mode corresponding to the fusion feature vector through the distance-probability inverse relationship built in the converter;

The matching probability values are arranged in a descending order according to the numerical value, and are compared with a preset diagnosis threshold item by item, the probability value larger than the threshold and the associated fault mode are determined, and a candidate fault mode set is formed;

Extracting a first-order fault mode in the candidate fault mode set, analyzing equipment fault type codes corresponding to the modes and influencing component identifications;

based on the fault type codes and the influencing component identifications, and combining with a preset confidence grading rule, a deterministic diagnosis result comprising a specific fault position identification, a fault type description and a confidence grading is generated.

Further, based on the fault diagnosis result and the network status feedback, the method automatically reconstructs the topology structure of the multi-module network, dynamically adjusts the working mode of each sensing unit, realizes the self-adaptive maintenance and adjustment of the multi-module network monitoring, and comprises the following steps:

based on fault position identification and confidence rating in a deterministic diagnosis result, generating a multi-module network topology reconstruction instruction by combining network state feedback data acquired in real time, wherein the network state feedback data comprises a node connection state, a link quality index and node residual energy;

According to the topology reconstruction instruction, re-dividing a cluster area in the clustered multi-hop ad hoc network, determining cluster head nodes, isolating a fault area with the opposite confidence rating exceeding a preset threshold value, and constructing a redundant transmission path bypassing the fault area;

Dynamically adjusting the working mode of the sensing unit in the associated area based on the reconstructed topological structure and the fault type influence range in the deterministic diagnosis result;

And periodically verifying the validity of the reconstruction topology according to the link quality change trend in the network state feedback, and realizing the self-adaptive running state of the monitoring network based on the verification result.

In a second aspect, a computing device includes:

One or more processors;

and a storage device for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the system.

In a third aspect, a computer readable storage medium has a program stored therein, which when executed by a processor, implements the system.

The scheme of the invention at least comprises the following beneficial effects:

Vibration and partial discharge signals are acquired by arranging a plurality of sensors in a multi-mode manner, and a chaotic enhancement type weak signal detection device is utilized to capture the mutation of the attractor phase diagram and the waveform threshold value, so that weak fault characteristics can be extracted accurately, early potential faults can be identified effectively, and the accident occurrence probability is reduced compared with the traditional monitoring mode. The dual-channel transmission adopts a wired and wireless hot standby transmission mechanism, and when the signal attenuation reaches a preset threshold value, the channel is automatically switched, and the relay node is triggered to perform gain compensation. And dynamically calculating a compensation gain value based on signal attenuation prediction, ensuring continuity and accuracy of data transmission, and effectively avoiding monitoring failure caused by transmission interruption. The networking planning utilizes a clustering multi-hop ad hoc network architecture, and cluster head nodes realize the automatic breakpoint repair of the wireless mesh network based on a dynamic path finding strategy. The network topology change can be responded quickly, the transmission path is reconstructed by automatically bypassing the fault area, the network recovery time is shortened to the second level, and the network stability and the fault resistance are improved. And performing space-time correlation fusion on the multi-source fault feature vectors by fault diagnosis, and generating a deterministic diagnosis report by combining a pre-training fault mode library and matching diagnosis results and through Euclidean distance measurement and probability conversion. The self-adaptive regulation and control is based on fault diagnosis and network state feedback, automatically reconstructs a multi-module network topological structure and dynamically adjusts the working mode of the sensing unit. The intelligent level and the operation and maintenance efficiency of the power transmission and transformation construction monitoring system can be improved by rapidly adapting to equipment faults and environmental changes.

Drawings

Fig. 1 is a schematic diagram of a power transmission and transformation construction weak signal multi-module network adaptive monitoring system provided by an embodiment of the invention.

Fig. 2 is a flow chart of a process of inputting the fusion feature vector into a pre-training fault mode library for similarity matching, obtaining a device fault type and a probability value according to a matching result, and generating a deterministic diagnosis result when the probability value is greater than a preset diagnosis threshold.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

As shown in fig. 1, an embodiment of the present invention provides a power transmission and transformation construction weak signal multi-module network adaptive monitoring system, including:

The multimode module is used for deploying multimode sensing units at key monitoring points of power transmission and transformation equipment, collecting vibration, partial discharge, leakage current and environmental parameter signals, and performing anti-interference processing on the signals through electromagnetic shielding shell encapsulation and built-in harmonic wave filter circuits so as to obtain original monitoring signal data;

In the embodiment of the invention, the multi-mode sensing units are deployed at key monitoring points of the power transmission and transformation equipment, so that synchronous acquisition of multi-dimensional signals such as vibration, partial discharge, leakage current, environmental parameters and the like is realized, key indexes of the running state of the equipment are comprehensively covered, and the limitation of single signal monitoring is avoided. The electromagnetic shielding shell is packaged and the harmonic filter circuit is built in to perform anti-interference treatment, so that the influence of external electromagnetic interference and harmonic noise is reduced from a signal acquisition source, and the purity and reliability of original monitoring signal data are improved. The chaotic enhanced weak signal detection device is adopted, the sensitivity of the chaotic system to weak signal change is utilized, the precision bottleneck of the traditional detection method is broken through, and extremely tiny abnormal signal change in the running process of equipment can be captured. By combining the attractor phase diagram mutation with the time domain waveform threshold criterion, the fault feature vector can be effectively extracted, weak fault signals can be accurately identified even in the early fault stage of the equipment, and the timeliness and accuracy of fault early warning are improved.

A redundant data transmission path is constructed by using a wired and wireless dual-channel hot standby transmission mechanism, and when the quality of a main transmission channel is reduced to a preset threshold value due to signal attenuation and environmental interference, a transmission device is automatically and quickly switched to a standby channel, so that uninterrupted transmission of fault feature vector data is ensured. Meanwhile, the relay node is triggered to carry out gain compensation on the data, the transmission power is dynamically adjusted according to the signal attenuation condition, the problems of distance limitation and attenuation in the signal transmission process are effectively overcome, the stability and the integrity of data transmission are ensured, and monitoring failure caused by transmission interruption is avoided. Based on the clustering multi-hop ad hoc network architecture planning transmission path, the method is fully suitable for the characteristics of wide distribution and complex environment of power transmission and transformation equipment, and flexibly constructs network topology. The cluster head nodes adopt a dynamic path searching strategy, the communication state of network nodes is monitored in real time, when a wireless mesh network breakpoint occurs, paths can be automatically repaired rapidly, a data transmission route is automatically planned again by bypassing a fault area, manual investigation and intervention are reduced, the anti-fault capability and self-healing performance of the network are improved, and the fault feature vector data can be efficiently and stably transmitted to the sink nodes.

And carrying out space-time association fusion on the multisource fault feature vectors collected by the sink nodes, comprehensively considering signal information of different equipment and different time and space dimensions, and deeply mining potential association among signals, so as to avoid misjudgment and missed judgment of single signal diagnosis. And matching diagnosis is carried out by combining a pre-training fault mode library, the type, probability and position of the equipment fault can be rapidly and accurately judged, and the sampling rate, transmission power and filtering parameters are dynamically adjusted according to the diagnosis result, so that intelligent optimal configuration of monitoring resources is realized. Meanwhile, an alarm event is generated timely, so that operation and maintenance personnel can be helped to rapidly locate faults, and the fault processing efficiency is improved. According to the fault diagnosis result and the network state feedback, the multi-module network topology structure is automatically reconstructed, isolation processing is carried out on the fault area, the cluster area is divided again, the cluster head nodes are determined, a redundant transmission path bypassing the fault area is constructed, and the reliability and fault tolerance of the network are enhanced. The working modes of each sensing unit are dynamically adjusted, for example, the sampling frequency of the sensor is increased in a fault high-incidence area, and the transmission strategy is optimized when the network is congested, so that the whole multi-module network monitoring system can be rapidly adapted to equipment faults, environment changes and network state fluctuation, and self-adaptive maintenance and adjustment are realized.

In a preferred embodiment of the present invention, the method for inputting the original monitoring signal data into the chaotic enhanced weak signal detection device, and extracting the fault feature vector by capturing the mutation of the attractor phase diagram and the time domain waveform threshold value may include:

In the embodiment of the invention, original monitoring signal data are collected by vibration, partial discharge and leakage current multi-mode sensors, and the signals have dimensional differences due to different physical quantities (for example, the vibration is acceleration m/s2, and the current is ampere A). For unified processing, a linear normalization method is adopted for the original signal of each sensorAnd (5) performing calculation. Assuming that the minimum value of a certain sensor signal isMaximum value ofNormalized formula isThe signal is mapped to the [0,1] interval. Through calculation, the influence of dimension is eliminated, so that different sensor signals have comparability, standardized signal data is generated, and the standardized signal data is used as an external driving signal of the chaos detection structure. The chaos detection structure of the preset parameters has a specific dynamics equation (such as a Lorentz equation and other chaos system equations), and the state of the chaos detection structure changes with time. In order to judge the state change trend, dynamic stability indexes are calculated in real time. Taking Lyapunov indexes as an example, the method describes average index divergence or convergence speed of adjacent tracks in a phase space, and performs linearization processing on a dynamic equation of a chaos detection structure during calculation, and solves the Lyapunov indexes by iteratively calculating a Jacobian matrix. If the index is positive, the adjacent tracks are separated exponentially along with time, and if the index is towards zero, the track is converted to a stable state. Meanwhile, the track form of the attractor is tracked in a state space, and the attractor is the final form of the long-term evolution of the system and reflects the stable state or the change trend.

The attractor track is continuously monitored, and when the attractor track is detected to be suddenly changed from a chaotic state (the track presents an irregular and complex winding form) to a regular periodic state (the track presents a simple form which is periodically repeated), the moment of occurrence of the state transition is recorded. In the time domain waveform of the standardized signal, signals before and after the transition time are focused, and the amplitude and frequency change condition is analyzed. The amplitude value is calculated by adopting a root mean square value (RMS) with the formula ofWhereinFor the number of sample points,Is the firstAnd the frequency analysis adopts Fast Fourier Transform (FFT) to convert the time domain signal into a frequency domain to acquire the frequency component and the corresponding amplitude of the signal. And identifying the signal segment with faults according to the preset amplitude threshold value and the frequency change characteristic (such as the sudden increase of the amplitude beyond the threshold value or the enhancement of specific frequency components). And carrying out wavelet packet decomposition on the potential fault signal fragments, wherein the wavelet packet decomposition is a method for decomposing signals to different frequency bands. It gradually subdivides the signal into narrower frequency bands by multi-layer decomposition. For example, three layers of wavelet packet decomposition is performed, and the signal can be decomposed into 8 different frequency bands. In the decomposition process, convolution operation is carried out according to the wavelet function and the signal to obtain coefficients of each frequency band, so that energy distribution conditions of different frequency bands are obtained, and energy is calculated as the square sum of the coefficients of the frequency bands. And constructing a frequency domain energy distribution vector based on the energy duty ratio of each frequency band. Calculating the ratio of energy in each frequency band to total energy, assuming sharingFrequency band, the firstThe energy of each frequency band isTotal energy ofThen (1)The energy duty ratio of each frequency band isThe energy duty ratios are arranged according to the frequency band order to form a frequency domain energy distribution vectorThe vector serves as a fault signature vector reflecting the operating state of the device.

The dimension difference is eliminated through normalization processing, so that the multi-mode signals are analyzed under the same dimension, analysis deviation caused by the dimension difference is avoided, and a foundation is laid for accurately extracting fault characteristics. The chaotic detection structure is sensitive to weak signal change, and the attractor track mutation is analyzed by combining dynamic stability indexes such as Lyapunov index and the like, so that an early fault signal of equipment which is difficult to find by a traditional method can be captured, and the precision of fault feature extraction is improved. And the comprehensive attractor phase diagram mutation, the time domain waveform amplitude and the frequency change are used for carrying out fault judgment, signals are analyzed from two dimensions of a phase space and a time domain, the limitation of single dimension judgment is avoided, the comprehensiveness and the accuracy of fault judgment are improved, and the misjudgment and missed judgment probability is effectively reduced. The wavelet packet decomposition can adaptively decompose signals to different frequency bands, comprehensively acquire energy distribution of each frequency band according to the characteristic of complex frequency components of fault signals of power transmission and transformation equipment, accurately describe the characteristics of the fault signals, and the constructed frequency domain energy distribution vector contains rich signal characteristic information, calculates dynamic stability indexes in real time and tracks attractor tracks, can discover the change of the fault signals in time, and realizes real-time monitoring of faults. Through strict calculation process and multi-step verification (such as amplitude threshold judgment, frequency analysis and the like), the extracted fault feature vector is ensured to be real and reliable, solid monitoring guarantee is provided for stable operation of power transmission and transformation equipment, and economic loss and safety risk caused by equipment faults are reduced.

In a preferred embodiment of the present invention, the fault feature vector is transmitted by a wired and wireless dual-channel hot standby transmission device, and when the signal attenuation reaches a preset threshold, the transmission device automatically switches the transmission channel, and triggers the relay node to perform gain compensation on the fault feature vector, which may include:

The method comprises the steps of predicting a signal attenuation track of a current transmission link based on signal attenuation data, dynamically calculating a compensation gain value required for amplifying power of the fault characteristic vector data packet according to signal attenuation rate, specifically, obtaining channel attenuation data and environment interference characteristics of the current transmission link, predicting a change trend of signal attenuation amplitude along with transmission time and distance based on an association relation between time characteristics of the channel attenuation data and the environment interference characteristics, dynamically generating a real-time signal attenuation rate predicted value of each discrete position point in a transmission path by combining the signal attenuation change trend with a link impedance fluctuation parameter and an electromagnetic interference intensity instantaneous value acquired in real time, dividing the transmission path of the fault characteristic vector data packet into continuous sections according to attenuation rate mutation points according to real-time signal attenuation rate predicted value distribution, calculating corresponding theoretical signal attenuation degrees at each section node, comparing the theoretical signal attenuation degrees of the section nodes with actual attenuation degrees monitored in real time, obtaining attenuation degree deviation amounts at each node, and dynamically generating the compensation gain value required for amplifying power of the fault characteristic vector data packet according to attenuation degree deviation amounts of the section and the influence degree ratio of transmission distance of the corresponding section on the signal attenuation.

In the embodiment of the invention, the main controller monitors the fault characteristic vector data transmitted by the wired channel in real time. In the data transmission process, each time a certain number of data packets are transmitted (set asNumber of packets in which errors occur (set as)And (c) a). The calculation formula of the error rate is. For example, if 1000 packets are transmitted, 5 of which are erroneous, the bit error rate is=0.5%. And when the calculated error rate is smaller than a preset wired channel error rate threshold (such as 1%), judging that the signal attenuation of the wired channel reaches the preset threshold. For the wireless channel, the main controller continuously reads the received signal strength indication value, and the RSSI value reflects the strength of the received signal, wherein the unit is dBm. For example, the RSSI value read at a certain moment is-70 dBm. And comparing the RSSI value obtained in real time with a preset wireless channel RSSI threshold (such as-80 dBm), and judging that the wireless channel signal attenuation reaches the preset threshold when the RSSI value is smaller than the threshold. Once the quality index of the main channel meets the threshold condition, the main controller immediately generates a channel switching instruction and a gain compensation trigger signal.

After receiving the channel switching instruction, the transmission device firstly stops the data transmission operation on the main channel. Then, the initialization setting of channel switching is carried out, including configuring communication parameters (such as frequency band of wireless channel, port protocol of wired channel, etc.) of the standby channel, and establishing connection with the standby channel. After connection establishment is completed, the transmission device switches the fault feature vector data packet to a standby channel for transmission. The method comprises the steps that a gain compensation trigger signal is sent to a preset designated relay node on a transmission path, after the relay node receives the trigger signal, a data receiving program is started, a fault characteristic vector data packet which is interrupted to be transmitted due to the fact that a main channel is disconnected is obtained, the relay node caches the received data packet, and gain compensation processing is waited. The main controller collects channel attenuation data (such as error rate or RSSI value change records of different time periods) of the current transmission link and environmental interference characteristics (such as surrounding electromagnetic equipment distribution, weather conditions and other environmental factors affecting signal transmission). By analysing the time series characteristics of the channel attenuation data, e.g. by moving average, the time period elapsed (set to) The average amount of attenuation within the range, thus, the change trend of the signal attenuation amplitude with the transmission time is predicted. And simultaneously, correcting the prediction result by combining the environmental interference characteristics, for example, properly increasing the predicted signal attenuation amplitude when detecting that the surrounding strong electromagnetic equipment is started. In addition, the influence of the transmission distance on the signal attenuation is considered, and the attenuation predicted value is adjusted according to the length of the transmission path, so that the comprehensive variation trend of the signal attenuation amplitude along with the transmission time and the distance is obtained.

The signal attenuation change trend is combined with a link impedance fluctuation parameter (reflecting the change of the electrical characteristics of the transmission line) acquired in real time, and an electromagnetic interference intensity instantaneous value is combined. For example, when the link impedance suddenly increases, it is indicated that there may be a problem of poor contact on the transmission line, which may result in an increase in signal attenuation, and at this time, the predicted signal attenuation rate is correspondingly increased according to the impedance variation amplitude and the data experience, and when the electromagnetic interference strength instantaneous value increases, the predicted signal attenuation rate value is adjusted as well. In this way, real-time signal decay rate predictions for discrete location points in the transmission path are dynamically generated. And dividing the transmission path of the fault characteristic vector data packet into continuous sections according to the attenuation rate abrupt change points according to the real-time signal attenuation rate predicted value distribution. For each segment node, calculating a theoretical signal attenuation degree, wherein the theoretical attenuation degree can be comprehensively calculated according to factors such as the length of the segment, a predicted attenuation rate, initial signal strength and the like. Simultaneously, the sensor monitors the actual attenuation degree at each node in real time. And comparing the theoretical signal attenuation degree and the actual attenuation degree of the segmented nodes to obtain attenuation degree deviation values at all nodes. And dynamically generating a compensation gain value required for power amplification of the fault feature vector data packet according to the attenuation degree deviation amount and combining the influence degree proportion of the transmission distance of the corresponding section on the signal attenuation (for example, the longer the distance is, the higher the influence weight of the distance factor on the attenuation is). For example, if the theoretical attenuation of a certain section is 10dB, the actual attenuation is 12dB, the deviation amount is 2dB, the distance is long, the distance factor weight ratio is 60%, and the compensation gain value is finally determined to be 3dB according to a preset calculation rule, so as to ensure that the signal can maintain enough strength in the transmission process.

The dual channel hot standby transmission mechanism provides redundant transmission paths for fault feature vector data. When the quality of the main channel is reduced due to signal attenuation, equipment failure or environmental interference, the main channel can be automatically and quickly switched to the standby channel, and the interruption of data transmission is avoided. Even in complex and changeable power transmission and transformation environments (such as strong electromagnetic interference, bad weather affecting wireless signals, or physical damage of a wired line), continuous and stable data transmission can be ensured. The transmission strategy can be intelligently adjusted according to the actual transmission condition by monitoring the quality index of the main channel in real time and dynamically judging and deciding based on a preset threshold value. Whether the error rate of the wired channel is abnormal or the signal intensity of the wireless channel is insufficient, the corresponding processing mechanism can be triggered in time. The gain compensation function of the relay node can dynamically adjust the compensation gain value according to the signal attenuation track and the real-time attenuation rate, accurately match the signal enhancement requirements of different transmission sections, effectively overcome the problems of distance limitation and attenuation in the signal transmission process, ensure that the data can still keep good quality when being transmitted in a long-distance and complex environment, and improve the stability and the effectiveness of the transmission. The automatic channel switching and gain compensation capability is achieved, manual detection and switching of transmission channels are not needed, and signal gain is not needed to be calculated and adjusted manually. When the transmission channel is in a problem, fault response and repair can be completed autonomously, and the workload and maintenance cost of operation and maintenance personnel are reduced. Meanwhile, the rapid fault response mechanism can shorten the data transmission interruption time and reduce the influence of data loss or transmission delay on power transmission and transformation equipment monitoring and fault diagnosis. In a power transmission and transformation environment, electromagnetic interference and line aging factors easily cause signal attenuation and transmission faults. The dual channel transmission and dynamic gain compensation mechanism is able to effectively cope with these disturbances and faults. The existence of the standby channel provides fault tolerance space, and gain compensation of the relay node enhances the resistance to signal attenuation. Even if a problem occurs in a local transmission link, data transmission can be maintained through channel switching and gain adjustment, normal operation of a monitoring system is guaranteed, and anti-interference and fault-tolerant performances of the power transmission and transformation construction weak signal multi-module network self-adaptive monitoring system are improved.

In a preferred embodiment of the present invention, for fault feature vector data, a clustered multi-hop ad hoc network architecture is used to plan a transmission path, and a cluster head node realizes break point autonomous repair of a wireless mesh network based on a dynamic routing policy, and transmits the fault feature vector data to a sink node, which may include:

In the embodiment of the invention, the cluster head node receives the fault feature vector data packet which is subjected to gain compensation from the relay node, wherein the data packet comprises data per se and attached meta information such as geographical position coordinates (longitude and latitude information) of the sending node and data packet generation time. The cluster head node analyzes the information and extracts the geographical position information of the nodes required by data packet transmission. The cluster head node sends a detection signal (such as a low-power broadcast signal) to each node in the cluster, and each node calculates a link quality index between the cluster head node and the cluster head node according to the received signal strength and signal-to-noise ratio parameters after receiving the detection signal. Common link quality index calculation methods are, for example, based on Received Signal Strength Indication (RSSI), mapping the RSSI value to a quality score interval of 0-100, for example, a score of 80-60 minutes for RSSI values between-50 dBm and-70 dBm, and feeding back the calculated link quality score to the cluster head node by the node.

Based on the extracted node geographic position information and link quality data, the cluster head nodes construct a topological connection structure among nodes in the cluster by using a method in graph theory. Each node is regarded as a vertex in the graph, the connection relationship between the nodes is regarded as an edge, the weight of the edge is determined by the link quality score, and the higher the score, the lower the weight (the better the link quality is indicated). The shortest path (based on link quality weights) from each node to the cluster head node is calculated by a shortest path algorithm, thereby forming an initial transmission path. For example, if there are H, M, G nodes in the cluster, the link quality scores of the H and the cluster head nodes are 80, M is 70, and G is 60, and after the algorithm calculation, the transmission paths of the H-cluster head, the M-H-cluster head and the G-M-H-cluster head may be determined. The cluster head node periodically (for example, every 10 seconds) sends a connectivity detection data packet (including simple identification information) to the neighbor node, the neighbor node immediately replies a confirmation data packet after receiving the detection data packet, the cluster head node judges the connection state of the neighbor node according to whether the confirmation data packet is received or not, and if the confirmation is not received within a specified time (for example, 2 seconds), the neighbor node is judged to be in the disconnection state.

And updating the network routing table by the cluster head node in real time according to the detection result of the communication state. The routing table records the information of each reachable node, including the node ID, the geographic position, the link quality score with the node, and the information of the next hop node. When detecting the connection state change of a certain node, updating the related information of the corresponding node, if a new reachable node is found, adding a new record, and if the node is disconnected, deleting or marking the node record. And performing performance evaluation on the comprehensive signal intensity and the node residual energy of the cluster head nodes aiming at each path recorded in the routing table. The signal strength is expressed by a link quality score, and the node residual energy is measured by the percentage of battery power periodically reported by the node. By adjusting the weight, the signal strength or the node residual energy can be emphasized according to the actual demand, and the higher the score is, the better the performance is. In the data transmission process, if the cluster head node does not receive the confirmation reply of a certain next-hop node within a set time after sending the data packet to the next-hop node, and does not respond after repeated retransmission (for example, 3 times), the breakpoint of the current transmission path is determined. When a breakpoint is detected, the cluster head node starts a dynamic routing strategy, and firstly, nodes which are adjacent to the breakpoint node and are in a communication state are screened out from a network routing table to serve as candidate nodes. Then, with the cluster head node as a starting point, the candidate node as an intermediate node, and the sink node as an end point, a shortest path algorithm (based on the updated link quality weight and the node remaining energy weight) is used again to calculate a new path from the cluster head node to the sink node. In the calculation process, the path segment with the determined fault is removed, and the path with higher performance evaluation index is preferentially selected. After the path repair is completed, the cluster head nodes relay the fault characteristic vector data according to the repaired multi-hop path. The cluster head node sends the data packet to the next hop node of the new path, and the node forwards the data packet to the next hop according to the routing table information after receiving the data packet, and relays the data packet in turn until the data packet is transmitted to the sink node. Each node checks the integrity of the data packet (e.g., by checksum calculation) when forwarding the data packet, and if the data packet is found to be corrupted, the node of the previous hop is discarded and notified of the retransmission.

The clustered multi-hop ad hoc network architecture effectively responds to complex and changeable network conditions in a power transmission and transformation environment by establishing a topological connection structure in a cluster and combining a dynamic path searching strategy and a path repairing mechanism. When the breakpoint occurs in the transmission path, the path can be quickly and autonomously repaired, interruption of data transmission caused by single-point faults is avoided, connectivity of the network can be maintained even under severe environments (such as interruption of partial node signals caused by strong electromagnetic interference), stable transmission of fault feature vector data to the sink nodes is ensured, and stability and reliability of the network are improved. The performance of the paths is evaluated by combining the signal strength and the node residual energy, and when the transmission path is planned, the paths with good signal quality and sufficient node energy are selected, so that the nodes with low energy are prevented from being excessively used, and the load of each node in the network is effectively balanced. The cluster head node periodically detects the communication state of the neighbor nodes and updates the routing table in real time, so that the network can quickly sense the environment change (such as equipment position change, new node joining or old node exiting). The dynamic path searching strategy ensures that the network can timely adjust the transmission path according to the environmental change, can adapt to complex and changeable power transmission and transformation field environments without manual intervention, enhances the self-adaptability and flexibility of the network, and meets the monitoring requirements of wide equipment distribution and complex environment in power transmission and transformation construction. The clustering multi-hop transmission mode decomposes long-distance data transmission into a plurality of short-distance relay transmissions, and can effectively reduce data transmission delay by combining dynamic path finding and selecting a final path. Meanwhile, the rapid response mechanism of path repair enables data to be rapidly switched to new path transmission when faults occur, long-time waiting or data accumulation is avoided, real-time performance of monitoring data is ensured, and powerful support is provided for rapid fault diagnosis and timely processing of power transmission and transformation equipment. The clustered multi-hop ad hoc network architecture facilitates the expansion and upgrading of the network.

In a preferred embodiment of the present invention, performing space-time correlation fusion on the multi-source fault feature vector according to the sink node, and matching the diagnosis result based on the pre-training fault mode library, dynamically adjusting the sampling rate, the transmission power and the filtering parameters according to the diagnosis result, and generating the alarm event at the same time, may include:

Inputting the fusion feature vector into a pre-training fault mode library for similarity matching, obtaining equipment fault types and probability values according to the matching result, and generating a deterministic diagnosis result when the probability value is larger than a preset diagnosis threshold value, wherein the method specifically comprises the steps of respectively calculating Euclidean distances between each fault mode feature vector in the pre-training fault mode library and the fusion feature vector in a feature space, generating a distance measurement value set comprising distance values corresponding to all fault modes, and performing standardization processing on the distance measurement value set to obtain a standardized distance value set;

The matching probability values are arranged in a descending order according to the numerical value, and are compared with a preset diagnosis threshold item by item, the probability value larger than the threshold and the associated fault mode are determined, and a candidate fault mode set is formed; based on the fault type codes and the influencing component identifications, combining with a preset confidence level grading rule, and generating a deterministic diagnosis result comprising a specific fault position identification, a fault type description and a confidence level grading;

In the embodiment of the invention, the sink node receives fault feature vectors from different devices, and each vector records the signal acquisition time (accurate to millisecond) and the device installation position (comprising the device number and the geographic coordinates). The sink node extracts the time and position information independently by analyzing the data format, and prepares for subsequent unified processing. The length of the time window (e.g., 500 milliseconds) and the interval of each slide (e.g., 100 milliseconds) are set. And taking the signal acquisition time as a basis, and taking signals acquired by different devices in the same time window as data at the same moment. If the acquisition time of a certain device signal is inconsistent with the window starting time, the signal is corresponding to a proper time point in the window in a reasonable estimation mode, so that the time alignment of different device signals is realized. Meanwhile, according to the equipment position information, equipment signals with similar positions are associated, and consistency of time and space dimensions is guaranteed.

A weight is assigned to each device's fault signature based on the importance of the device (e.g., more important devices on critical power lines) and the accuracy of the signal acquisition (more reliable signals acquired by high accuracy sensors). The weights of all devices add up to 1. And then, adding the values of each device in each characteristic dimension (such as vibration frequency, partial discharge intensity and the like) according to the weight to obtain the fused characteristic value. The fused eigenvalues are combined to form a fused eigenvector. And comparing the fusion feature vector with each fault mode feature vector in the pre-trained fault mode library, and judging the similarity degree of the fusion feature vector and each fault mode feature vector. The comparison method is to calculate the distance between the two, and the closer the distance is, the higher the similarity is. The calculated distances are adjusted firstly, all the distances are in the range of 0 to 1, and then according to the corresponding relation between the distances and the probability, the fault mode with the closer distance is endowed with a higher matching probability value.

The calculated matching probability values are ranked from large to small and are compared with a set diagnosis standard (such as 0.7) in sequence. And screening fault modes with probability values exceeding the standard to form a candidate list. From this list, the failure mode with the highest probability value is selected, and its corresponding equipment failure type and affected components are analyzed. And then combining with a preset credibility standard (such as low credibility of probability 0.7-0.8, medium credibility of 0.8-0.9 and high credibility of more than 0.9), and generating a diagnosis result comprising the specific fault position, fault type description and credibility rating. And comparing the fault probability in the diagnosis result with a set probability standard (such as 0.6), and if the fault probability exceeds the standard, indicating that the equipment fault risk is higher, and acquiring more detailed signal information. At this time, the signal sampling frequency of the relevant equipment is increased according to a certain proportion, and a new sampling frequency setting is sent to the equipment, and the equipment automatically adjusts the sampling frequency after receiving the signal. The quality of the current signal transmission is monitored in real time (comprehensively estimated by indexes such as error rate, signal strength and the like) and is compared with a set quality standard (such as 80 minutes). If the transmission quality is lower than the standard, the signal transmission effect is poor, the transmission power of the node is increased proportionally according to the quality reduction degree, an adjustment instruction is sent to the node, and the node can strengthen the signal transmission power according to the instruction.

And analyzing the fusion characteristic vector, and checking whether a frequency band interference signal exists (setting an interference frequency band range and judging whether the signal intensity in the range is abnormal or not). If interference is detected, the suppression capability of the filter to the interference frequency band is proportionally enhanced according to the severity of the interference, and new parameter settings are sent to the filter, which filters out more interference signals accordingly. And extracting the voltage signal part in the fusion feature vector in real time, comparing the voltage values at adjacent moments, and calculating the variation amplitude of the voltage signal. The calculated voltage variation amplitude is compared with a set safety standard (e.g. 20% of rated voltage). If the amplitude of the change exceeds the standard, different levels of alarms are triggered according to the degree of the exceeding.

By considering the time and space information of the multi-equipment signals at the same time, the limitation of diagnosing by only relying on single equipment signals is avoided, and the accuracy and the comprehensiveness of fault diagnosis are improved. The method for fusing the distribution weights according to the importance of the equipment and the signal quality ensures that the diagnosis result is more reliable. And the sampling rate, the transmission power and the filtering parameters are automatically adjusted according to the diagnosis result, so that reasonable allocation of resources is realized. The signal acquisition frequency is automatically increased when the equipment fault risk is high, the transmission power is enhanced when the signal transmission quality is poor, the filtering effect is optimized when interference occurs, the automatic adjustment can be performed according to the actual running condition, the monitoring efficiency and the data quality are improved, and the resource waste is avoided. The voltage signal in the fusion characteristic is monitored in real time, abnormal change of the voltage can be rapidly found, and alarms of different levels are sent out according to the change amplitude. The grading alarm mode enables operation and maintenance personnel to rapidly judge the severity of the fault, and the high-risk fault is preferentially processed, so that the fault processing time is shortened, the risk of equipment damage or grid accidents caused by voltage abnormality is reduced, and the safe and stable operation of the power transmission and transformation system is ensured. The multi-source data fusion and dynamic parameter adjustment are combined, so that the method can adapt to complex and variable power transmission and transformation operating environments. Whether equipment faults, network fluctuation or environment interference are caused, the system can keep stable operation through self diagnosis and regulation mechanisms, the influence of external factors on monitoring and diagnosis results is reduced, the anti-interference capability and stability are enhanced, and the reliability and usability of the whole monitoring system are improved.

In a preferred embodiment of the present invention, based on the fault diagnosis result and the network status feedback, the method automatically reconstructs the topology structure of the multi-module network, dynamically adjusts the working mode of each sensing unit, and realizes the self-adaptive maintenance and adjustment of the multi-module network monitoring, and may include:

In the embodiment of the invention, a deterministic diagnosis result output by a fault diagnosis module is obtained, and fault position identifiers (such as equipment numbers and geographic coordinates) and confidence ratings (representing the reliability degree of the diagnosis result and a value range of 0-1) are extracted. Meanwhile, network state feedback data are collected in real time, wherein the network state feedback data comprise the connection state of each node (whether the node is on-line or not is judged by sending a detection signal and receiving a recovery signal), the link quality index (obtained by calculating parameters such as a comprehensive error rate, signal strength, signal to noise ratio and the like, and the higher the value is, the better the link quality is) and the node residual energy (the node periodically reports the battery power percentage or the power residual capacity to determine).

If the failure confidence rating in a certain area exceeds a preset threshold (e.g. 0.8), the node communication state in the area is deteriorated, the link quality index is reduced to a certain degree (e.g. less than 60 minutes), and the node residual energy is low (e.g. less than 30%), then the area is judged to need topology reconstruction. Based on these conditions, a multi-module network topology reconfiguration instruction is generated that includes information on the extent of the fault region, the reconfiguration target (e.g., isolating the fault region, optimizing the transmission path), etc.

Based on a clustering multi-hop ad hoc network architecture, a cluster area is re-planned by taking a fault area as a center and combining with the geographical position distribution of network nodes. And calculating the distance from each node to the boundary of the fault area by adopting a distance measurement method, and dividing the nodes which are far away from the fault area and have good interconnection into new clusters. For example, a distance threshold (e.g., 50 meters) is set, and nodes that are above the threshold from the failure zone and have a link quality score between nodes that is above a certain criteria (e.g., 70 minutes) are grouped into the same cluster. For each newly partitioned cluster, the cluster head node is elected. Election criteria comprehensively consider factors such as node remaining energy (higher priority is higher with higher energy), processing capacity (such as CPU performance and memory capacity), link quality (average link quality score with other nodes in the cluster), and the like. And determining cluster head nodes by a voting mechanism or a weighted scoring method, such as node residual energy accounting for 40%, processing capacity accounting for 30% and link quality accounting for 30%, calculating the comprehensive score of each node, and selecting the node with the highest score as the cluster head node. And (3) grading the fault area with the confidence coefficient exceeding a preset threshold value, cutting off the connection links of the area and other normal areas, and realizing physical isolation. Meanwhile, based on the remaining normal nodes, a path search algorithm (such as a variant of the dijkstra algorithm) in graph theory is used to construct a plurality of redundant transmission paths from a source node (normal node close to a fault area) to a target node (sink node or other key nodes), avoiding the fault area. In the construction process, a path with good link quality and high node residual energy is preferentially selected.

And determining the influence range according to the fault type in the deterministic diagnosis result. For example, if the fault type is a partial discharge fault, equipment and surrounding areas possibly affected by the fault are analyzed, and if the fault type is a network link fault, the affected transmission paths and related nodes are determined. And for the sensing units in the associated area, adjusting the working mode according to the fault influence degree and the network state. If the fault influence range is large, the sampling frequency of the sensing unit is increased (for example, from 1 time per minute to 5 times per minute) so as to collect data more frequently, and if the network link quality is poor, the data transmission frequency of the sensing unit is reduced (for example, from 1 time per second to 1 time per 5 seconds), and the data transmission pressure is reduced. And for the sensing units which are close to the fault area but not directly affected, starting an early warning mode, and enhancing the monitoring sensitivity to abnormal signals. And periodically (e.g. every 10 minutes) collecting data such as error rate, signal strength, transmission delay and the like of each transmission path according to the link quality change trend in the network state feedback. And calculating the comprehensive performance index of each path, wherein the comprehensive performance index is obtained by weighting the bit error rate accounting for 30%, the signal strength accounting for 40% and the transmission delay accounting for 30%. And (3) comparing the calculated comprehensive performance index with a preset performance standard (for example, the comprehensive score is required to reach more than 75 minutes). If the comprehensive performance index of a certain path or the whole reconstruction topology does not reach the standard, the reconstruction topology is proved to have a problem. At this time, the network state and the fault condition are re-evaluated, the topology reconstruction flow is executed again, and the cluster area division, cluster head node selection or redundant path construction strategy is adjusted until the reconstruction topology meets the performance requirement, so as to realize the self-adaptive running state of the monitoring network.

By automatically reconstructing the multi-module network topology structure, fault areas are timely isolated, redundant transmission paths are constructed, and fault diffusion and network paralysis are effectively avoided. Even if the emergency such as equipment failure, link interruption and the like occurs in the power transmission and transformation environment, the network structure can be quickly adjusted, the continuity of data transmission is maintained, and the stable acquisition and transmission of monitoring data are ensured. And dynamically adjusting the working mode of the sensing unit, and reasonably distributing resources according to the fault influence range and the network state. And the sampling frequency is increased in the fault high-incidence area to ensure the acquisition of detailed fault information, and the transmission frequency is reduced when the network is congested or the link quality is poor, so that the network burden is reduced. The intelligent resource allocation mode not only improves the effectiveness of monitoring data, but also prolongs the service lives of the sensing units and the network nodes, and reduces the overall energy consumption and the operation and maintenance cost. Based on real-time network state feedback and fault diagnosis results, changes in the power transmission and transformation environment (such as link quality degradation caused by equipment faults and environment interference) can be quickly perceived and responded quickly. The effectiveness of the reconstruction topology is periodically verified, so that the monitoring network always keeps a final operation state, the self-adaptive capacity to complex and changeable environments is enhanced, and the requirement of long-term stable operation of power transmission and transformation construction is met. The isolation mechanism for the high-confidence fault area effectively prevents the spread of faults and reduces the influence range of the faults on the whole network. Meanwhile, the construction of the redundant transmission path ensures that data can still be transmitted through other paths when part of links fail, and shortens the network recovery time. The self-adaptive maintenance and adjustment mechanism realizes automation and intellectualization of network management, and reduces workload of manual intervention and manual configuration. The operation and maintenance personnel do not need to monitor the network state in real time and manually adjust the topological structure, and only need to conduct targeted processing according to the generated alarming and diagnosis results, so that the efficiency and accuracy of operation and maintenance management are improved, and the operation and maintenance of power transmission and transformation construction is promoted to develop towards an intelligent direction.

Embodiments of the invention also provide a computing device comprising a processor, a memory storing a computer program which, when executed by the processor, performs a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.

Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.

While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.

Claims

1. A weak signal multi-mode networking adaptive monitoring system for power transmission and transformation construction, characterized by comprising:

Multimodal module, used to deploy multimodal sensing units at key monitoring points of power transmission and transformation equipment, collect vibration, partial discharge, leakage current and environmental parameter signals, and process the signals through electromagnetic shielding enclosure and built-in harmonic filtering circuit to obtain original monitoring signal data;

The detection module is used to input the original monitoring signal data into the chaos-enhanced weak signal detection device, and extract the fault feature vector by capturing the attractor phase diagram mutation and the time domain waveform threshold;

The transmission module is used to transmit the fault feature vector through a wired and wireless dual-channel hot standby transmission device. When the signal attenuation reaches a preset threshold, the transmission device automatically switches the transmission channel and triggers the relay node to perform gain compensation for the fault feature vector. Specifically, it includes: obtaining the channel attenuation data and environmental interference characteristics of the current transmission link, and predicting the trend of signal attenuation amplitude changing with transmission time and distance based on the correlation between the time characteristics of the channel attenuation data and the environmental interference characteristics; combining the signal attenuation change trend with the real-time collected link impedance fluctuation parameters and the instantaneous value of the electromagnetic interference intensity to dynamically generate a real-time signal attenuation rate prediction value for each discrete position point in the transmission path; based on the distribution of the real-time signal attenuation rate prediction value, the transmission path of the fault feature vector data packet is divided into continuous segments according to the attenuation rate mutation point, and the corresponding theoretical signal attenuation degree at each segment node is calculated; comparing the theoretical signal attenuation degree of the segment node with the actual attenuation degree monitored in real time by the sensor, and obtaining the attenuation degree deviation at each node; based on the attenuation degree deviation, combined with the proportion of the influence of the transmission distance of the corresponding section on the signal attenuation, dynamically generating the compensation gain value required for power amplification of the fault feature vector data packet;

The planning module is used to plan the transmission path of the fault feature vector data using a clustered multi-hop self-organizing network architecture. The cluster head node implements autonomous repair of wireless mesh network breakpoints based on a dynamic pathfinding strategy and transmits the fault feature vector data to the sink node.

The diagnostic module is used to perform spatiotemporal correlation fusion of multi-source fault feature vectors based on the convergence node, match the diagnostic results based on the pre-trained fault mode library, dynamically adjust the sampling rate, transmission power and filtering parameters according to the diagnostic results, and generate alarm events at the same time, including: calculating the Euclidean distance between each fault mode feature vector and the fused feature vector in the pre-trained fault mode library, generating a distance measurement value set and normalizing it to obtain a standardized distance value set; inputting it into a preset similarity converter, and dynamically generating matching probability values corresponding to each fault mode of the fused feature vector based on the built-in distance-probability inverse relationship; arranging the matching probability values in descending order of value, comparing them with the preset diagnostic threshold item by item, determining the probability values greater than the threshold and the associated fault modes, and forming a candidate fault mode set; extracting the fault mode ranked first in the set, parsing the equipment fault type code and the affected component identification; combining with the preset confidence grading rules, generating a deterministic diagnostic result including the specific fault location identification, fault type description and confidence rating;

The control module is used to automatically reconstruct the multi-module network topology based on fault diagnosis results and network status feedback, dynamically adjust the working mode of each sensor unit, and realize adaptive maintenance and adjustment of multi-module network monitoring.

2. The weak signal multi-mode networking adaptive monitoring system for power transmission and transformation construction according to claim 1 is characterized in that the fault characteristic vector is transmitted through a wired and wireless dual-channel hot standby transmission device. When the signal attenuation reaches a preset threshold, the transmission device automatically switches the transmission channel and simultaneously triggers the relay node to perform gain compensation for the fault characteristic vector, including:

The main controller monitors the quality index of the currently activated main transmission channel. If the main channel is a wired channel, it monitors the bit error rate; if the main channel is a wireless channel, it monitors the received signal strength indicator value. When the quality index of the main channel is less than the corresponding preset threshold, it determines that the channel signal attenuation has reached the preset threshold and generates a channel switching instruction and a gain compensation trigger signal.

Based on the channel switching instruction and the gain compensation trigger signal, the transmission device performs a switching operation from the current active channel to the standby channel. At the same time, the gain compensation trigger signal activates the designated relay node on the transmission path to obtain the fault feature vector data packet of the transmission interruption caused by the disconnection of the active channel;

For the fault feature vector data packet, the signal attenuation trajectory of the current transmission link is predicted based on the signal attenuation data, and the compensation gain value required for power amplification of the fault feature vector data packet is dynamically calculated according to the signal attenuation rate.

3. The weak signal multi-mode networking adaptive monitoring system for power transmission and transformation construction according to claim 2 is characterized in that, for fault feature vector data, a clustered multi-hop ad hoc network architecture is used to plan the transmission path, the cluster head node implements autonomous repair of wireless mesh network breakpoints based on a dynamic pathfinding strategy, and transmits the fault feature vector data to the sink node, including:

Receive the fault feature vector data packet after relay node gain compensation, and establish the topological connection structure between nodes in the cluster in the clustered multi-hop ad hoc network based on the node geographic location information and real-time link quality data required for data packet transmission to form an initial transmission path;

Based on the topological connection structure, the cluster head node periodically detects the connectivity status of each neighboring node and updates the network routing table in real time based on the detection results. For each path recorded in the table, the performance is evaluated based on the comprehensive signal strength and node residual energy.

When connectivity status monitoring indicates that there is a breakpoint in the current transmission path, the cluster head node initiates a dynamic pathfinding strategy to perform autonomous repair;

After the path repair is completed, the cluster head node relays the fault feature vector data to the sink node through the repaired multi-hop path.

4. The weak signal multi-mode networking adaptive monitoring system for power transmission and transformation construction according to claim 3 is characterized by performing spatiotemporal correlation fusion on multi-source fault feature vectors based on the sink node, matching diagnosis results based on a pre-trained fault pattern library, dynamically adjusting the sampling rate, transmission power, and filtering parameters based on the diagnosis results, and generating alarm events, including:

The aggregation node extracts the timestamp and device location tag of each fault feature vector and aligns the signals from different devices using a sliding time window based on the timestamp and location tags. After alignment, the weighted evidence theory is used to fuse the fault features associated in the temporal and spatial dimensions to generate a fused feature vector.

The fused feature vector is input into the pre-trained fault pattern library for similarity matching. Based on the matching results, the equipment fault type and probability value are obtained. When the probability value is greater than the preset diagnostic threshold, a deterministic diagnostic result is generated.

Dynamically adjust parameters based on the diagnosis results. If the fault probability in the diagnosis results is greater than the preset probability threshold, the signal sampling rate of the relevant equipment is increased; if the current link quality index is less than the preset quality threshold, the node transmission power is increased; if a frequency band interference signal is detected in the fusion feature, the suppression parameter of the filter is adaptively enhanced;

The voltage signal in the fusion feature is monitored in real time. When the amplitude of the transient voltage mutation is detected to be greater than the safety limit, the hierarchical alarm event generation mechanism is immediately triggered.

5. A computing device, comprising:

one or more processors;

A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the system according to any one of claims 1 to 4.

6 . A computer-readable storage medium, wherein a program is stored in the computer-readable storage medium, and when the program is executed by a processor, the system according to claim 1 is implemented.