CN119919119A

CN119919119A - Fault handling method, device, electronic device, storage medium and product

Info

Publication number: CN119919119A
Application number: CN202510005542.6A
Authority: CN
Inventors: 于琦; 林恩德; 李婉; 张凌凡; 李雨欣; 苏一博; 王振宇
Original assignee: China Three Gorges Corp
Current assignee: China Three Gorges Corp
Priority date: 2025-01-02
Filing date: 2025-01-02
Publication date: 2025-05-02

Abstract

The present invention provides a fault handling method, device, electronic device, storage medium and product, including: obtaining real-time operating parameters of power station equipment, performing fault prediction on the real-time operating parameters, obtaining predicted fault types and predicted fault occurrence time points for power station equipment, performing multi-dimensional impact evaluation on the predicted fault types, obtaining multi-dimensional impact results on power station equipment, performing dynamic cost analysis on power station equipment by predicting fault types and predicted fault occurrence time points, obtaining predicted repair costs of power station equipment, determining target fault handling decisions for power station equipment by multi-dimensional impact results and predicted repair costs, and optimizing the target fault handling decisions in response to user feedback on the target fault handling decisions on a preset user interaction page, thereby reducing operation and maintenance costs, improving fault handling efficiency, improving the availability and reliability of power stations, and improving user satisfaction.

Description

Fault processing method, device, electronic equipment, storage medium and product

Technical Field

The invention belongs to the technical field of new energy, and particularly relates to a fault processing method, a fault processing device, electronic equipment, a storage medium and a product.

Background

With the wide application of electrochemical energy storage technology in power grids, operation and maintenance management of energy storage power stations becomes a key problem for ensuring long-term stable operation of the energy storage power stations. Currently, operation and maintenance management of electrochemical energy storage power stations mainly relies on periodic inspection and maintenance to ensure proper operation of the equipment. The service life of the power station is usually more than 20 years, but the quality guarantee period is usually only five years, and in the quality guarantee period, an operation and maintenance team can utilize services provided by manufacturers to carry out maintenance or replacement of equipment. After exceeding the warranty period, the operation and maintenance team needs to bear the cost of maintaining or replacing the equipment by itself. Typically, an operation and maintenance team decides whether to repair or replace equipment based on experience or simple cost comparisons.

The prior art has a number of major problems in the operation and maintenance management of electrochemical energy storage power stations. Firstly, the information is opaque, and the operation and maintenance team has insufficient knowledge of specific fault reasons, maintenance cost and replacement cost of the equipment, so that the information is not comprehensive in decision making. Secondly, a predictive maintenance mechanism is lacking, potential faults of equipment cannot be identified in advance, and the operation and maintenance passivity is improved. In addition, the economical evaluation is inaccurate, and the lack of systematic evaluation on the influence of equipment faults on the overall operation safety and economic benefit of the power station makes operation and maintenance decisions difficult to optimize, so that the problems result in high operation and maintenance cost, low efficiency and poor reliability of safe operation of the power station.

Disclosure of Invention

The invention provides a fault processing method, a fault processing device, electronic equipment, a storage medium and a product, so as to solve the problems of high operation and maintenance cost, low efficiency and poor reliability of safe operation of the current power station.

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

In a first aspect, the present invention provides a fault handling method, the method comprising:

acquiring real-time operation parameters of power station equipment;

performing fault prediction on the real-time operation parameters to obtain a predicted fault type and a predicted fault occurrence time point of the power station equipment;

performing multidimensional influence assessment on the predicted fault type to obtain a multidimensional influence result on the power station equipment;

Carrying out dynamic cost analysis on the power station equipment through the predicted fault type and the predicted fault occurrence time point to obtain predicted repair cost of the power station equipment;

determining a target fault handling decision for the power plant equipment through the multi-dimensional influence result and the predicted repair cost;

And responding to feedback of the target fault processing decision with a user on a preset user interaction page, and optimizing the target fault processing decision.

Optionally, the performing fault prediction on the real-time operation parameter, obtaining a predicted fault type and a predicted fault occurrence time point of the power station device, includes:

Collecting historical data of the power station equipment, wherein the historical data comprises historical operation parameters of the power station equipment, historical fault occurrence time points and historical fault types;

Respectively pre-training an autoregressive integral moving average model and a deep learning model according to the historical data;

inputting the real-time operation parameters into the pre-trained autoregressive integral moving average model to obtain a predicted fault occurrence time point of the power station equipment;

and inputting the real-time operation parameters into the deep learning model after the pre-training to obtain the predicted fault type of the power station equipment.

performing fault prediction on the real-time operation parameters to obtain a plurality of predicted operation parameters of the power station equipment in a preset time period;

if any one of the predicted operation parameters is greater than or equal to a preset fault threshold, acquiring first power station equipment corresponding to the predicted operation parameter, a target parameter type and a target time point;

Acquiring a predicted fault type and a predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point;

and if the plurality of predicted operation parameters are smaller than a preset fault threshold value, judging that the power station equipment has no fault risk in a preset time period.

Optionally, the performing multidimensional influence assessment on the predicted fault type, and obtaining a multidimensional influence result on the power station equipment, includes:

determining different influence dimensions related to the predictive failure type assessment in advance, wherein the influence dimensions comprise an economic influence dimension, an environmental influence dimension and a social influence dimension;

Setting different weights and different evaluation indexes for different influence dimensions;

And determining a single dimension influence result and a comprehensive dimension influence result of different influence dimensions on the power station equipment through the weight and the evaluation index.

Optionally, the dynamic cost analysis is performed on the power station equipment through the predicted fault type and the predicted fault occurrence time point, so as to obtain the predicted repair cost of the power station equipment, including:

determining second power station equipment to be processed from the power station equipment through the predicted fault type;

acquiring the replacement cost and the maintenance cost of the second power station equipment;

determining the loss cost caused by the predicted fault type through the predicted fault occurrence time point;

And obtaining the predicted repair cost of different fault repair modes of the power station equipment according to the replacement cost, the maintenance cost and the loss cost, wherein the fault repair modes comprise replacement of the power station equipment or maintenance of the power station equipment.

Optionally, the determining the target fault handling decision for the power station device by the multi-dimensional influence result and the predicted repair cost further includes:

acquiring a first fault handling decision regarding the power plant equipment through the multi-dimensional impact result;

acquiring a second fault handling decision regarding the power plant equipment by means of the predicted repair costs;

And screening the first fault handling decision and the second fault handling decision through a preset strategy, and determining a target fault handling decision of the power station equipment.

Optionally, the screening the first fault handling decision and the second fault handling decision through a preset policy, determining a target fault handling decision for the power station device includes:

Under the condition that any single dimension influence result in the multi-dimension influence results is larger than a preset value, determining the first fault handling decision as a target fault handling decision for the power station equipment;

and under the condition that the single dimension influence result in the multi-dimension influence results is smaller than or equal to a preset value, determining the second fault handling decision as a target fault handling decision for the power station equipment.

Optionally, the optimizing the target fault handling decision in response to the feedback of the target fault handling decision on a preset user interaction page with a user further includes:

acquiring behavior mode information of operation and maintenance personnel;

Setting a user interaction page according to the behavior mode information;

processing the power station equipment through the target fault processing decision to obtain a processing result;

and according to the processing result, the feedback of the target fault processing decision is performed on the user interaction page, and the target fault processing decision is optimized.

Optionally, after the optimizing the target fault handling decision in response to the feedback of the target fault handling decision with the user on the preset user interaction page, the method further includes:

acquiring the actual fault restoration cost and the actual fault processing mode corresponding to the optimized target fault processing decision;

and integrating the real-time operation parameters, the predicted fault types, the predicted fault occurrence time points, the actual fault repair cost and the actual fault processing mode into a central database.

Optionally, the acquiring the real-time operation parameters of the power station equipment includes:

Deploying a plurality of sensors of different types in the power station equipment in advance;

different types of real-time operation parameters of the power station equipment are acquired through different types of sensors, wherein the real-time operation parameters comprise at least one of voltage, current and temperature of the power station equipment.

Optionally, after the acquiring the real-time operation parameters of the power station equipment, the method further includes:

Transmitting the real-time operating parameters to an edge computing device;

performing data cleaning and standardization processing on the real-time operation parameters through the edge computing equipment;

And extracting key features from the processed real-time operation parameters.

In a second aspect, the present invention provides a fault handling apparatus, the apparatus comprising:

The first acquisition module is used for acquiring real-time operation parameters of power station equipment;

the second acquisition module is used for carrying out fault prediction on the real-time operation parameters and acquiring the predicted fault type and the predicted fault occurrence time point of the power station equipment;

the third acquisition module is used for carrying out multidimensional influence assessment on the predicted fault type and acquiring a multidimensional influence result on the power station equipment;

The fourth acquisition module is used for carrying out dynamic cost analysis on the power station equipment through the predicted fault type and the predicted fault occurrence time point to acquire the predicted repair cost of the power station equipment;

the first determining module is used for determining a target fault processing decision of the power station equipment through the multi-dimensional influence result and the predicted repair cost;

And the decision optimization module is used for responding to the feedback of the target fault processing decision with a user on a preset user interaction page and optimizing the target fault processing decision.

In a third aspect, the invention provides an electronic device comprising a transceiver, a memory, a processor, and a program stored on the memory and executable on the processor;

the processor is configured to read a program in the memory to implement the fault handling method described in any of the above.

In a fourth aspect, the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform any of the above described fault handling methods.

In a fifth aspect, embodiments of the present invention provide a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the fault handling method according to the first aspect of the embodiments of the present invention.

According to the invention, the real-time operation parameters are obtained, the predicted fault type and the predicted fault occurrence time point of the power station equipment are obtained, predictive maintenance is realized, unexpected downtime is reduced, reliability of the power station is improved, multidimensional influence assessment is carried out on the predicted fault type, multidimensional influence results of the power station equipment are obtained, all important factors can be comprehensively considered in decision making, dynamic cost analysis is carried out on the power station equipment through the predicted fault type and the predicted fault occurrence time point, predicted repair cost of the power station equipment is obtained, economy of maintenance and replacement can be predicted and evaluated in real time, cost benefit maximization decision making is carried out by an operation and maintenance team, target fault processing decision of the power station equipment is determined through the multidimensional influence results and the predicted repair cost, processing decision is determined after comprehensive consideration, decision making efficiency and accuracy are improved, feedback of the target fault processing decision is carried out in response to a preset user interaction page, the target fault processing decision is optimized, the target fault processing decision making process is simplified, efficiency is improved through setting a user interaction page, and the operation and maintenance staff can rapidly obtain the target fault processing decision making process. In summary, the method and the system have the advantages that the faults are predicted in advance, the influence of the multiple dimensions on the faults is evaluated, the evaluation result is combined with the cost benefit of fault treatment, the target fault treatment decision of the power station equipment is determined, and then the target fault treatment decision is optimized by a user, so that the operation and maintenance cost is reduced, the fault treatment efficiency is improved, the availability and reliability of the power station are improved, and the user satisfaction degree is improved.

Drawings

In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of steps of a fault handling method provided by the present invention;

FIG. 2 is a flowchart of step 102 in the fault handling method provided by the present invention shown in FIG. 1;

FIG. 3 is a flowchart of step 103 in a fault handling method according to the present invention shown in FIG. 1;

FIG. 4 is a flowchart of step 104 in the fault handling method of FIG. 1 according to the present invention;

FIG. 5 is a system architecture diagram of a fault handling method provided by the present invention shown in FIG. 1;

FIG. 6 is a flow chart of a fault handling method provided by the present invention shown in FIG. 1;

FIG. 7 is a block diagram of a fault handling apparatus provided by the present invention;

fig. 8 is a block diagram of an electronic device provided by the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, fig. 1 is a flowchart illustrating steps of a fault handling method according to the present invention, as shown in fig. 1, the method may include:

And step 101, acquiring real-time operation parameters of power station equipment.

The power station equipment in the embodiment of the invention can comprise an energy storage battery system, wherein the energy storage battery system comprises a lithium ion battery, a lead-acid battery, a flow battery, a sodium-sulfur battery, a solid-state battery and the like, a battery management system, an energy storage converter (for converting direct current stored by the battery into alternating current or converting the alternating current into direct current for storage), a fire-fighting system, and a fire extinguishing device, such as a smoke detector, a gas fire extinguishing system (such as heptafluoropropane) or a water spraying system, a ventilation system, a transformer and the like.

In order to acquire real-time operation parameters of power station equipment, different types of sensors need to be deployed in advance, and then different types of real-time operation parameters can be acquired through the different types of sensors, and the specific steps comprise:

deploying a plurality of different types of sensors in the power station equipment in advance;

Different types of real-time operating parameters of the power station equipment are acquired through different types of sensors, wherein the real-time operating parameters comprise at least one of voltage, current and temperature of the power station equipment.

It should be noted that the different types of sensors may include a voltage sensor, a current sensor, a temperature sensor, an environmental humidity monitoring sensor, and a device vibration monitoring sensor. The real-time operating parameters may include humidity, pressure, vibration, etc., in addition to voltage, current and temperature, and the present invention is not particularly limited herein.

Further, after acquiring the real-time operation parameters, the edge computing device performs preliminary processing on the data, including data cleaning, standardization and feature extraction, and the specific steps include:

transmitting the real-time operating parameters to the edge computing device;

Performing data cleaning and standardization processing on the real-time operation parameters through edge computing equipment;

and extracting key features from the processed real-time operation parameters.

The data cleansing may be removing noise by using a filtering algorithm (e.g., kalman filtering), and the normalization may be performed by using a normalization algorithm (e.g., Z-score normalization algorithm) to perform data format unification. It should be noted that the acquired real-time operation parameters may be regarded as time-series data arranged in time series.

After the key features are extracted, the fault prediction can be performed through the key features.

And 102, carrying out fault prediction on the real-time operation parameters, and obtaining the predicted fault type and the predicted fault occurrence time point of the power station equipment.

When the embodiment of the invention predicts faults of real-time operation parameters, an autoregressive integral moving average model and a deep learning model are needed, and other models, such as a seasonal autoregressive integral moving average model, an exponential smoothing model, a support vector machine and the like, can be used. Taking autoregressive integral moving average model as an example, the model needs to be pre-trained firstly when being used, and the pre-training needs to collect the historical data of power station equipment, because the embodiment of the invention uses real-time operation parameters, the type of fault to be detected and the occurrence time point are predicted, so that the collected historical data is also required to include these factors, namely, the historical data includes the historical operation parameters of the power station equipment, the occurrence time point of the historical fault and the type of the historical fault. And training the autoregressive integral moving average model through historical data to obtain a predicted fault occurrence time point of the power station equipment, and training the deep learning model through the historical data to obtain a predicted fault type of the power station equipment.

When the model parameter is determined, the model parameter can be optimized and adjusted (such as a recursive least square method) by calculating the prediction result and the error value of the actual result of the model, until the error value meets the requirement, the model parameter is the expected model parameter, then the autoregressive integral sliding average model with the expected model parameter is used for predicting the real-time operation parameter, and the predicted fault occurrence time point of the power station equipment is obtained, which comprises the following specific steps:

Collecting historical data of power station equipment, wherein the historical data comprises historical operation parameters of the power station equipment, historical fault occurrence time points and historical fault types;

Respectively pre-training an autoregressive integral moving average model and a deep learning model through historical data;

Inputting real-time operation parameters into a pre-trained autoregressive integral moving average model to obtain a predicted fault occurrence time point of power station equipment;

And inputting the real-time operation parameters into a pre-trained deep learning model to obtain the predicted fault type of the power station equipment.

It should be noted that, when new data prediction is performed on the pre-trained autoregressive integral moving average model and the deep learning model, optimization adjustment is continuously performed according to the new data.

Predicting real-time operation parameters through the pre-trained autoregressive integral moving average model, obtaining predicted operation parameters in a future period of time, checking whether the predicted operation parameters exceed a preset fault threshold value, if so, recording corresponding first power station equipment, parameter types and time points, determining the predicted fault types and occurrence time points according to the first power station equipment and the parameter types and the time points exceeding the threshold value, and if all the predicted operation parameters do not exceed the threshold value, judging that the equipment has no fault risk in the preset time period. Specifically, step 102, as shown in fig. 2:

and 1021, performing fault prediction on the real-time operation parameters to obtain a plurality of predicted operation parameters of the power station equipment in a preset time period.

Step 1022, if any predicted operation parameter is greater than or equal to the preset fault threshold, obtaining the first power station equipment corresponding to the predicted operation parameter, the target parameter type and the target time point.

Step 1023, obtaining the predicted fault type and the predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point.

Step 1024, if the plurality of predicted operation parameters are smaller than the preset fault threshold, determining that the power station equipment has no fault risk in the preset time period.

By way of example, it is assumed that the real-time operating parameters of the device of an electrochemical energy storage station are as follows, the voltage in the battery module a is 220V, the current is 10A, the temperature is 25 ℃, the voltage in the battery module B is 215V, the current is 12A, the temperature is 28 ℃, the operating parameters within 24 hours of the future are predicted, the battery module a is the voltage in [220,221,222 ], the voltage in [ 235], the current in [10,11,12 ], the voltage in [ 15] a, the temperature in [25,26,27 ], the voltage in [ 30], the battery module B is the voltage in [215,216,217 ], the voltage in [220 ] V, the current in [12,13,14 ], the voltage in [ 18] a, the temperature in [28,29,30 ], the preset fault threshold of the voltage is 230V, the preset fault threshold of the current is 20A, the preset fault threshold of the temperature is 40 ℃, the voltage in the battery module a is 230V in the 12 hours of the power station, so that the first device is the voltage in the "when the target device a is the type of the voltage is the high, and the predicted time is the type of the high, and the fault condition of the battery module is the predicted when the target type of the voltage is the high, and the fault condition is the predicted is the type of the high. Since all of the predicted operating parameters of "battery module B" do not exceed the threshold value, it is determined that "battery module B" does not present a risk of failure. Likewise, if all the predicted operating parameters of the power station equipment are smaller than the preset fault threshold, the prediction is considered to be fault-free.

By the method, the time sequence analysis is carried out on the equipment faults, and the accuracy of fault prediction is improved. In addition, through continuous adjustment and optimization of the autoregressive integral moving average model, potential faults can be early warned more accurately in advance, and unexpected downtime is reduced.

And step 103, performing multidimensional influence assessment on the predicted fault type, and obtaining a multidimensional influence result on power station equipment.

After the predicted fault type is determined, the influence dimension to be considered when the fault type is explicitly estimated is also determined, and the comprehensiveness and scientificity of the estimation are ensured, wherein the influence dimension can be an economic influence dimension, the influence of the fault on the economic benefit of the power station can be estimated through the dimension, such as maintenance cost, power generation loss and the like, the influence of the fault on the environment can be estimated through the dimension, such as energy waste, emission increase and the like, and the influence of the fault on the society can be estimated through the dimension, such as power supply reliability, user satisfaction and the like. Based on expert experience, historical data or related research, weight is allocated to each influence dimension, specific evaluation indexes are set, scientificity and operability of evaluation are guaranteed, single-dimension influence results of different influence dimensions are calculated according to the weight and the evaluation indexes, comprehensive dimension influence results are comprehensively obtained, and in particular, step 103 is shown in fig. 3:

step 1031, predetermines different impact dimensions associated with the predictive failure type assessment.

Step 1032, different weights and different evaluation indexes are set for different influence dimensions.

And 1033, determining a single dimension influence result and a comprehensive dimension influence result of different influence dimensions on the power station equipment through the weights and the evaluation indexes.

Wherein the impact dimension includes an economic impact dimension, an environmental impact dimension and a social impact dimension.

For example, the predicted fault types include a battery module a with overheated battery, the related different influence dimensions include an economic influence dimension (maintenance cost 5000 yuan, power generation loss 10000 yuan), an environmental influence dimension (energy waste 200kWh, emission 100kg CO2 increased) and a social influence dimension (power supply reliability 10% decrease, user satisfaction 5%) set as weight conditions of 0.5 for the economic influence dimension, 0.3 for the environmental influence dimension, 0.2 for the social influence dimension, maintenance cost, power generation loss for the economic influence dimension, energy waste, emission increase for the social influence dimension, power supply reliability 10000 yuan (power generation loss) =15000 yuan for the calculated single dimension influence result, 200kWh (energy waste) +100kg CO2 (emission increase) 300 for the social influence result 10% (reliability decrease) +5% (user satisfaction decrease) =15×00×3+20.7500+20+20.7500 for the calculated single dimension influence result.

By performing multidimensional influence assessment, not only is the influence of faults on economy considered, but also the influence of the faults on environment and society is considered, so that the decision is more comprehensive and responsible.

And 104, carrying out dynamic cost analysis on the power station equipment through the predicted fault type and the predicted fault occurrence time point to obtain the predicted repair cost of the power station equipment.

In the embodiment of the invention, the multi-dimensional influence evaluation is carried out on the predicted fault type, and the fault repair cost is also predicted. Firstly, determining equipment (second power station equipment) to be processed according to a predicted fault type, then acquiring replacement cost and maintenance cost of the second power station equipment, providing data support for subsequent cost analysis, calculating loss cost caused by a fault according to a predicted fault occurrence time point, integrating the replacement cost, the maintenance cost and the loss cost, and calculating a prediction result of fault repair cost, specifically, step 104 is shown in fig. 4:

in step 1041, a second power plant to be processed is determined from the power plant by predicting the fault type.

Step 1042, the replacement cost and maintenance cost of the second power station equipment are obtained.

In step 1043, the cost of loss due to the predicted fault type is determined by predicting the fault occurrence time point.

Step 1044, obtaining the predicted repair costs related to different fault repair modes of the power station equipment through the replacement costs, the maintenance costs and the loss costs.

Among these, the above-described different fault restoration methods with respect to the power plant equipment include replacement of the power plant equipment (second power plant equipment) or maintenance of the power plant equipment (second power plant equipment). The replacement cost can include equipment replacement cost and installation and debugging cost, the maintenance cost can include equipment maintenance cost and maintenance personnel cost, and the loss cost can include power generation loss cost and other loss cost. The predicted repair costs include a predicted repair cost of the replacement mode, at which time the predicted repair cost=the replacement cost+the loss cost, and a predicted repair cost of the repair mode, at which time the predicted repair cost=the repair cost+the loss cost.

For example, assuming that the type of the predicted fault is overheating of the battery module a, the occurrence time point of the predicted fault is 12 hours, the second power station equipment is determined to be the battery module a, the replacement cost of the battery module a is 20000 yuan and the maintenance cost is 5000 yuan, because the power generation is reduced due to overheating of the battery, the power generation loss cost is 10000 yuan, at this time, the predicted repair cost of the replacement mode is 20000 yuan+10000 yuan=30000 yuan, and the predicted repair cost of the maintenance mode is 5000 yuan+10000 yuan=15000 yuan.

The steps provide quantitative economic evaluation for maintenance and replacement, and help operation and maintenance personnel to make more economic decisions.

The cost prediction may be achieved by an exponential smoothing method. In addition, when the cost of the maintenance mode is predicted, the service life of the equipment after maintenance and the service life of the equipment after replacement can be considered, and the service life of the equipment after maintenance and the service life of the equipment after replacement can be turned into the discount cost, so that the economy of the maintenance mode can be more comprehensively evaluated. The method comprises the following steps:

Obtaining the residual service life of the second power station equipment after maintenance;

acquiring the total service life of the second power station equipment;

the discount rate is used for discount the benefits of the residual service life into a first discount cost and discount the benefits of the total service life into a second discount cost;

Obtaining a predicted repair cost in a repair mode through the first discount cost, the loss cost and the repair cost;

and obtaining the predicted repair cost in the replacement mode through the second discount cost, the loss cost and the replacement cost.

Wherein discount cost = benefit of usable lifetime/(1+ discount rate)/(years)

For example, if the service life of the battery module a after maintenance is 2 years, the discount rate is 5%, the benefit of 2 years after maintenance is 10000 yuan, the first discount cost of the service life of 2 years after maintenance=10000/(1+0.05)/(2=9070 yuan, corresponding to the predicted repair cost in the maintenance mode=5000 yuan (maintenance cost) +10000 yuan (loss cost) -9070 yuan (discount cost) =5930 yuan, if the service life of the battery module a after replacement is 10 years, the benefit is 50000 yuan, the second discount becomes 50000/(1+0.05)/(10=306995 yuan, and the predicted repair cost in the replacement mode=20000 yuan+10000 yuan-306995 yuan= -695 yuan.

By the aid of the method, an operation and maintenance team is helped to avoid unnecessary maintenance and premature equipment replacement, so that long-term operation and maintenance cost is reduced.

And 105, determining a target fault processing decision of the power station equipment through the multidimensional influence result and the predicted repair cost.

In the embodiment of the invention, the multidimensional influence result and the predicted repair cost are comprehensively considered through an intelligent decision tree based on a CART algorithm, and the target fault processing decision of the power station equipment is finally determined, and the specific steps comprise:

Acquiring a first fault handling decision concerning the power plant equipment through the multi-dimensional influence result;

acquiring a second fault handling decision regarding the power plant equipment by predicting repair costs;

It should be noted that, the step of screening the first fault handling decision and the second fault handling decision by the preset strategy, and determining the target fault handling decision for the power station equipment includes:

under the condition that any single dimension influence result in the multi-dimension influence results is larger than a preset value, determining a first fault processing decision as a target fault processing decision for power station equipment;

and under the condition that the single dimension influence result in the multi-dimension influence results is smaller than or equal to a preset value, determining the second fault processing decision as a target fault processing decision for the power station equipment.

For example, if the economic impact result is 5000 yuan, the power generation loss is 10000 yuan, the cost is 15000 minutes, the environmental impact result is 200kWh, the emission is 100kg CO2, the cost is 300 minutes, the social impact result is 10 percent of power supply reliability, 5 percent of user satisfaction is 15 minutes. The preset value of the set economic impact result is 15000, the preset value of the environment impact result is 300, the preset value of the social impact result is 20 minutes, and because all the single-dimension impact results are smaller than or equal to the preset value, the target fault handling decision of the power station equipment is determined through the predicted repair cost, and because the predicted repair cost in a maintenance mode is 5930 yuan and the predicted repair cost in a replacement mode is 695 yuan, the target fault handling decision of the power station equipment is to replace the second power station equipment with faults. If the preset value of the set economic impact result is 15000, the preset value of the environmental impact result is 200, and the preset value of the social impact result is 20 minutes, because the environment impact result is 300>200, before considering the cost, the environmental protection strategy needs to be prioritized, and because the environmental pollution caused by replacement is more serious, the maintenance mode is prioritized, namely the target fault handling decision on the power station equipment is to maintain the second power station equipment with fault.

By the method, the optimal maintenance or replacement strategy based on the current data and the predicted result is provided for the operation and maintenance personnel, so that the complexity and uncertainty of the decision are reduced, and the efficiency and effect of the decision are improved.

And step 106, responding to feedback of the target fault processing decision with the user on a preset user interaction page, and optimizing the target fault processing decision.

In the embodiment of the invention, the behavior mode of the operation and maintenance personnel is also analyzed by using K-means clusters. User interaction pages are designed based on the behavior patterns of the operation and maintenance personnel, for example, the operation and maintenance personnel often view the running states and historical fault records of specific devices, at which time the states of the devices can be automatically placed in the conspicuous positions of the instrument panel, or quick links of the devices can be provided when the users log in, or some operation and maintenance personnel can be more prone to making decisions based on cost benefit analysis, while others can be more focused on the instant states of the devices, at which time customized decision support tools and reports can be provided according to the user's preference, such as highlighting economic analysis for cost-oriented users, and real-time monitoring data for state-oriented users. Or the user may be accustomed to using a particular operational procedure, such as first viewing alarm information and then viewing detailed status of the associated device. At this time, an intuitive workflow can be designed to guide the user to operate according to the habit of the user, or a customizable workflow can be provided to enable the user to set the operation sequence according to the habit of the user. Or some users may prefer charts and graphics to obtain information while others may prefer text reports. Various information presentation modes can be provided at this time, and the user is allowed to select a chart, a graph or a text format according to own preference. Or in the event of a fault, some operators may require immediate notification of the system, while others may have less stringent reaction time requirements for non-emergency situations. At this time, different notification priorities and notification modes, such as short messages, mails or in-application notifications, can be set according to the sensitivity of the user to the response time. Or the user may follow specific steps in handling the fault, such as first performing a fault diagnosis, then looking up spare parts, and finally performing maintenance. At this time, a structured fault handling interface may be provided, which guides the user to complete each operation according to the flow that the user is accustomed to.

After the decision of determining the target fault processing is carried out, comprehensive testing is needed in the actual power station environment, fault processing results including processing time, processing cost, equipment state and the like are recorded, the accuracy, reliability and user satisfaction of the system are verified according to the processing results, and optimization is carried out according to feedback. The method comprises the following specific steps of:

acquiring behavior mode information of operation and maintenance personnel;

Setting a user interaction page through behavior mode information;

Processing the power station equipment through a target fault processing decision to obtain a processing result;

The behavior patterns can be divided into two types, namely a maintenance preference type and a replacement preference type, wherein maintenance options are highlighted on a page according to the behavior patterns of maintenance preference type operation and maintenance personnel, and replacement options are highlighted on the page according to the behavior patterns of replacement preference type operation and maintenance personnel. The user can evaluate and feed back the processing result, the feedback content can be the score of the target fault processing decision, the satisfaction is 10 points, and the dissatisfaction is 1 point. The target fault handling decision may be further adjusted based on the feedback content. The user interface of the above process can display the state of the power station equipment, the predicted fault type and the predicted fault occurrence time point during fault prediction, the influence evaluation result on the predicted fault type and the target fault processing decision on the power station equipment, and provide a customized view and an interactive tool.

The behavior mode of the operation and maintenance personnel is analyzed in the process, so that the user interaction interface and interaction flow are optimized, the usability and user satisfaction of the system are improved, and the long-term stable operation and continuous improvement of the system are ensured by the test and feedback loop.

Further, after the test result is obtained, all the data obtained at this time are integrated in a central database, and the data warehouse technology is used for effective management, and the specific steps include:

By integrating the data in the mode, a large amount of time consumption caused by information dispersion can be avoided, and the efficiency of operation and maintenance management is improved.

It should be noted that, the fault processing method of the embodiment of the present invention may be implemented by an intelligent operation and maintenance management system of a power station, as shown in fig. 5, where the intelligent operation and maintenance management system includes a data acquisition layer, a data processing layer, a decision support layer and a user interaction layer. The data acquisition layer comprises a sensor network, a data preprocessing module, an autoregressive integral moving average model, a multi-dimensional evaluation model, a cost prediction model and a decision tree algorithm model, wherein the sensor network is used for acquiring real-time operation parameters of power station equipment, the data preprocessing module is used for carrying out data cleaning, standardization and feature extraction operation on the real-time operation parameters, the decision support layer analyzes fault prediction results, influence evaluation results and cost benefit analysis results and determines maintenance or replacement strategies, the autoregressive integral moving average model is used for acquiring fault prediction results (comprising a predicted fault type and a predicted fault occurrence time point), the multi-dimensional evaluation model is used for acquiring influence evaluation results (corresponding multi-dimensional influence results) and cost benefit analysis results (corresponding predicted repair costs), the decision tree algorithm model is used for determining maintenance or replacement strategies (corresponding target fault processing decisions), and the user interaction layer is used for setting user interaction interfaces and interactive tools (such as shortcut keys) and feedback systems.

Specifically, the functions in the intelligent operation and maintenance management system of the power station comprise data acquisition, fault prediction, influence assessment, cost prediction, decision analysis, decision support, data management, user interaction and feedback improvement as shown in fig. 6. Wherein the data acquisition comprises sensor data acquisition, data cleaning and feature extraction, the fault prediction analyzes real-time operation parameters forming a time sequence through an adaptive fault prediction algorithm, model parameters are estimated firstly through an autoregressive integral moving average model, model training is carried out to obtain model parameters conforming to expectations, the fault prediction is carried out through the autoregressive integral moving average model after pretraining, a fault prediction result (comprising a predicted fault type and a predicted fault occurrence time point) is output, the influence assessment is realized through a multidimensional assessment model, the weight distribution is required to be carried out on the influence dimension of the multidimensional assessment model firstly, the multidimensional influence result is obtained through a hierarchical analysis method, the cost prediction is realized through a cost prediction model, the cost is predicted by an exponential smoothing method, the predicted repair cost is obtained, the maintenance and replacement economy is further evaluated by an NPV algorithm, the target predicted repair cost is obtained, the decision support is to determine maintenance or replacement strategies by an intelligent decision tree, the data management is to integrate and manage data, the information is integrated into a central database, the central database is used for management, the subsequent data query and data retrieval are convenient, the user interaction is user interface and interaction design, the user interaction interface is arranged, the user interaction interface comprises an interactive tool and a feedback system, the feedback improvement is realized by carrying out actual performance test on a target fault processing decision, and then the user feedback is collected for optimization adjustment.

Fig. 7 is a block diagram of a fault handling apparatus according to the present invention, which may include:

a first obtaining module 201 is configured to obtain real-time operation parameters of the power station equipment.

The second obtaining module 202 is configured to perform fault prediction on the real-time operation parameter, and obtain a predicted fault type and a predicted fault occurrence time point for the power station device.

And the third obtaining module 203 is configured to perform multidimensional influence assessment on the predicted fault type, and obtain a multidimensional influence result on the power station equipment.

And a fourth obtaining module 204, configured to obtain a predicted repair cost of the power plant equipment by performing dynamic cost analysis on the power plant equipment through the predicted fault type and the predicted fault occurrence time point.

A first determining module 205 is configured to determine a target fault handling decision for the power plant device by affecting the result and predicting the repair cost in multiple dimensions.

The decision optimization module 206 is configured to optimize the target fault handling decision in response to feedback of the target fault handling decision on a preset user interaction page with a user.

Optionally, the second obtaining module 202 specifically includes:

And the acquisition sub-module is used for acquiring historical data of the power station equipment, wherein the historical data comprises historical operation parameters of the power station equipment, historical fault occurrence time points and historical fault types.

And the first determining submodule is used for respectively pre-training the autoregressive integral moving average model and the deep learning model through historical data and determining expected model parameters.

The first acquisition submodule is used for inputting real-time operation parameters into the pre-trained autoregressive integral moving average model to acquire a predicted fault occurrence time point of power station equipment;

And the second acquisition sub-module is used for inputting real-time operation parameters into the pre-trained deep learning model to acquire the predicted fault type of the power station equipment.

And the third acquisition sub-module is used for carrying out fault prediction on the real-time operation parameters and acquiring a plurality of predicted operation parameters of the power station equipment in a preset time period.

And the fourth acquisition sub-module is used for acquiring the first power station equipment corresponding to the predicted operation parameter, the target parameter type and the target time point if any predicted operation parameter is greater than or equal to a preset fault threshold.

And the fifth acquisition sub-module is used for acquiring the predicted fault type and the predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point.

And the judging sub-module is used for judging that the power station equipment has no fault risk in a preset time period if the plurality of predicted operation parameters are smaller than a preset fault threshold value.

Optionally, the third obtaining module 203 specifically includes:

A second determination sub-module for predetermining different impact dimensions associated with the predictive failure type assessment, the impact dimensions including an economic impact dimension, an environmental impact dimension and a social impact dimension.

The first setting submodule is used for setting different weights and different evaluation indexes for different influence dimensions.

And the third determining submodule is used for determining a single dimension influence result and a comprehensive dimension influence result of different influence dimensions on the power station equipment through the weight and the evaluation index.

Optionally, the fourth obtaining module 204 specifically includes:

And a fourth determination submodule for determining a second power plant equipment to be processed from the power plant equipment by predicting the fault type.

And the sixth acquisition submodule is used for acquiring the replacement cost and the maintenance cost of the second power station equipment.

And a fifth determining sub-module for determining the cost of loss caused by the predicted fault type by predicting the fault occurrence time point.

And a seventh obtaining sub-module, configured to obtain, through the replacement cost, the maintenance cost and the loss cost, predicted repair costs related to different fault repair modes of the power plant equipment, where the fault repair modes include replacement of the power plant equipment or maintenance of the power plant equipment.

Optionally, the first determining module 205 specifically includes:

And an eighth acquisition sub-module, configured to acquire a first fault handling decision about the power plant equipment through the multi-dimensional impact result.

And a ninth acquisition sub-module for acquiring a second fault handling decision regarding the power plant equipment by predicting repair costs.

And the sixth determining submodule is used for screening the first fault processing decision and the second fault processing decision through a preset strategy and determining a target fault processing decision of the power station equipment.

Optionally, the sixth determining submodule specifically includes:

And the first determining unit is used for determining the first fault handling decision as the target fault handling decision for the power station equipment under the condition that any one single dimension influence result in the multi-dimension influence results is larger than a preset value.

And the second determining unit is used for determining the second fault handling decision as the target fault handling decision for the power station equipment under the condition that the single dimension influence result in the multi-dimension influence results is smaller than or equal to the preset value.

Optionally, the decision optimization module 206 specifically includes:

and a tenth acquisition sub-module for acquiring the behavior pattern information of the operation and maintenance personnel.

And the second setting sub-module is used for setting the user interaction page through the behavior mode information.

And the eleventh acquisition sub-module is used for processing the power station equipment through the target fault processing decision to acquire a processing result.

And the decision optimization sub-module is used for optimizing the target fault processing decision according to the feedback of the processing result to the target fault processing decision on the user interaction page.

Optionally, the fault handling apparatus further includes:

And the fifth acquisition module is used for acquiring the actual fault restoration cost and the actual fault processing mode corresponding to the optimized target fault processing decision.

And the integration module is used for integrating the real-time operation parameters, the predicted fault types, the predicted fault occurrence time points, the actual fault repair cost and the actual fault processing mode into the central database.

Optionally, the first obtaining module 201 specifically includes:

a deployment sub-module for deploying in advance a number of different types of sensors in the power plant equipment.

A twelfth acquisition sub-module is used for acquiring different types of real-time operation parameters of the power station equipment through different types of sensors, wherein the real-time operation parameters comprise at least one of voltage, current and temperature of the power station equipment.

Optionally, the fault handling apparatus further includes:

and the transmission module is used for transmitting the real-time operation parameters to the edge computing equipment.

And the data processing module is used for carrying out data cleaning and standardization processing on the real-time operation parameters through the edge computing equipment.

And the feature extraction module is used for extracting key features from the processed real-time operation parameters.

The invention also provides an electronic device, as shown in fig. 8, comprising a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, the memory 303 complete the communication with each other through the communication bus 304,

A memory 303 for storing a computer program;

The processor 301 is configured to execute the program stored in the memory 303, and implement the following steps:

acquiring real-time operation parameters of power station equipment;

The communication bus mentioned by the above terminal may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, etc. The communication bus may be classified as a physical address bus, a data bus, a control bus, etc. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the terminal and other devices.

The memory may include random access memory (Random Access Memory, RAM) or may include non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central Processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a digital signal processor (DIGITAL SIGNAL Processing, DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

The present invention also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the fault handling method according to any of the above embodiments of the present invention.

The invention also provides a computer program product comprising computer programs/instructions which when executed by a processor implement the steps in a fault handling method according to any of the above embodiments of the invention.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a sorting device according to the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention may also be implemented as an apparatus or device program for performing part or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

It should be noted that, in the embodiment of the present invention, the related processes of obtaining various data are all performed under the premise of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.

Claims

1. A method of fault handling, the method comprising:

acquiring real-time operation parameters of power station equipment;

2. The method of claim 1, wherein said performing fault prediction on said real-time operating parameters to obtain a predicted fault type and a predicted fault occurrence time point for said power plant equipment comprises:

3. The method of claim 1, wherein said performing fault prediction on said real-time operating parameters to obtain a predicted fault type and a predicted fault occurrence time point for said power plant equipment comprises:

4. The method of claim 1, wherein the performing the multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power plant equipment comprises:

5. The method according to claim 1, wherein said dynamically analyzing the cost of the power plant by the predicted fault type and the predicted fault occurrence time point to obtain a predicted repair cost of the power plant comprises:

6. The method of claim 1, wherein said determining a target fault handling decision for said power plant equipment by said multi-dimensional impact result and said predicted repair cost further comprises:

7. The method of claim 6, wherein the screening the first and second fault handling decisions by a preset strategy to determine a target fault handling decision for the power plant equipment comprises:

8. The method of claim 1, wherein the optimizing the target fault handling decision in response to feedback on the target fault handling decision with a user on a preset user interaction page further comprises:

acquiring behavior mode information of operation and maintenance personnel;

Setting a user interaction page according to the behavior mode information;

9. The method of claim 1, further comprising, after said optimizing said target fault handling decision in response to feedback to said target fault handling decision on a preset user interaction page with a user:

10. The method of claim 1, wherein the obtaining real-time operating parameters of the power plant equipment comprises:

11. The method of claim 1, further comprising, after said obtaining real-time operating parameters of the power plant equipment:

Transmitting the real-time operating parameters to an edge computing device;

And extracting key features from the processed real-time operation parameters.

12. A fault handling apparatus, the apparatus comprising:

13. An electronic device comprising a transceiver, a memory, a processor, and a program stored on the memory and executable on the processor;

the processor being arranged to read a program in a memory for implementing the steps of the fault handling method according to any of claims 1-11.

14. A readable storage medium for storing a program, wherein the stored program, when executed by a processor, implements the steps of the fault handling method as claimed in any one of claims 1 to 11.

15. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps in the fault handling method according to any of claims 1-11.