[go: up one dir, main page]

CN118694452B - Audio communication control method and system based on mine - Google Patents

Audio communication control method and system based on mine Download PDF

Info

Publication number
CN118694452B
CN118694452B CN202411180155.8A CN202411180155A CN118694452B CN 118694452 B CN118694452 B CN 118694452B CN 202411180155 A CN202411180155 A CN 202411180155A CN 118694452 B CN118694452 B CN 118694452B
Authority
CN
China
Prior art keywords
gas concentration
data
conductivity
mine
electromagnetic wave
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411180155.8A
Other languages
Chinese (zh)
Other versions
CN118694452A (en
Inventor
肖耀猛
赵国志
孙峰
彭蓬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yankuang Energy Group Co Ltd
Original Assignee
Yankuang Energy Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yankuang Energy Group Co Ltd filed Critical Yankuang Energy Group Co Ltd
Priority to CN202411180155.8A priority Critical patent/CN118694452B/en
Publication of CN118694452A publication Critical patent/CN118694452A/en
Application granted granted Critical
Publication of CN118694452B publication Critical patent/CN118694452B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/373—Predicting channel quality or other radio frequency [RF] parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/12—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/12—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality
    • H04W40/14—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality based on stability
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/12—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality
    • H04W40/16—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality based on interference
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/22—Communication route or path selection, e.g. power-based or shortest path routing using selective relaying for reaching a BTS [Base Transceiver Station] or an access point
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/34—Modification of an existing route
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Feedback Control In General (AREA)

Abstract

本发明涉及煤矿矿井通信技术领域，具体涉及一种基于矿井音频通信控制方法及系统，包括以下步骤：实施岩层电导率实时监测，采用传感器网络分布于煤矿井关键区域，持续监测岩层电导率变化；配置煤层瓦斯监测设备，实时探测各作业区域的瓦斯浓度；在中心处理单元中，根据接收到的岩层电导率和瓦斯浓度分布数据，运用机器学习算法分析当前井下环境的电磁波传播条件，预测通信链路的质量和稳定性；根据电磁波传播条件和通信链路质量评估，动态调整传输路径；实施环境自适应信号编码技术。本发明，增强了无线电磁波通信的自适应能力，也最大化了通信的效率和可靠性。

The present invention relates to the field of coal mine communication technology, and specifically to a method and system based on mine audio communication control, including the following steps: implementing real-time monitoring of rock stratum conductivity, using a sensor network distributed in key areas of coal mines, and continuously monitoring changes in rock stratum conductivity; configuring coal seam gas monitoring equipment to detect gas concentrations in each operating area in real time; in a central processing unit, according to the received rock stratum conductivity and gas concentration distribution data, using a machine learning algorithm to analyze the electromagnetic wave propagation conditions of the current underground environment, and predict the quality and stability of the communication link; according to the electromagnetic wave propagation conditions and the communication link quality evaluation, dynamically adjusting the transmission path; and implementing environmental adaptive signal coding technology. The present invention enhances the adaptive ability of wireless electromagnetic wave communication and maximizes the efficiency and reliability of communication.

Description

Mine-based audio communication control method and system
Technical Field
The invention relates to the technical field of mine communication, in particular to a mine audio communication control method and system.
Background
In a mine underground audio communication system, stable and reliable communication is a key for ensuring the safety of miners and improving the production efficiency, and the conventional mine underground audio communication system faces various challenges, including complex underground environment, non-uniformity of rock stratum conductivity and the existence of gas such as gas and the like, which can interfere with the propagation of electromagnetic waves, so that communication is unstable and signal quality is reduced. Furthermore, conventional approaches often lack flexibility and adaptation in dynamically adjusting the communication link to cope with environmental changes.
In response to these problems, there have been recent attempts to optimize mine communication networks using advanced communication techniques and machine learning algorithms, which aim to improve the robustness and reliability of the communication system by monitoring downhole environmental parameters (such as formation conductivity and gas concentration) in real time and dynamically adjusting the communication links. However, the prior art still faces challenges in accurately predicting and adapting to complex environmental changes, and on this basis, the need for efficient and stable communications is realized.
Therefore, it is important to develop a system that can accurately analyze the downhole environmental impact, predict the quality of the communication link, and dynamically adjust the communication strategy based on real-time environmental data to achieve stable and reliable communication in constantly changing mine environments.
Disclosure of Invention
Based on the above purpose, the invention provides a mine-based audio communication control method and system.
The invention discloses a mine audio communication control method, which comprises the following steps:
S1: implementing real-time monitoring of the conductivity of the rock stratum, distributing the sensor network in a key area of a coal mine, continuously monitoring the conductivity change of the rock stratum, and transmitting the conductivity data of the rock stratum to a central processing unit in real time;
S2: configuring coal seam gas monitoring equipment, detecting the gas concentration of each operation area in real time, and transmitting gas concentration distribution data to a central processing unit;
S3: in the central processing unit, according to the received rock stratum conductivity and gas concentration distribution data, analyzing electromagnetic wave propagation conditions of the current underground environment by using a machine learning algorithm, and predicting the quality and stability of a communication link;
s4: realizing a dynamic routing protocol, dynamically adjusting a transmission path according to electromagnetic wave propagation conditions and communication link quality evaluation, avoiding an area with serious interference and attenuation, deploying a movable wireless relay node, and automatically adjusting physical position and configuration by the wireless relay node according to the dynamically adjusted transmission path so as to construct an optimal communication link;
S5: and (3) implementing an environment self-adaptive signal coding technology, dynamically adjusting a coding scheme according to real-time monitoring data of rock stratum conductivity and gas concentration distribution in an optimal communication link, and automatically optimizing redundancy and error correction capability of electromagnetic waves by adopting an optimization model so as to adapt to the current transmission condition.
Further, the step S1 comprises the steps of deploying a multipoint conductivity sensor on a main channel and a working surface of the underground coal mine, directly measuring the conductivity of the rock, and transmitting the monitored conductivity data to a central processing unit in real time through a wireless network.
Further, the machine learning algorithm in the step S3 is based on an improved long-short-term memory network LSTM model, the central processing unit firstly preprocesses the received rock stratum conductivity and gas concentration data, adopts the LSTM model to analyze the influence of the rock stratum conductivity and the gas concentration on the electromagnetic wave propagation, processes time series data, identifies modes and trends in the data, and predicts the propagation performance of the electromagnetic wave under different underground environment conditions;
the communication link is simulated and analyzed to predict link quality and stability at current mine conditions, including signal strength, signal to noise ratio, data transmission rate, and outage conditions.
Further, the analysis of the influence of the rock stratum conductivity and the gas concentration on the electromagnetic wave propagation by adopting the LSTM model specifically comprises the following steps:
S31: characteristic engineering: integrating the conductivity, gas concentration distribution and depth multidimensional features of the rock stratum, constructing a comprehensive feature set to capture complex factors influencing electromagnetic wave propagation, performing space-time feature mapping, and integrating spatial positions (such as depth from an inlet and specific roadway positions) and time factors into the comprehensive feature set to simulate the actual propagation process of the electromagnetic wave in a mine;
S32: model building and training: constructing an LSTM model, designing an LSTM network architecture, comprising a plurality of LSTM units, wherein the LSTM units comprise an input layer, a plurality of LSTM layers and an output layer, the number and configuration of the LSTM layers are determined according to the complexity and the data quantity of the problem, the LSTM model is trained by using historical data, and in training, how to predict the propagation performance of electromagnetic waves based on the historical and current values of the conductivity and the gas concentration of a rock stratum is learned;
S33: real-time analysis and prediction: input data to be collected in real time Inputting a trained LSTM model, predicting propagation performance of electromagnetic waves based on current and past data trends, including electromagnetic wave attenuation, signal attenuation and interference areas, interpreting the output of the LSTM model, determining predicted values of the propagation performance of electromagnetic waves, and using the predicted values to dynamically adjust a communication strategy.
Further, the spatio-temporal feature map is included in the input dataCombining space-time characteristics, combining the rock stratum conductivity and the gas concentration with the corresponding spatial position and time information to form a complex input characteristic vector so as to capture the time and space dependency relationship, wherein the method specifically comprises the following steps:
spatial position coding: distributing a unique geographic tag for each monitoring point in the mine, converting the geographic tag into a digital form by using a single thermal code, and using the geographic tag as an input characteristic in a model;
And (3) time factor integration: converting the time stamp of data acquisition into a format which can be understood by a model, calculating a time interval from a time point of monitoring, converting time into a continuous numerical value, reflecting the duration from the monitoring to the present, combining the converted time numerical value with conductivity and gas concentration to form a time sequence data set, and training an LSTM model;
Model training is carried out by combining space-time characteristics: combining the space position code and the time factor with the sensor data to form a comprehensive feature vector, wherein the feature vector can be [ space code, time value, conductivity and gas concentration ] for the data of each time point, and the constructed comprehensive feature vector is used as the input of an LSTM model, so that the model simultaneously learns the space-time dependency relationship in the electromagnetic wave propagation process.
Further, the step S4 specifically includes:
receiving LSTM model output: the central processing unit periodically receives prediction data generated by the improved LSTM model, including electromagnetic wave propagation condition predictions for each monitoring point;
Calculating an optimal path: calculating an optimal communication path avoiding interference and attenuation areas by using a dynamic routing algorithm and combining a prediction result of an LSTM model;
Dynamically adjusting a transmission path: dynamically updating a routing table according to the calculated optimal path, adjusting the transmission path of data, and ensuring that electromagnetic waves are transmitted through the optimal path;
deploying and adjusting wireless relay nodes: according to the dynamically adjusted transmission path, the deployment and position adjustment of the wireless relay node are guided, the wireless relay node is provided with automatic positioning and moving functions, and the physical position and configuration are adjusted according to the instruction of the central processing unit so as to support a new optimal communication link.
Further, the dynamic routing algorithm uses a Dijkstra algorithm based on a graph, and specifically includes:
modeling a mine propagation network: modeling electromagnetic wave propagation in a mine as a weighted graph Where V is the set of nodes in the graph, representing wireless relay nodes, E is the set of edges, representing communication links, each edgeAll have a weight ofRepresenting the communication cost or quality from node u to node v, the weight reflects the interference level and attenuation degree factors of the signal, and the Dijkstra algorithm comprises the following calculation steps:
initializing: for each node in the graph Assigning a distance valueFor the starting point; For all of the other nodes to be present,Creating an empty set S to store the nodes which have found the shortest path;
update distance: for nodes Is updated if n is not in SIs that；
Determining the shortest path: selecting a node with the smallest distance from an untreated set of nodesAdding to the set S, updating the nodesDistance values of adjacent nodes of (a);
The updating of the distance and the determination of the shortest path are repeated until all nodes are in S, i.e. the shortest path from the starting point to all other nodes is found.
Further, the optimization model in S5 adopts a bayesian network model, processes the probability relation between uncertainty and variables, selects an electromagnetic wave coding strategy in the changed mine environment, constructs the bayesian network model to represent the influence of the formation conductivity and the gas concentration on the communication performance, and deduces the optimal coding strategy.
Further, the constructing a bayesian network model specifically includes:
Defining a node: creating nodes to represent key variables affecting communication performance, including formation conductivity EDR, gas concentration GC, coding redundancy CR and error correction level ECL; defining probability dependence relations among key variables, namely, the coding redundancy and the error correction level depend on the rock stratum conductivity and the gas concentration;
parameter learning: collecting historical data including formation conductivity, gas concentration, and corresponding optimal coding redundancy and error correction levels, using the collected data to estimate a conditional probability distribution for each node in the bayesian network;
Reasoning and decision: monitoring the current rock stratum conductivity and gas concentration in real time, giving the current rock stratum conductivity and gas concentration, using a Bayesian network to infer, and calculating posterior probabilities of different coding scheme parameters (CR and ECL);
outputting a recommended scheme: the posterior probability is calculated by Bayesian rules, and the formula is as follows:
wherein, the method comprises the steps of, wherein, Is the posterior probability of a specific coding redundancy CR and error correction level ECL given the formation conductivity EDR and gas concentration GC,The probability of observing specific rock stratum conductivity and gas concentration given the coding parameters is learned from historical data,Is the prior probability of coding redundancy and error correction level,Is the marginal probability of the currently observed formation conductivity and gas concentration;
selecting an optimal scheme: the coding redundancy and error correction level that maximizes the posterior probability are selected as the recommendation.
The control system based on the mine audio communication is used for realizing the control method based on the mine audio communication, and comprises the following modules:
formation conductivity monitoring module: a distributed sensor network is adopted and deployed in a mine area, so that the conductivity change of the rock stratum is continuously monitored, and data are transmitted to a central processing unit in real time;
the gas concentration monitoring module: using gas monitoring equipment, installing the gas monitoring equipment in a mine operation area, detecting the gas concentration in real time and sending distribution data to a central processing unit;
and a data analysis and prediction module: the system comprises a central processing unit, a control unit and a control unit, wherein the central processing unit is provided with a machine learning algorithm, analyzes rock stratum conductivity and gas concentration data, and predicts electromagnetic wave propagation conditions and communication link quality and stability;
Dynamic route adjustment module: the method comprises the steps of dynamically adjusting a transmission path according to electromagnetic wave propagation conditions and communication link quality evaluation, and automatically adjusting the position and configuration of a wireless relay node;
The code adjustment module: based on the environment self-adaptive signal coding technology, the coding scheme is dynamically adjusted according to real-time monitoring data in a communication link, and the redundancy and error correction capability of electromagnetic waves are optimized to adapt to transmission conditions.
The invention has the beneficial effects that:
According to the invention, the improved LSTM model is used for analyzing the electromagnetic wave propagation condition of the current underground environment, so that the quality and stability of a communication link can be effectively predicted, and the advantages of LSTM in the aspect of processing time sequence data are utilized, so that the model can learn and identify the influence of the conductivity of a rock stratum and the change of gas concentration on the electromagnetic wave propagation. Since the model can capture long-term data dependencies, it can predict future environmental changes and their impact on the performance of the communication link, making adjustments in advance to maintain continuity and stability of the communication.
According to the invention, the transmission path is dynamically regulated by adopting the Dijkstra algorithm based on the graph, so that the region with serious interference and attenuation can be effectively avoided, the weight of each link (reflecting the interference and attenuation degree) is updated in real time by regarding the mine communication network as a weighted graph, and the Dijkstra algorithm can calculate the optimal communication path, thereby not only enhancing the self-adaptive capacity of wireless electromagnetic wave communication, but also maximizing the communication efficiency and reliability. In addition, the flexibility of the network is further enhanced by deploying the movable wireless relay nodes, so that the communication network can dynamically adapt to the change of the mine environment.
According to the invention, the uncertainty of the rock stratum conductivity and the gas concentration and the influence of the uncertainty on the communication performance are processed by adopting a Bayesian network model, the Bayesian network formally describes the dependency relationship among variables by a probability method, and the optimal electromagnetic wave coding strategy can be deduced under the condition that the mine environment is continuously changed. The method enables the communication system to intelligently select coding redundancy and error correction level according to the current environment condition, optimizes the data transmission process and reduces the risks of communication interruption and data loss.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a control method according to an embodiment of the present invention;
Fig. 2 is a schematic diagram of a functional module of a control system according to an embodiment of the invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1, the mine-based audio communication control method comprises the following steps:
s1: implementing real-time monitoring of the conductivity of the rock stratum, distributing the sensor network in a key area of a coal mine, continuously monitoring the conductivity change (uneven condition) of the rock stratum, and transmitting the conductivity data of the rock stratum to a central processing unit in real time;
S2: configuring coal seam gas monitoring equipment, detecting the gas concentration of each operation area in real time, and transmitting gas concentration distribution data to a central processing unit;
S3: in the central processing unit, according to the received rock stratum conductivity and gas concentration distribution data, analyzing electromagnetic wave propagation conditions of the current underground environment by using a machine learning algorithm, and predicting the quality and stability of a communication link;
s4: realizing a dynamic routing protocol, dynamically adjusting a transmission path according to electromagnetic wave propagation conditions and communication link quality evaluation, avoiding an area with serious interference and attenuation, deploying a movable wireless relay node, and automatically adjusting physical position and configuration by the wireless relay node according to the dynamically adjusted transmission path so as to construct an optimal communication link;
S5: the environment self-adaptive signal coding technology is implemented, and as the conditions of slight uneven rock stratum conductivity and slight gas concentration still exist in the optimal communication link, the coding scheme is dynamically adjusted according to real-time monitoring data of rock stratum conductivity and gas concentration distribution in the optimal communication link, the redundancy and error correction capability of electromagnetic waves are automatically optimized by adopting an optimization model so as to adapt to the current transmission condition, the signal redundancy is increased, and stronger error correction coding is adopted so as to resist signal loss and interference possibly increased in the transmission process.
S1 comprises deploying a multipoint conductivity sensor on a main channel and a working surface of a coal mine underground, directly measuring the conductivity of rock, and measuring the current quantity passing through a rock sample by using an electrode to calculate the conductivity, wherein the monitored conductivity data is transmitted to a central processing unit in real time through a wireless network.
The machine learning algorithm in S3 is based on an improved long-short-term memory network LSTM model, a central processing unit firstly preprocesses received rock stratum conductivity and gas concentration data, adopts the LSTM model to analyze the influence of the rock stratum conductivity and the gas concentration on electromagnetic wave propagation, processes time sequence data, identifies modes and trends in the data, and predicts the propagation performance of the electromagnetic wave under different underground environment conditions;
the communication link is simulated and analyzed to predict link quality and stability at current mine conditions, including signal strength, signal to noise ratio, data transmission rate, and outage conditions.
The LSTM model is adopted to analyze the influence of the rock stratum conductivity and the gas concentration on the electromagnetic wave propagation, and the method specifically comprises the following steps:
S31: characteristic engineering: integrating the conductivity, gas concentration distribution and depth multidimensional features of the rock stratum, constructing a comprehensive feature set to capture complex factors influencing electromagnetic wave propagation, performing space-time feature mapping, integrating spatial positions (such as depth from an inlet and specific roadway positions) and time factors into the comprehensive feature set to simulate the actual propagation process of the electromagnetic wave in a mine, for example, converting time sequence data into sequence input;
S32: model building and training: constructing an LSTM model, designing an LSTM network architecture, comprising a plurality of LSTM units, wherein the LSTM units comprise an input layer, a plurality of LSTM layers and an output layer, the number and configuration of the LSTM layers are determined according to the complexity and the data quantity of the problem, the LSTM model is trained by using historical data, and in training, how to predict the propagation performance of electromagnetic waves based on the historical and current values of the conductivity and the gas concentration of a rock stratum is learned;
the LSTM unit consists of four parts, namely a forgetting door Input doorOutput doorAnd cell stateThe expression is as follows:
Forgetting the door: Control how much of the previous information should be forgotten by the memory unit.
An input door:；
; it is decided how much new information is stored in the cell state.
Cell state update: ; the updated cell state is the sum of the product of the state at the previous time and the forget gate and the product of the input gate and the new candidate.
Output door:
；
; the output value of the unit at the next time is determined.
Wherein, Is a sigmoid activation function for limiting the outputs of the forget gate, the input gate, and the output gate to between 0 and 1; tanh is a hyperbolic tangent activation function that limits the hidden state output range of the candidate cell states and the final output to between-1 and 1;
Indicating that the hidden state of the previous time is connected to the input of the current time.
The hidden state of the previous moment is represented, and the output state of the network at the time step t-1 is represented.
The input representing the current time instant represents the external input received at time step t.
An output representing a forgetting gate for controlling the amount of information forgotten from the cell state.
The output of the input gate determines how much new information is to be stored in the cell state.
The candidate cell state at the current time is indicated, and the new information content is indicated.
The state of the cell at the current time is indicated and updated by combining the previous state and the new candidate state.
Representing the output of the output gate for determining the output from the cell state to the hidden state.
The hidden state representing the current time is the final output determined by the output gate and the current cell state.
And the weight matrix is used for controlling the influence of the input and the previous hidden state on the output of the forgetting gate.
A bias term representing a forgetting gate for adjusting an activation level of the forgetting gate.
And the weight matrix is used for controlling the influence of the input and the previous hidden state on the output of the input gate.
Representing the bias term of the input gate for adjusting the activation level of the input gate.
A weight matrix representing candidate cell states for controlling the impact of the input and the previous hidden state on the candidate cell states.
A bias term representing a candidate cell state for adjusting an activation level of the candidate cell state.
A weight matrix representing the output gates for controlling the effect of the input and previous hidden states on the output gates.
A bias term representing the output gate for adjusting the activation level of the output gate.
A further explanation in connection with the present invention is as follows:
1. And Two variables are critical and they directly process and integrate real-time monitoring data from the mine environment, including data collected from formation conductivity and gas concentration sensors, which are the basis for evaluating the current downhole environment and predicting the quality of the communication link.
2.AndGating and status updating mechanisms enable the LSTM to decide which old information to retain and when to introduce new information, which is critical to adjusting communication strategies under mine dynamics and complex environmental conditions, e.g., if the predictive model detects significant changes in formation conductivity, the behavior of the forget gate and the input gate needs to be adjusted to accommodate the new environmental conditions.
3. Weight matrix and bias termThe parameters determine how the LSTM learns from the data and responds to environmental changes, and in a mine communication control system, weights and biases are trained based on historical data so that the model can optimally predict the effect of different environmental variables, such as formation conductivity and gas concentration, on the communication effect.
4. Activating function [ ]And tanh), the choice of the activation function is critical to ensuring the stability and effectiveness of the network output, the use of the sigmoid function helps the model maintain the output range when determining the information transfer ratio, and the tanh function helps control and regulate the normalization process of the data.
S33: real-time analysis and prediction: input data to be collected in real timeInputting a trained LSTM model, predicting propagation performance of electromagnetic waves based on current and past data trends, including electromagnetic wave attenuation, signal attenuation and interference areas, interpreting the output of the LSTM model, determining predicted values of the propagation performance of electromagnetic waves, and using the predicted values to dynamically adjust a communication strategy.
Spatio-temporal feature mapping is included in the input dataCombining space-time characteristics, combining the rock stratum conductivity and the gas concentration with the corresponding spatial position and time information to form a complex input characteristic vector so as to capture the time and space dependency relationship, wherein the method specifically comprises the following steps:
Spatial position coding: each monitoring point in the mine is assigned a unique geographic tag, for example, based on the layout of the mine, each monitoring point can be tagged according to the specific position of the monitoring point in the roadway (such as an entrance, the vicinity of a ventilation shaft, a mining face and the like), the geographic tag is converted into a digital form by using single-heat coding, the geographic tag is used as an input characteristic in a model, for example, the roadway can be divided into different sections according to the position of the roadway in the mine, and a vector code is assigned to each section;
And (3) time factor integration: converting the time stamp of data acquisition into a format which can be understood by a model, calculating a time interval from a time point of monitoring, converting time into a continuous numerical value, reflecting the duration from the monitoring to the present, combining the converted time numerical value with conductivity and gas concentration to form a time sequence data set, and training an LSTM model;
Model training is carried out by combining space-time characteristics: combining the space position codes and the time factors with sensor data to form a comprehensive feature vector, wherein the feature vector can be [ space codes, time values, conductivity and gas concentration ] for the data of each time point, and the constructed comprehensive feature vector is used as the input of an LSTM model to learn the space-time dependency relationship in the electromagnetic wave propagation process;
The output of the LSTM model is designed to be a relevant index for predicting electromagnetic wave propagation, including signal intensity, attenuation rate or quality of a communication link, and the model can dynamically predict electromagnetic wave propagation performance under specific space-time conditions by learning modes and trends in time sequence data and guide a communication system to make corresponding adjustment.
S4 specifically comprises the following steps:
Receiving LSTM model output: the central processing unit periodically receives prediction data generated by the improved LSTM model, including electromagnetic wave propagation condition predictions for each monitoring point, signal strength, signal-to-noise ratio, data transmission rate and potential interruption risk;
Calculating an optimal path: calculating an optimal communication path avoiding interference and attenuation areas by using a dynamic routing algorithm and combining a prediction result of an LSTM model;
Dynamically adjusting a transmission path: dynamically updating a routing table according to the calculated optimal path, adjusting the transmission path of data, and ensuring that electromagnetic waves are transmitted through the optimal path;
deploying and adjusting wireless relay nodes: according to the dynamically adjusted transmission path, the deployment and position adjustment of the wireless relay node are guided, the wireless relay node is provided with automatic positioning and moving functions, and the physical position and configuration are adjusted according to the instruction of the central processing unit so as to support a new optimal communication link.
The dynamic routing algorithm uses a Dijkstra algorithm based on a graph, and specifically comprises the following steps:
modeling a mine propagation network: modeling electromagnetic wave propagation in a mine as a weighted graph Where V is the set of nodes in the graph, representing wireless relay nodes, E is the set of edges, representing communication links, each edgeAll have a weight ofRepresentative nodeTo the nodeThe weight reflects the interference level and attenuation degree factors of the signal, and the Dijkstra algorithm comprises the following calculation steps:
initializing: for each node in the graph Assigning a distance valueFor the starting point; For all of the other nodes to be present,Creating an empty set S to store the nodes which have found the shortest path;
update distance: for nodes Is updated if n is not in SIs that；
Determining the shortest path: selecting a node with the smallest distance from an untreated set of nodesAdding to the set S, updating the nodesDistance values of adjacent nodes of (a);
The updating of the distance and the determination of the shortest path are repeated until all nodes are in S, i.e. the shortest path from the starting point to all other nodes is found.
In the present invention, the weight of an edgeNot only reflects the traditional distance cost, but also combines the influence of the conductivity of the rock stratum and the concentration of gas on the propagation of electromagnetic waves, so that the weight can be defined as follows:
wherein PathLoss is a Representing slave nodesTo the point ofIs the signal path loss of the interfaceRepresenting the interference level on the link GasLevelIndicating the effect of gas concentration on the link,Is a weight coefficient for adjusting the influence of each factor.
This weight calculation method allows Dijkstra's algorithm to find the optimal communication path taking into account signal quality, interference and gas concentration. By the method, the mine audio communication system can dynamically adjust the communication path so as to avoid areas with poor signal quality, large interference or high gas concentration, thereby ensuring the reliability and efficiency of communication.
In a mine audio radio wave communication network, there are four communication nodes: A. b, C and D, which are connected by different communication links, the weight of each link reflects the communication quality of the link (taking into account signal attenuation and interference etc.), and the optimal communication path from node a to node D needs to be calculated.
The weights of the links are set as follows:
the link weights a to B are 4 (lower interference and attenuation);
The link weights a to C are 2 (lowest interference and attenuation);
The link weights B to C are 5 (medium interference and attenuation);
The link weights B to D are 10 (higher interference and attenuation);
the link weight of C to D is 3 (low interference and attenuation);
initializing: let a be the source node, therefore: initially, set S is empty.
Updating the distance value: starting from a:
Accessing node a, updating their distance values taking into account their neighbors B and C
；
; Add a to set S.
Selecting the non-visited node of the shortest distance;
Node C has the shortest distance value, so C is selected as the next node.
Updating the distance value, starting from C:
access node C updates its distance value taking into account its neighbors B and D:
(B) the distance value is unchanged;
Adding C to set S.
The update process is repeated: nodes B and D are not accessed, the distance value of node B is 4 and D is 5. And selecting B as the next node.
Accessing node B, only considering node D, updating the distance value of D:
(distance value of D is unchanged), add B to set S.
Results: all nodes are processed and the shortest path is determined. The optimal path from A to D isThe total weight or path cost is 5.
From this procedure, it can be seen how the Dijkstra algorithm chooses the shortest path step by step, even though some direct paths (e.g., a through B) appear to be less costly in the initial stages, the algorithm still considers the overall shortest path. In this example, even though the total cost of the path through C to D is low, it becomes the final selected path. Such a path selection mechanism can effectively avoid areas with serious interference and attenuation, and ensure optimization of communication links in the mine.
And S5, the optimized model adopts a Bayesian network model, processes the probability relation between uncertainty and variables, selects an electromagnetic wave coding strategy in the changed mine environment, constructs the Bayesian network model to represent the influence of the rock stratum conductivity and the gas concentration on the communication performance, and deduces the optimal coding strategy.
The construction of the Bayesian network model specifically comprises the following steps:
Defining a node: creating nodes to represent key variables affecting communication performance, including formation conductivity EDR, gas concentration GC, coding redundancy CR and error correction level ECL; defining probability dependence relations among key variables, namely, the coding redundancy and the error correction level depend on the rock stratum conductivity and the gas concentration;
Parameter learning: collecting historical data including formation conductivity, gas concentration, and corresponding optimal coding redundancy and error correction levels, using the collected data to estimate a conditional probability distribution for each node in the bayesian network, e.g., to estimate the probability of a particular coding redundancy and error correction level given the formation conductivity and gas concentration;
Reasoning and decision: monitoring the current rock stratum conductivity and gas concentration in real time, giving the current rock stratum conductivity and gas concentration, using a Bayesian network to infer, and calculating posterior probabilities of different coding scheme parameters (CR and ECL);
outputting a recommended scheme: the posterior probability is calculated by Bayesian rules, and the formula is as follows:
wherein, the method comprises the steps of, wherein, Is the posterior probability of a specific coding redundancy CR and error correction level ECL given the formation conductivity EDR and gas concentration GC,The probability of observing specific rock stratum conductivity and gas concentration given the coding parameters is learned from historical data,Is the prior probability of coding redundancy and error correction level,Is the marginal probability of the currently observed formation conductivity and gas concentration;
selecting an optimal scheme: the coding redundancy and error correction level that maximizes the posterior probability are selected as the recommendation.
As shown in fig. 2, a mine-based audio communication control system is configured to implement the above mine-based audio communication control method, and includes the following modules:
formation conductivity monitoring module: a distributed sensor network is adopted and deployed in a mine area, so that the conductivity change of the rock stratum is continuously monitored, and data are transmitted to a central processing unit in real time;
the gas concentration monitoring module: using gas monitoring equipment, installing the gas monitoring equipment in a mine operation area, detecting the gas concentration in real time and sending distribution data to a central processing unit;
and a data analysis and prediction module: the system comprises a central processing unit, a control unit and a control unit, wherein the central processing unit is provided with a machine learning algorithm, analyzes rock stratum conductivity and gas concentration data, and predicts electromagnetic wave propagation conditions and communication link quality and stability;
Dynamic route adjustment module: the method comprises the steps of dynamically adjusting a transmission path according to electromagnetic wave propagation conditions and communication link quality evaluation, and automatically adjusting the position and configuration of a wireless relay node;
The code adjustment module: based on the environment self-adaptive signal coding technology, the coding scheme is dynamically adjusted according to real-time monitoring data in a communication link, and the redundancy and error correction capability of electromagnetic waves are optimized to adapt to transmission conditions.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the invention is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.

Claims (7)

1.一种基于矿井音频通信控制方法，其特征在于，包括以下步骤：1. A mine audio communication control method, characterized in that it includes the following steps: S1：实施岩层电导率实时监测，采用传感器网络分布于煤矿井关键区域，持续监测岩层电导率变化，并将岩层电导率数据实时传输至中心处理单元；S1: Implement real-time monitoring of rock conductivity, use a sensor network distributed in key areas of coal mines, continuously monitor changes in rock conductivity, and transmit rock conductivity data to a central processing unit in real time; S2：配置煤层瓦斯监测设备，实时探测各作业区域的瓦斯浓度，将瓦斯浓度分布数据传送至中心处理单元；S2: Equip coal seam gas monitoring equipment to detect the gas concentration in each operating area in real time and transmit the gas concentration distribution data to the central processing unit; S3：在中心处理单元中，根据接收到的岩层电导率和瓦斯浓度分布数据，运用机器学习算法分析当前井下环境的电磁波传播条件，预测通信链路的质量和稳定性；S3: In the central processing unit, based on the received rock conductivity and gas concentration distribution data, the machine learning algorithm is used to analyze the electromagnetic wave propagation conditions of the current underground environment and predict the quality and stability of the communication link; S4：实现动态路由协议，根据电磁波传播条件和通信链路质量评估，动态调整传输路径，避开受干扰和衰减严重的区域，部署可移动的无线中继节点，无线中继节点根据动态调整的传输路径自动调整物理位置和配置，以构建最优通信链路；S4: Implement dynamic routing protocols, dynamically adjust the transmission path according to electromagnetic wave propagation conditions and communication link quality assessment, avoid areas with severe interference and attenuation, and deploy mobile wireless relay nodes. The wireless relay nodes automatically adjust their physical positions and configurations according to the dynamically adjusted transmission paths to build the optimal communication links. S5：实施环境自适应信号编码技术，根据最优通信链路中的岩层电导率和瓦斯浓度分布的实时监测数据动态调整编码方案，采用优化模型自动优化电磁波的冗余度和错误更正能力，以适应当前的传输条件，S5: Implement environmental adaptive signal coding technology, dynamically adjust the coding scheme according to the real-time monitoring data of rock conductivity and gas concentration distribution in the optimal communication link, and use the optimization model to automatically optimize the redundancy and error correction capability of electromagnetic waves to adapt to the current transmission conditions. 所述S3中的机器学习算法基于改进长短期记忆网络LSTM模型，中心处理单元首先对接收到的岩层电导率和瓦斯浓度数据进行预处理，采用LSTM模型来分析岩层电导率和瓦斯浓度对电磁波传播的影响，处理时间序列数据，识别数据中的模式和趋势，并预测电磁波在不同井下环境条件下的传播性能；The machine learning algorithm in S3 is based on an improved long short-term memory network LSTM model. The central processing unit first pre-processes the received rock conductivity and gas concentration data, uses the LSTM model to analyze the impact of rock conductivity and gas concentration on electromagnetic wave propagation, processes time series data, identifies patterns and trends in the data, and predicts the propagation performance of electromagnetic waves under different underground environmental conditions; 对通信链路进行模拟和分析，预测在当前矿井条件的链路质量和稳定性，这包括信号强度、信噪比、数据传输速率和中断情况，Simulate and analyze communication links to predict link quality and stability under current mine conditions, including signal strength, signal-to-noise ratio, data transmission rate, and interruptions. 所述S4具体包括：接收LSTM模型输出：中心处理单元定期接收由改进的LSTM模型生成的预测数据，包括针对各个监测点的电磁波传播条件预测；The S4 specifically includes: receiving LSTM model output: the central processing unit regularly receives prediction data generated by the improved LSTM model, including predictions of electromagnetic wave propagation conditions for each monitoring point; 计算最优路径：使用动态路由算法，结合LSTM模型的预测结果，计算出避开干扰和衰减区域的最优通信路径；Calculate the optimal path: Use the dynamic routing algorithm and the prediction results of the LSTM model to calculate the optimal communication path that avoids interference and attenuation areas; 动态调整传输路径：根据计算出的最优路径，动态更新路由表，调整数据的传输路径，确保电磁波通过最佳的路径发送；Dynamically adjust the transmission path: According to the calculated optimal path, dynamically update the routing table and adjust the data transmission path to ensure that the electromagnetic waves are sent through the best path; 部署和调整无线中继节点：根据动态调整的传输路径，指导无线中继节点的部署和位置调整，无线中继节点配备自动定位和移动功能，根据中心处理单元的指令调整物理位置和配置，以支持新的最优通信链路，Deploy and adjust wireless relay nodes: According to the dynamically adjusted transmission path, guide the deployment and position adjustment of wireless relay nodes. Wireless relay nodes are equipped with automatic positioning and movement functions. According to the instructions of the central processing unit, adjust the physical position and configuration to support the new optimal communication link. 所述动态路由算法使用基于图的Dijkstra算法，具体包括：矿井传播网络建模：将矿井内的电磁波传播建模为加权图，其中V是图中的节点集合，代表无线中继节点，E是边集合，代表通信链路，每条边都有一个权重，代表节点到节点的通信成本或质量，该权重反映信号的干扰水平、衰减程度因素，Dijkstra算法的计算步骤如下：The dynamic routing algorithm uses the graph-based Dijkstra algorithm, which specifically includes: Mine propagation network modeling: modeling the electromagnetic wave propagation in the mine as a weighted graph , where V is the node set in the graph, representing the wireless relay node, and E is the edge set, representing the communication link. There is a weight , representing the node To Node The communication cost or quality of the signal. The weight reflects the interference level and attenuation factor of the signal. The calculation steps of the Dijkstra algorithm are as follows: 初始化：为图中的每个节点分配一个距离值，对于起点；对于所有其他节点,，创建一个空集合S存放已经找到最短路径的节点；Initialization: For each node in the graph Assign a distance value , for the starting point ; For all other nodes, , create an empty set S to store the nodes whose shortest paths have been found; 更新距离：对于节点每个邻接节点n，如果n不在S中，则更新为；Update distance: for nodes For each adjacent node n, if n is not in S, update for ; 确定最短路径：从未处理的节点集合中选择距离最小的节点，加入到集合S，更新节点的邻接节点的距离值；Determine the shortest path: Select the node with the smallest distance from the set of unprocessed nodes , add to set S, update node The distance value of the adjacent nodes; 重复更新距离、确定最短路径，直到所有的节点都在S中，即找到了从起点到所有其他节点的最短路径。Repeat updating the distance and determining the shortest path until all nodes are in S , that is, the shortest path from the starting point to all other nodes is found. 2.根据权利要求1所述的基于矿井音频通信控制方法，其特征在于，所述S1包括在煤矿井下的主要通道、作业面部署多点电导率传感器，直接测量岩石的电导率，监测到的电导率数据通过无线网络实时传输至中心处理单元。2. According to the mine audio communication control method according to claim 1, it is characterized in that S1 includes deploying multi-point conductivity sensors in the main channels and working surfaces underground in the coal mine to directly measure the conductivity of the rock, and the monitored conductivity data is transmitted to the central processing unit in real time via a wireless network. 3.根据权利要求1所述的基于矿井音频通信控制方法，其特征在于，所述采用LSTM模型来分析岩层电导率和瓦斯浓度对电磁波传播的影响具体包括：3. According to the mine audio communication control method of claim 1, it is characterized in that the use of the LSTM model to analyze the influence of rock conductivity and gas concentration on electromagnetic wave propagation specifically includes: S31：特征工程：整合岩层电导率、瓦斯浓度分布、深度多维特征，构建一个综合特征集，以捕获影响电磁波传播的复杂因素，进行时空特征映射，将空间位置和时间因素整合进综合特征集，以模拟电磁波在矿井中的实际传播过程；S31: Feature Engineering: Integrate the multi-dimensional features of rock conductivity, gas concentration distribution, and depth to construct a comprehensive feature set to capture the complex factors affecting the propagation of electromagnetic waves, perform spatiotemporal feature mapping, and integrate spatial position and time factors into the comprehensive feature set to simulate the actual propagation process of electromagnetic waves in mines; S32：模型建立与训练：构建LSTM模型，设计LSTM网络架构，包括多个LSTM单元，且LSTM单元包括输入层、多个LSTM层以及输出层，使用历史数据对LSTM模型进行训练，训练中，学习如何基于岩层电导率和瓦斯浓度的历史和当前值来预测电磁波的传播性能；S32: Model establishment and training: Build an LSTM model and design an LSTM network architecture, including multiple LSTM units, and the LSTM unit includes an input layer, multiple LSTM layers, and an output layer. Use historical data to train the LSTM model. During training, learn how to predict the propagation performance of electromagnetic waves based on the historical and current values of rock conductivity and gas concentration. S33：实时分析与预测：将实时收集的输入数据输入训练好的LSTM模型，模型基于当前和过去的数据趋势预测电磁波的传播性能，包括电磁波衰减、信号衰减和干扰区域，解释LSTM模型的输出，确定电磁波传播性能的预测值，并用于动态调整通信策略。S33: Real-time analysis and prediction: Input data collected in real time The trained LSTM model is input. The model predicts the propagation performance of electromagnetic waves based on current and past data trends, including electromagnetic wave attenuation, signal attenuation, and interference areas. The output of the LSTM model is interpreted to determine the predicted value of the electromagnetic wave propagation performance and is used to dynamically adjust the communication strategy. 4.根据权利要求3所述的基于矿井音频通信控制方法，其特征在于，所述时空特征映射包括在输入数据中结合时空特征，将岩层电导率、瓦斯浓度与其对应的空间位置和时间信息进行组合，形成复杂输入特征向量，以捕捉时间和空间上的依赖关系，具体包括：4. The mine audio communication control method according to claim 3, characterized in that the spatiotemporal feature map is included in the input data In the process of combining temporal and spatial characteristics, the rock conductivity and gas concentration are combined with their corresponding spatial position and time information to form a complex input feature vector to capture the temporal and spatial dependencies, including: 空间位置编码：为矿井内的每个监测点分配一个唯一地理标签，使用独热编码将地理标签转换为数值形式，在模型中作为输入特征使用；Spatial location encoding: Assign a unique geographic tag to each monitoring point in the mine, use one-hot encoding to convert the geographic tag into a numerical form, and use it as an input feature in the model; 时间因素整合：将数据采集的时间戳转换为模型可理解的格式，通过从监测开始的时间点计算时间间隔来实现，将时间转换为一个连续的数值，反映从监测开始到现在的持续时间，将转换后的时间数值与电导率、瓦斯浓度结合，形成一个时间序列数据集，用于训练LSTM模型；Time factor integration: The timestamp of data collection is converted into a format that the model can understand. This is achieved by calculating the time interval from the start of monitoring, converting the time into a continuous value that reflects the duration from the start of monitoring to the present. The converted time value is combined with conductivity and gas concentration to form a time series data set for training the LSTM model. 结合时空特征进行模型训练：将空间位置编码和时间因素与传感器数据结合，构成一个综合特征向量，使用构建的综合特征向量作为LSTM模型的输入，模型同时学习电磁波传播过程中的时空依赖关系。Combine spatiotemporal features for model training: Combine spatial position encoding and time factors with sensor data to form a comprehensive feature vector. Use the constructed comprehensive feature vector as the input of the LSTM model. The model also learns the spatiotemporal dependencies in the process of electromagnetic wave propagation. 5.根据权利要求1所述的基于矿井音频通信控制方法，其特征在于，所述S5中的优化模型采用贝叶斯网络模型，处理不确定性和变量间的概率关系，在变化的矿井环境中选择电磁波编码策略，构建贝叶斯网络模型，以表示岩层电导率和瓦斯浓度对通信性能的影响，并推断最佳的编码策略。5. According to the mine audio communication control method described in claim 1, it is characterized in that the optimization model in S5 adopts a Bayesian network model to process uncertainty and the probabilistic relationship between variables, selects an electromagnetic wave coding strategy in a changing mine environment, and constructs a Bayesian network model to represent the impact of rock conductivity and gas concentration on communication performance, and infer the optimal coding strategy. 6.根据权利要求5所述的基于矿井音频通信控制方法，其特征在于，所述构建贝叶斯网络模型具体包括：6. The mine audio communication control method according to claim 5, characterized in that the construction of the Bayesian network model specifically comprises: 定义节点：创建节点来表示影响通信性能的关键变量，包括岩层电导率EDR、瓦斯浓度GC、编码冗余度CR、错误更正等级ECL；定义关键变量之间的概率依赖关系，即编码冗余度和错误更正等级依赖于岩层电导率和瓦斯浓度；Define nodes: Create nodes to represent key variables that affect communication performance, including formation conductivity EDR, gas concentration GC, coding redundancy CR, and error correction level ECL; define the probabilistic dependency between key variables, that is, coding redundancy and error correction level depend on formation conductivity and gas concentration; 参数学习：收集历史数据，包括岩层电导率、瓦斯浓度以及对应的最佳编码冗余度和错误更正等级，使用收集的数据来估计贝叶斯网络中每个节点的条件概率分布；Parameter learning: Collect historical data, including formation conductivity, gas concentration, and the corresponding optimal coding redundancy and error correction level, and use the collected data to estimate the conditional probability distribution of each node in the Bayesian network; 推理和决策：实时监测当前的岩层电导率和瓦斯浓度，给定当前的岩层电导率和瓦斯浓度，使用贝叶斯网络进行推理，计算不同编码方案参数的后验概率；Reasoning and decision-making: Real-time monitoring of the current rock conductivity and gas concentration. Given the current rock conductivity and gas concentration, Bayesian network is used for reasoning to calculate the posterior probability of different coding scheme parameters. 输出推荐方案：后验概率通过贝叶斯规则计算，公式如下：Output recommendation plan: The posterior probability is calculated by Bayes' rule, and the formula is as follows: ，其中，是给定岩层电导率EDR和瓦斯浓度GC时，具体编码冗余度CR和错误更正等级ECL的后验概率，是给定编码参数时，观察到具体岩层电导率和瓦斯浓度的概率，从历史数据中学习得到，是编码冗余度和错误更正等级的先验概率，是当前观测到的岩层电导率和瓦斯浓度的边缘概率； ,in, is the posterior probability of the specific coding redundancy CR and error correction level ECL when the rock conductivity EDR and gas concentration GC are given, is the probability of observing a specific formation conductivity and gas concentration given the encoded parameters, learned from historical data, is the prior probability of coding redundancy and error correction level, is the marginal probability of the currently observed rock conductivity and gas concentration; 选择最优方案：选择使后验概率最大化的编码几余度和错误更正等级作为推荐方案。Select the best solution: Select the coding redundancy and error correction level that maximizes the posterior probability as the recommended solution. 7.一种基于矿井音频通信控制系统，用于实现如权利要求1-6任一项所述的基于矿井音频通信控制方法，其特征在于，包括以下模块：7. A mine audio communication control system, used to implement the mine audio communication control method according to any one of claims 1 to 6, characterized in that it comprises the following modules: 岩层电导率监测模块：采用分布式传感器网络，部署于矿井区域，持续监测岩层电导率变化，并实时将数据传输至中心处理单元；Rock conductivity monitoring module: It uses a distributed sensor network, deployed in the mine area, to continuously monitor changes in rock conductivity and transmit data to the central processing unit in real time; 瓦斯浓度监测模块：使用瓦斯监测设备，安装在矿井作业区域，实时探测瓦斯浓度并将分布数据发送至中心处理单元；Gas concentration monitoring module: Use gas monitoring equipment, installed in the mine operation area, to detect gas concentration in real time and send distribution data to the central processing unit; 数据分析与预测模块：包括中心处理单元，配备机器学习算法，分析岩层电导率和瓦斯浓度数据，预测电磁波传播条件及通信链路质量和稳定性；Data analysis and prediction module: includes a central processing unit equipped with machine learning algorithms to analyze rock conductivity and gas concentration data, predict electromagnetic wave propagation conditions and communication link quality and stability; 动态路由调整模块：包含动态路由算法和可移动无线中继节点，根据电磁波传播条件和通信链路质量评估动态调整传输路径，并自动调整无线中继节点的位置和配置；Dynamic routing adjustment module: It includes dynamic routing algorithms and mobile wireless relay nodes. It dynamically adjusts the transmission path according to electromagnetic wave propagation conditions and communication link quality evaluation, and automatically adjusts the location and configuration of wireless relay nodes. 编码调整模块：基于环境自适应信号编码技术，根据通信链路中的实时监测数据动态调整编码方案，优化电磁波的冗余度和错误更正能力，以适应传输条件。Coding adjustment module: Based on environmental adaptive signal coding technology, the coding scheme is dynamically adjusted according to the real-time monitoring data in the communication link, and the redundancy and error correction capability of the electromagnetic wave are optimized to adapt to the transmission conditions.
CN202411180155.8A 2024-08-27 2024-08-27 Audio communication control method and system based on mine Active CN118694452B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411180155.8A CN118694452B (en) 2024-08-27 2024-08-27 Audio communication control method and system based on mine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411180155.8A CN118694452B (en) 2024-08-27 2024-08-27 Audio communication control method and system based on mine

Publications (2)

Publication Number Publication Date
CN118694452A CN118694452A (en) 2024-09-24
CN118694452B true CN118694452B (en) 2024-11-08

Family

ID=92770105

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411180155.8A Active CN118694452B (en) 2024-08-27 2024-08-27 Audio communication control method and system based on mine

Country Status (1)

Country Link
CN (1) CN118694452B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119421184B (en) * 2025-01-06 2025-04-15 创瑞技术有限公司 Sustainable communication optimization processing method under limited connection environment
CN119727908B (en) * 2025-02-28 2025-06-17 江苏黑马高科股份有限公司 A method and system for monitoring transmission of optical terminal
CN120358079B (en) * 2025-06-18 2025-08-22 国网浙江省电力有限公司桐庐县供电公司 Active defense method and system for power network in open converged network environment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101240717A (en) * 2007-02-07 2008-08-13 中国科学院自动化研究所 A method and system for underground personnel positioning and gas concentration dynamic monitoring in coal mines
CN107770779A (en) * 2017-10-19 2018-03-06 中国矿业大学 A kind of cognitron suitable for Minepit environment can communication means

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7362709B1 (en) * 2001-11-02 2008-04-22 Arizona Board Of Regents Agile digital communication network with rapid rerouting
KR100772524B1 (en) * 2005-12-07 2007-11-01 한국전자통신연구원 Label switch route selection system and method based on network management system
US20100062802A1 (en) * 2006-04-10 2010-03-11 Noam Amram Method device and system for receiving a communication signal
KR101022530B1 (en) * 2009-04-17 2011-03-16 삼성탈레스 주식회사 Routing method and apparatus in communication network including wireless network
US9379971B2 (en) * 2012-05-11 2016-06-28 Simula Inovation AS Method and apparatus for determining paths between source/destination pairs
US9685009B2 (en) * 2015-04-01 2017-06-20 Caterpillar Inc. System and method for managing mixed fleet worksites using video and audio analytics
CN110135564A (en) * 2019-05-15 2019-08-16 深圳朴生智能科技有限公司 Coal mine gas sensing data method for detecting abnormality based on edge calculations
CN112649086B (en) * 2020-11-10 2024-09-17 安徽理工大学 Improved vibration monitoring system and method for jointed rock burst model test
CN117214455B (en) * 2023-08-17 2024-03-26 江苏微之润智能技术有限公司 Wind speed and direction monitoring method based on satellite-ground link and microwave link networking
CN116859478B (en) * 2023-09-05 2023-11-28 中国地质大学（武汉） Groundwater simulation method and system based on transient electromagnetic imaging
CN117609836A (en) * 2023-11-29 2024-02-27 华东计算技术研究所（中国电子科技集团公司第三十二研究所） Electromagnetic sensitivity prediction and health management method for integrated module
CN117973613A (en) * 2024-01-29 2024-05-03 重庆市生态环境科学研究院 A water environment monitoring and intelligent early warning system
CN117850653B (en) * 2024-03-04 2024-06-21 山东京运维科技有限公司 Control method and system of touch display screen
CN117857220A (en) * 2024-03-07 2024-04-09 广东工业大学 Block chain-based Internet of vehicles safety evaluation system
CN118297023A (en) * 2024-04-08 2024-07-05 无锡中清互连科技有限公司 Dynamic signal path optimization techniques in high speed PCB design
CN118446513A (en) * 2024-04-25 2024-08-06 江西志宏数字技术有限公司 Industrial park environment quality monitoring system
CN118364899B (en) * 2024-04-28 2024-12-31 北京龙软科技股份有限公司 Mine disaster map construction method based on space-time semantics
CN118214502B (en) * 2024-05-17 2024-08-20 山东工程职业技术大学 Digital broadcast signal quality real-time monitoring method and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101240717A (en) * 2007-02-07 2008-08-13 中国科学院自动化研究所 A method and system for underground personnel positioning and gas concentration dynamic monitoring in coal mines
CN107770779A (en) * 2017-10-19 2018-03-06 中国矿业大学 A kind of cognitron suitable for Minepit environment can communication means

Also Published As

Publication number Publication date
CN118694452A (en) 2024-09-24

Similar Documents

Publication Publication Date Title
CN118694452B (en) Audio communication control method and system based on mine
CN119147094B (en) Underground facility vibration monitoring method and system based on distributed sensing network
Bagwari et al. An enhanced energy optimization model for industrial wireless sensor networks using machine learning
Sarikhani et al. Cooperative spectrum sensing meets machine learning: Deep reinforcement learning approach
CN117666367A (en) Remote control method and system for underground coal mine machinery
Boussaïd et al. Hybridizing biogeography-based optimization with differential evolution for optimal power allocation in wireless sensor networks
Mahalakshmi et al. An energy efficient data fault prediction based clustering and routing protocol using hybrid ASSO with MERNN in wireless sensor network
Chithaluru et al. Energy-balanced neuro-fuzzy dynamic clustering scheme for green & sustainable IoT based smart cities
CN105959988B (en) Cognitive wireless self-organizing network node stability judgment method based on support vector machine
CN118714597B (en) Wireless ad hoc network signal optimization method and system
CN118573610A (en) Bluetooth transmission speed testing method and system
CN117938563A (en) A communication method based on intelligent switch
Nathiya et al. A hybrid optimization and machine learning based energy-efficient clustering algorithm with self-diagnosis data fault detection and prediction for WSN-IoT application
Gao et al. Attention enhanced multi-agent reinforcement learning for cooperative spectrum sensing in cognitive radio networks
Mohamad et al. Optimizing network reliability in dynamic or rapidly-changing topologies
Boovarahan et al. Back propagation model based machine learning in feed forward neural networks for 6G communication
Harb et al. CLARA: A cluster-based node correlation for sampling rate adaptation and fault tolerance in sensor networks
Suganthi et al. Enhancing energy efficiency in wireless sensor networks via predictive model for node status classification and coverage integrity using relational Bi-level aggregation graph convolutional network
Garca et al. A Literature Review on Outlier Detection in Wireless Sensor Networks
Singh A neural network-guided correlation thresholding technique for wireless sensor networks
Khan et al. A Hybrid CT-DEWCA Based Energy-Efficient Routing Protocol for Data and Storage Nodes in Underwater Acoustic Sensor Networks
Dineshkumar et al. Proactive Resilient Adaptive Sensor Node Management with Neuro-Symbolic Systems for Optimized Coverage Efficiency in the Mission-Critical Applications
CN120389955B (en) A method, system, device and medium for optimizing stable transmission of Internet of Things data
Yadav et al. Predicting Battery Levels of Sensor Nodes Using Reinforcement Learning in Harsh Underground Mining Environments
CN119362238B (en) Intelligent closed-loop linkage inspection method, model training method, system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant