Online metering and control system for borehole gas drainage

Abstract

The present application provides an on-line metering control system for borehole gas drainage, which relates to the technical field of coal mine information systems. The system includes: a data acquisition unit for acquiring the control timing data of the drainage pump and the pipeline gas sensing timing data; a flow prediction unit for predicting the gas flow prediction timing data corresponding to the future second time period through a gas drainage flow prediction model; the backbone network of the gas drainage flow prediction model adopts an LSTM model; a drainage control unit for determining the predicted timing data of the control parameters of the drainage pump corresponding to the second time period through a gas drainage pressure control model, and the gas drainage pressure control model adopts a Transformer model based on an attention mechanism. Thus, through a fully automated on-line control system, relying on machine learning models to monitor gas data in real time and make dynamic adjustments, the frequency of human intervention and the dependence on operators are reduced.

Description

Technical Field

[0001] This application relates to the technical field of coal mine informatization systems, and particularly to an online metering control system for borehole gas drainage. Background Art

[0002] With the continuous exploitation of coal resources, gas accidents have become one of the main threats to coal mine safety production. Borehole gas drainage is one of the important measures to prevent gas accidents. Its purpose is to extract the gas in the coal seam, reduce the gas content in the coal seam, and thus reduce the occurrence of gas accidents.

[0003] The existing borehole gas drainage control systems mainly adopt manual control or simple automatic control methods. In the manual control mode, operators need to constantly monitor the changes in gas drainage parameters and manually adjust the operating status of the drainage equipment, which is not only inefficient but also prone to human errors, resulting in untimely control. In addition, most of the existing borehole gas drainage metering systems only have simple data collection and storage functions, lack the ability to deeply analyze and process data, and cannot extract valuable information from a large amount of gas drainage data, making it difficult to discover potential problems and laws in the gas drainage process.

[0004] In response to the above problems, the industry has not yet proposed a better technical solution. Summary of the Invention

[0005] This application provides an online metering control system for borehole gas drainage, which is used to at least solve the problem that the traditional borehole gas drainage system relies on manual or simple automatic control and cannot support real-time and accurate adjustment of gas drainage parameters, making it difficult to cope with sudden or dynamically complex working conditions.

[0006] An embodiment of the present application provides an online metering control system for borehole gas drainage, including: a data acquisition unit for acquiring pumping control timing data and pipeline gas sensing timing data; the pipeline gas sensing timing data includes a plurality of gas sensing data for a corresponding adjacent first time period at a sampling position in the borehole gas drainage pipeline, and the gas sensing data includes gas flow rate, gas concentration, pressure, and temperature; the pumping control timing data includes a plurality of pumping control parameters corresponding to the first time period, and the pumping control parameters include pumping speed and pumping valve opening; a flow prediction unit for inputting the pumping control timing data and the pipeline gas sensing timing data into a gas drainage flow prediction model to predict gas flow prediction timing data for a corresponding future second time period; the backbone network of the gas drainage flow prediction model adopts an LSTM (Long Short-Term Memory) model; a pumping control unit for inputting the pipeline gas sensing timing data, the gas flow prediction timing data, and the pumping control timing data into a gas drainage pressure control model to determine pumping control parameter prediction timing data for the second time period; the gas drainage pressure control model adopts a Transformer model based on an attention mechanism.

[0007] Through the online metering control system for borehole gas drainage provided by the present application, at least the following technical effects can be achieved:

[0008] (1) By introducing the LSTM model and the Transformer model based on the attention mechanism, gas flow prediction and adaptive adjustment of pumping control parameters are carried out, realizing data-driven automatic control. The LSTM model is good at processing time series data and can capture the long-term and short-term dependencies of gas flow changes, while the introduction of the Transformer model further enhances the adaptability of the system to complex control scenarios and the fine capture of characteristic information in the gas drainage process. Through the synergistic effect of these two models, the system can quickly and accurately adjust the pumping control parameters, such as speed and valve opening, according to real-time and historical data, avoiding the lag and error caused by manual control, and greatly improving the timeliness and accuracy of control.

[0009] (2) By using a variety of gas sensing data, such as gas flow rate, gas concentration, pressure, and temperature, combined with the pumping control timing data, a complete timing data input is formed. Furthermore, relying on the LSTM model to predict the gas flow rate, the gas flow rate change in a future period of time can be accurately predicted according to the timing data input, and the change trend of the gas flow rate can be sensed in advance, so as to make targeted adjustments in advance to ensure the efficiency and safety of gas drainage.

[0010] (3) Since parameters such as gas concentration, flow rate, pressure, and temperature are affected by the geological conditions of the mining area and the coal mining technology, the complexity of gas drainage makes it difficult for traditional control methods to handle sudden or dynamically changing situations. Here, by using the Transformer model to deeply mine a large amount of time-series data and relying on the attention mechanism, it is possible to comprehensively consider multiple control factors in a complex gas drainage environment, enabling the automatic control system based on deep learning to dynamically adjust control strategies, effectively solving the problem of insufficient processing capacity caused by a large number of control dimensions in the traditional control mode. For example, in the case of drastic changes in gas concentration or large fluctuations in pipeline pressure, the stability of gas drainage can still be maintained, reducing the failure risk of the system in a complex environment.

[0011] Through this technical solution, with a fully automated online control system, relying on machine learning models to monitor gas data in real time and make dynamic adjustments, the frequency of human intervention and the dependence on operators are reduced, greatly reducing the safety hazards caused by human errors. In addition, when the system detects abnormal gas concentration or flow rate in real time, it can automatically make corresponding emergency parameter adjustments to the control extraction pump, thereby effectively reducing the accumulation of gas in the coal seam and extraction pipeline, reducing the risk of gas explosion or leakage, and enhancing the safety of gas drainage and coal mine production operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 The block diagram shows an example of the online metering control system for borehole gas drainage according to an embodiment of the present application;

[0014] Figure 2 The block diagram shows another example of the online metering control system for borehole gas drainage according to an embodiment of the present application;

[0015] Figure 3 The schematic diagram shows an example of the structural connection of the gas drainage flow prediction model according to an embodiment of the present application;

[0016] Figure 4 The schematic diagram shows an example of the structural connection of the gas drainage pressure control model according to an embodiment of the present application;

[0017] Figure 5Shows an operation flowchart of an example of the on-line metering control method for borehole gas drainage according to an embodiment of the present application;

[0018] Figure 6 Shows a field installation diagram of an example of the installation module of the high-level drill field according to an embodiment of the present application;

[0019] Figure 7 Shows a schematic interface diagram of an example of the terminal applying the on-line metering control system for borehole gas drainage according to an embodiment of the present application;

[0020] Figure 8 Is a schematic structural diagram of an embodiment of the electronic device of the present application. Detailed implementation manners

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0022] In the technical solutions of the present application, for the processing of collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved, etc., they all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0023] Figure 1 Shows a schematic block diagram of an example of the on-line metering control system for borehole gas drainage according to an embodiment of the present application.

[0024] Regarding the carrier of the system in the embodiments of the present application, it can be any controller or processor with computing or processing capabilities. By jointly using the LSTM and Transformer deep learning models, it can respond in a timely manner to potential gas over-standard or pressure abnormal conditions, provide effective intelligent control strategies, improve the automation and intelligence levels of the gas drainage control system, enhance the prediction and decision-making capabilities of the system, and significantly improve the safety, efficiency, and adaptability of the gas drainage process.

[0025] In some examples, it can be integrated and configured in an electronic device or a terminal in a software, hardware, or software-hardware combination manner, and the types of the terminal or the electronic device can be diversified, such as mobile phones, tablet computers, or desktop computers, etc.

[0026] As Figure 1 shown, the on-line metering control system 100 for borehole gas drainage includes a data acquisition unit 110, a flow prediction unit 120, and a drainage control unit 130.

[0027] The data acquisition unit 110 is used to acquire the control timing data of the extraction pump and the gas sensing timing data of the pipeline.

[0028] Here, the gas sensing timing data of the pipeline includes multiple gas sensing data for the corresponding adjacent first time period at the sampling positions in the borehole gas extraction pipeline. The gas sensing data includes gas flow rate, gas concentration, pressure, and temperature. The control timing data of the extraction pump includes multiple extraction pump control parameters for the corresponding first time period. The extraction pump control parameters include the extraction pump speed and the opening degree of the extraction valve.

[0029] It should be noted that the gas pressure in the coal seam directly affects the gas emission rate and the extraction difficulty. Monitoring the gas pressure can help understand the gas occurrence state in the coal seam. In addition, the change in temperature will affect the physical properties and fluidity of the gas, and during the gas extraction process, the change in temperature may be caused by reasons such as the natural heating of the coal seam and the operation heat generation of the extraction equipment.

[0030] In some embodiments, multimodal sensors are arranged in the borehole and its surrounding area. These sensors include a gas flow rate sensor, a gas concentration sensor, a pressure sensor, a temperature sensor, etc. The sensors are installed at the hole sealing position, key points inside the borehole, and on the gas extraction pipeline to achieve comprehensive monitoring of the entire extraction process. Specifically, it is recommended that the gas flow rate sensor and the pressure sensor be installed on the borehole gas extraction pipeline, as close as possible to the extraction hole outlet, so as to accurately measure the gas flow rate and pressure. In addition, the temperature sensor can be distributedly installed at different positions of the extraction pipeline to comprehensively monitor the temperature change of the entire extraction system.

[0031] Subsequently, the data is transmitted to the central control system through the optical fiber network, and the data acquisition frequency and resolution are set according to actual needs to ensure the accuracy and real-time of the data. In addition, by connecting to the control system of the extraction pump, the operating parameters of the extraction pump can be obtained to monitor the working state of the extraction pump in real time, which plays an important role in controlling the gas extraction flow rate and pressure. For example, the gas extraction flow rate can be changed by adjusting the speed of the extraction pump.

[0032] It should be emphasized that the gas flow rate parameter is a key parameter directly reflecting the gas extraction effect, and the magnitude of the gas flow rate is affected by various factors, such as coal seam permeability, extraction pump performance, pipeline resistance, etc.

[0033] The flow prediction unit 120 is used to input the control timing data of the extraction pump and the gas sensing timing data of the pipeline into the gas extraction flow rate prediction model to predict the gas flow rate prediction timing data for the corresponding future second time period.

[0034] Here, the backbone network of the gas drainage flow prediction model adopts the LSTM model. In an example of the embodiment of the present application, the gas drainage flow prediction model can adopt a hybrid model including a SARIMA (Seasonal Autoregressive Integrated Moving Average) model module and an LSTM model module. Specifically, first, the SARIMA model is used to make a preliminary prediction on the historical gas flow data to obtain a preliminary prediction value sequence. Then, the prediction value sequence of the SARIMA model and other input features (such as gas pressure, temperature, operation parameters of the drainage pump, pipeline parameters, etc.) are used as the input of the LSTM model. Subsequently, the LSTM model further adjusts and optimizes the prediction result of the SARIMA model by learning the complex relationship between these input features and the gas flow to obtain the final predicted value of the gas drainage flow.

[0035] It should be noted that during the gas drainage process, the flow rate may be affected by seasonal factors. For example, the conditions such as coal seam temperature and air pressure in different seasons may be different, thus affecting the gas emission volume and drainage flow rate. In this way, through the SARIMA model module integrated in the hybrid model, the seasonal autoregressive and seasonal moving average parts can effectively capture this seasonal variation law. In addition, in addition to seasonal factors, there may also be trend changes and non-seasonal fluctuations in the gas drainage flow rate. The non-seasonal autoregressive, differencing, and moving average parts in the SARIMA model module can handle these fluctuations, and the number of differencing times can be adjusted according to the stationarity requirements of the data to eliminate the trend in the data. The non-seasonal autoregressive and moving average coefficients can capture the short-term dependence relationships and random fluctuations in the data.

[0036] Through the embodiment of the present application, combining SARIMA with a deep learning algorithm (i.e., LSTM) gives full play to the advantages of both. SARIMA can provide a preliminary prediction framework and, by using its processing capabilities for seasonality and trends, provide a better input for the deep learning model. Furthermore, LSTM can further learn the complex non-linear relationship between the input features and the gas flow and adjust and optimize the prediction result of SARIMA. Through the hybrid model structure, the accuracy and robustness of the prediction can be improved, better adapting to the characteristics of the gas drainage flow data, and being able to better capture the seasonality, trends, and non-seasonal changes of the gas drainage flow rate, thereby improving the accuracy and reliability of the prediction.

[0037] In another example of the embodiment of the present application, the gas drainage flow prediction model can also adopt a Bi-LSTM model based on the attention mechanism, and more details will be elaborated in combination with other examples below.

[0038] The extraction control unit 130 is used to input the pipeline gas sensing time series data, the gas flow prediction time series data, and the extraction pump control time series data into the gas extraction pressure control model to determine the extraction pump control parameter prediction time series data corresponding to the second time period.

[0039] Here, the gas extraction pressure control model adopts a Transformer model based on the attention mechanism. By using a Transformer model based on the attention mechanism to drive the adaptive control of gas extraction control parameters, it can dynamically focus on the key parts of the input time series data, and intelligently adjust the rotation speed and valve opening of the extraction pump according to the estimated gas flow and historical multi-modal data to ensure the stability of the extraction pipeline pressure.

[0040] Thus, by using the Transformer model, it can dynamically adjust the operation parameters of the extraction pump in the face of various complex situations, realizing the automation and refined control of the extraction process, especially providing a rapid response when the gas concentration fluctuates violently, and avoiding the decline of extraction efficiency or accidents.

[0041] Through the embodiments of the present application, an intelligent and efficient borehole gas extraction control system is constructed. Through the collaborative work of the LSTM and Transformer models, the system realizes the accurate prediction and control of gas flow and pressure, reduces the risk of human intervention, and improves the stability of gas extraction. In addition, the system can automatically adapt to complex gas extraction environments, optimize the operation parameters of equipment, and thus improve the operation efficiency and safety of the overall gas extraction system.

[0042] Figure 2 The structural block diagram of another example of the borehole gas extraction on-line metering control system according to the embodiments of the present application is shown.

[0043] As Figure 2 shown, the borehole gas extraction on-line metering control system 200 includes a data acquisition unit 210, a flow prediction unit 220, an extraction control unit 230, an extraction volume monitoring unit 240, and an alarm monitoring unit 250.

[0044] Regarding the specific implementation details of the data acquisition unit 210, the flow prediction unit 220, and the extraction control unit 230, reference can be made to and combined with the description of the relevant operations of the corresponding units in Figure 1 and will not be elaborated here.

[0045] It should be noted that the gas flow rate and concentration are significantly affected by environmental conditions (such as pressure and temperature). Under high-pressure or low-temperature conditions, the density, flow velocity, etc. of the gas will change, resulting in inaccurate direct measurement of the gas flow rate and concentration, which affects the overall control of the extraction system. The state equation of the gas shows that the volume (or flow rate) of the gas is directly related to the pressure and temperature. As coal mining progresses, the pressure and temperature in the mine environment will change, thereby affecting the changes in the gas flow rate and concentration.

[0046] In some embodiments, the extraction volume monitoring unit 240 is configured to perform the following operations: calculate a correction coefficient based on the pressure and temperature in each gas sensing data, and calculate the actual gas extraction volume sequence corresponding to the first time period based on the correction coefficient and the gas flow rate and gas concentration in each gas sensing data.

[0047] Through the embodiments of the present application, during the gas extraction process, the temperature and pressure often change dynamically over time. By calculating the correction coefficients of the pressure and temperature in real time, the system can automatically adjust the calculation method of the extraction volume according to the current mine conditions, achieving accurate calculation results of the gas extraction volume.

[0048] In some examples of the embodiments of the present application, the actual gas extraction volume sequence is calculated by the following formula:

[0049]

[0050] V k (t)=Q(t - k·Δt)×C g (t - k·Δt)×C(t - k·Δt)×Δt, Equation (2)

[0051]

[0052] In the formula, β 1 、β 2 and β 3 respectively represent the corresponding calibration coefficients, which are preset according to the coal seam characteristics and experimental data; P(t) and θ(t) are the pressure and temperature sampled and detected at the time step t respectively; m represents the total number of historical time steps in the first time period relative to the time step t; P 0 and θ 0 respectively represent the standard pressure and standard temperature; C(t) represents the correction coefficient at the time step t; V k (t) represents the actual gas extraction volume corresponding to the kth historical time step relative to the time step t; w k represents the weight coefficient of the kth historical time step, w 0 > w 1 >...> w m-1 where w 0The weight coefficient representing the time step t; V(t) represents the actual gas extraction volume at time step t, Q(t - k·Δt) represents the gas flow rate at time step t - k·Δt, Δt represents the time interval between adjacent time steps; C(t - k·Δt) represents the correction coefficient corresponding to time step t - k·Δt, and C g (t - k·Δt) represents the gas concentration corresponding to time step t - k·Δt.

[0053] In this embodiment, an appropriate total number of time steps m and weight factor w are selected k , and for each historical time step k, the actual gas extraction volume V k (t) is calculated. Subsequently, the weight factor is applied to perform a weighted sum of all V k (t) to obtain the actual gas extraction volume V(t) at the current time point.

[0054] It should be noted that during the process of coal mine gas extraction, the sensor data may show short-term abnormal fluctuations due to equipment interference or external environmental changes.

[0055] Through the embodiments of the present application, the data of multiple historical time steps are introduced for weighted averaging, effectively smoothing the influence brought by the instantaneous fluctuations of data such as gas flow rate and concentration in a short period of time, reducing the interference of abnormal data on the calculation results, and improving the stability and accuracy of the actual gas extraction volume sequence. In addition, by dynamically adjusting the weight factor w k , different importance can be assigned to the data of different time steps by the system. For example, the system can assign a higher weight to the data at the current moment, so as to more sensitively reflect the current gas extraction situation; while for earlier time steps, a lower weight is assigned, so that the influence of historical data gradually weakens, thereby enabling the system to better capture the change trends of gas flow rate and concentration and improving the accuracy of the determined actual gas extraction volume sequence.

[0056] In some embodiments, the alarm monitoring unit 250 is used to perform the following operations: monitor whether the gas sensing data in the second time period conforms to a preset safe sensing range. When the monitored gas sensing data does not conform to the safe sensing range, reduce the pumping speed of the extraction pump of the current borehole gas extraction pipeline and gradually close the extraction valve, and start the extraction pump of the standby extraction pipeline to enter the standby state. At this time, the extraction valve of the standby extraction pipeline is in the closed state, and the sensor of the standby extraction pipeline is controlled to start collecting data. After the extraction valve of the current borehole gas extraction pipeline is completely closed, open the extraction valve of the standby extraction pipeline, and adjust the pumping speed and valve opening of the extraction pump of the standby extraction pipeline to switch to the standby extraction pipeline to respond to the gas extraction task.

[0057] In the embodiments of the present application, the system can monitor gas sensing data in real time, quickly respond to situations beyond the safe sensing range, implement a real-time monitoring and early warning mechanism, and when key parameters such as gas concentration, pressure or temperature deviate from the safe range, automatically reduce the speed of the extraction pump and gradually close the extraction valve to avoid dangers caused by too fast extraction, reduce the time of manual intervention, improve the response speed of the system to emergencies, and thus ensure the safety of coal mine production.

[0058] On the other hand, when an abnormality occurs in the main extraction pipeline, the system can automatically switch to the standby extraction pipeline, ensure the continuity of the gas extraction task by starting the standby extraction pump and adjusting the valve opening, and effectively avoid the interruption of gas extraction caused by the failure of the main extraction pipeline through the main and standby pipeline switching mechanism, ensuring the stable operation of the system. In addition, during the pipeline switching process, the system will gradually adjust the speed of the extraction pump and the valve opening to ensure a smooth transition of the pipeline pressure, avoid pressure fluctuations or pipeline damage caused by sudden switching, help extend the equipment life and reduce the maintenance cost.

[0059] Figure 3 Fig. shows a schematic structural connection diagram of an example of a gas extraction flow prediction model according to an embodiment of the present application.

[0060] As Figure 3 shown, the gas extraction flow prediction model 300 adopts a Bi-LSTM model based on the attention mechanism, which includes cascaded TCN layer 310, Bi-LSTM layer 320, attention layer 330 and output layer 340.

[0061] More specifically, the TCN layer 310 is used to capture short-term and long-term dependencies in the extraction pump control timing data and the pipeline gas sensing timing data through multiple convolutional layers at different time scales.

[0062] Specifically, the TCN (Temporal Convolutional Network) layer extracts features at different time scales through convolutional operations to capture short-term and long-term dependencies in the gas flow data.

[0063]

[0064] In the formula, represents the multi-scale feature vector extracted by the TCN layer at the time step t of historical sampling, and TCN represents the feature processing process of the multi-scale temporal convolutional network; p represents the input feature sequence from time step t -n + 1 to time step t p and n represents the time window length. p

[0065] Through this embodiment, based on the introduction of a multi-scale temporal convolutional network, the model can capture short-term fluctuations and long-term trends in gas flow from different time scales. Through a multi-level feature extraction method, the model can more comprehensively understand the dynamic changes in gas flow, avoiding prediction errors caused by the limitations of a single time scale.

[0066] The Bi-LSTM layer 320 is used to capture the bidirectional dependencies of multi-scale feature vectors.

[0067] Specifically, after extracting multi-scale features, the Bi-LSTM layer 320 further processes these features to capture forward and backward temporal dependencies, enabling deeper modeling of the dependencies of sequential data.

[0068]

[0069] In the formula, represents the forward LSTM hidden state at time step t p ; is the forward LSTM cell, used to process the forward dependencies of the time series; represents the forward LSTM hidden state at the previous time step t p -1; represents the backward LSTM hidden state at time step t p ; is the backward LSTM cell, used to process the backward dependencies of the time series; is the backward LSTM hidden state at the next time step t p +1; represents the comprehensive hidden state at time step t p .

[0070] Through this embodiment, the Bi-LSTM layer 320 further processes the multi-scale features. Through the forward and backward LSTM structures, it can effectively capture the complex temporal dependencies in gas flow data. Thus, by integrating forward and backward information, the model can consider more historical and future context information during prediction, improving the accuracy of the prediction results.

[0071] The attention layer 330 adopts an adaptive multi-head attention mechanism to dynamically adjust the weights of each time step.

[0072] Specifically, through the adaptive multi-head attention mechanism, the hidden states of each sampling time step are adaptively weighted, and the attention weights can be dynamically adjusted according to the characteristics of the input data.

[0073]

[0074] MultiHead(Q, K, V) = Concat(head 1 ,..., head H )W A + b A , Equation (12)

[0075] where Attention(Q, K, V) represents the output of the attention mechanism, Q, K, and V respectively represent the query vector, key vector, and value vector obtained by linear transformation, K T represents the vector transpose of K, and d k represents the dimension of the key vector; represents the adaptive bias term corresponding to time step t p , softmax represents the softmax activation function; W b and b b respectively represent the weight matrix and bias term of the adaptive weight adjustment module, represents the input feature vector corresponding to time step t p ; head i represents the output of the i-th attention head, and W i Q , W i K , and W i V respectively represent the query transformation matrix, key transformation matrix, and value transformation matrix of the i-th attention head; Concat(head 1 ,..., head H ) represents concatenating the outputs of all H attention heads by dimension, and MultiHead(Q, K, V) represents the final output of the multi-head attention mechanism corresponding to time step t p , and W A and b A respectively represent the linear transformation weight matrix and bias vector of the multi-head attention output.

[0076] Through this embodiment, by introducing the adaptive multi-head attention mechanism, the model can dynamically adjust the weights of each time step according to the specific characteristics of the gas flow data. Furthermore, by highlighting the time points that have the greatest impact on the prediction results, the attention mechanism greatly improves the adaptability and prediction accuracy of the model in complex scenarios.

[0077] It should be noted that the adaptive bias term adopted in the attention mechanism enables the model to dynamically adjust the weights according to the changes in the input features, enhancing the adaptability of the model to environmental changes. Whether it is the drastic fluctuation of the gas flow or the change of external conditions, the model can make corresponding adjustments through the adaptive mechanism to ensure the stability and accuracy of the prediction results.

[0078] The output layer 340 is used to predict the gas flow rate at each future time step.

[0079]

[0080] In the formula, represents the predicted value of the gas flow rate at the future time step t s , t s = t p +Δt, where Δt represents the time interval between t s and t p ; W o and b o respectively represent the weight matrix and the bias term of the linear output layer.

[0081] Here, based on the output of the multi-head attention mechanism, the model generates the final predicted value of the gas flow rate through a linear transformation.

[0082] Through the embodiments of the present application, by integrating multi-scale feature extraction and a dynamic attention mechanism, the model can still maintain high prediction ability when facing data noise, sudden changes, and complex environmental conditions. In particular, in the case of sudden increase or decrease of the gas flow rate or changes in equipment parameters, the model can quickly adjust the prediction strategy and provide accurate prediction results. By accurately predicting the gas flow rate, potential gas accumulation risks can be identified in a timely manner, providing a reliable basis for the safety control of gas drainage and reducing the likelihood of gas accidents.

[0083] Figure 4 FIG. shows a schematic structural connection diagram of an example of a gas drainage pressure control model according to an embodiment of the present application.

[0084] As Figure 4 shown, the gas drainage pressure control model 400 includes an input layer 410, an encoder layer 420, a decoder layer 430, and an output layer 440.

[0085] The input layer 410 is used to receive the pipeline gas sensing time series data, the gas flow rate prediction time series data, and the extraction pump control time series data. After linear embedding and position encoding, a comprehensive sequence representation containing time and feature information is formed.

[0086] In the input layer, the calculation process of the position encoding vector is very important because it provides sequence information for the model, enabling the Transformer model to perceive the time order in the input sequence. In the gas drainage pressure control scenario, by adding position encoding for each time step, it is ensured that the model can identify the order between different time steps. Specifically, the position encoding uses sine and cosine functions, which act on different dimensions respectively to provide position information with different frequencies.

[0087]

[0088] wherein represents the input information at the t-th 1 time step corresponding to the sampled detection in the input data, and its dimension is d input ; W emb represents the linear embedding matrix, and its dimension is d model ×d input ; represents the input feature representation at the t-th 1 time step, and its dimension is d model ; represents the position encoding vector corresponding to the t-th 1 time step, which is used to inject the position information in the time series into the model, and its dimension is d model ; j represents the dimension index of the position encoding.

[0089] The encoder layer 420 is used to process the comprehensive sequence representation to capture the dependencies between each time step through the self-attention mechanism, so as to generate the corresponding context feature vector.

[0090] Among them, the encoder layer contains multiple encoding units, and each of the encoding units contains a cascaded self-attention mechanism layer and a feed-forward neural network layer. The feature processing process of the encoding unit is expressed by the following formula:

[0091]

[0092] wherein is the output feature vector calculated by the encoding unit for the input information at the t-th 1 time step, representing the context information after being processed by the self-attention mechanism and the feed-forward neural network; represents the attention weight of the time step t of the historical sampling 1 to the time step τ, z τ represents the input feature representation at the τ-th time step, T 1 represents the total number of time steps corresponding to the input data; W enc1 , W enc2 represents the weight matrix of the feed-forward neural network layer in the encoding unit, b enc1 , b enc2 represents the bias term of the feed-forward neural network layer in the encoding unit; ReLU represents the ReLU non-linear activation function.

[0093] The derivation process for the above formula (17) is as follows:

[0094] The processing process of the encoding unit can be expressed by the following formula:

[0095]

[0096] In the formula, represents the input feature of the coding unit, which is the comprehensive sequence representation from the previous coding unit or the input layer. SelfAtt(·) represents the self-attention mechanism processing process; FFN(·) represents the feed-forward neural network processing process.

[0097] The self-attention mechanism calculates the dependencies between each time step and other time steps in the sequence, generates attention weights, and calculates the weighted feature representation. Its calculation formula is as follows:

[0098]

[0099] The feed-forward neural network is used to perform further non-linear mapping on the features output by the self-attention mechanism, and its calculation formula is as follows:

[0100] FFN(h) = W 2 ·ReLU(W 1 ·h + b 1 ) + b 2 , Equation (20)

[0101] Furthermore, by combining the above Equations (18) to (20), Equation (17) is obtained.

[0102] Through this embodiment, each coding unit captures the dependencies between time steps in the sequence through the self-attention mechanism, and further processes these features through the feed-forward neural network, thereby generating the context feature vector.

[0103] The decoder layer 430 is used to process the context feature vector to generate the predicted control parameter feature sequence corresponding to the future time step through the multi-head self-attention mechanism and in combination with the masking mechanism. The decoder layer includes multiple decoding units, and each decoding unit includes a cascaded self-attention mechanism layer and a feed-forward neural network layer based on the masking mechanism. The feature processing process of the decoding unit is expressed by the following formula:

[0104]

[0105] In the formula, represents the control parameter feature generated by the decoding unit at the future time step t 2 ; h enc,ξ represents the context feature vector calculated by the encoder layer for the input information of the ξ-th time step of the historical sampling; represents the dependency of the decoder at time step t 2 on time step ξ, which is the attention weight obtained through the multi-head self-attention mechanism; W dec1 , W dec2represents the weight matrix of the feed-forward neural network layer in the decoding unit, b dec1 , b dec2 represents the bias term of the feed-forward neural network layer in the decoding unit.

[0106] Here, the self-attention mechanism and the processing process of the feed-forward neural network in the decoding unit are symmetric to those in the encoding unit, and the derivation details for Equation (21) will not be elaborated here. In addition, a masking mechanism is incorporated into the decoding unit, which only allows the decoder to access the current and previous time steps, preventing the decoder from seeing future data when predicting future time steps. That is to say, in the maximum time step is t 2 itself, and only the prediction sequence before time step t 2 is used for self-attention calculation. In this way, through the autoregressive generation method, the model can adjust the control parameters in real time according to the current and historical data, avoid prematurely leaking future information, and improve the accuracy of the prediction results.

[0107] Therefore, the model has the ability to respond quickly. When the gas drainage environment changes, it can adjust the drainage parameters in real time, achieve dynamic regulation, reduce hysteresis, and improve the operation efficiency and safety of the system.

[0108] The output layer 440 is used to perform a linear layer process on the predicted control parameter feature sequence to output the predicted values of the drainage pump control parameters for each time step in the corresponding future second time period.

[0109] Here, through linear transformation, the decoder features are mapped into specific control parameter prediction values, generating the rotational speed of the drainage pump and the opening degree of the valve for future time steps.

[0110]

[0111] In the formula, y dec,t represents the control parameter features generated by the decoder layer for the future time step t 2 ; respectively represent the predicted rotational speed of the drainage pump and the opening degree of the drainage valve for the corresponding time step t 2 ; W rpm , W valve represents the linear transformation matrix of the output layer, b rpm , b valve represents the bias term of the output layer.

[0112] It should be noted that in the Transformer model architecture adopted in the embodiments of this application, both its encoder unit and decoder unit adopt a method that combines the multi-head self-attention mechanism and the feed-forward neural network, which can effectively capture the complex interaction relationships between multi-dimensional features, such as the non-linear correlations between factors such as flow rate, concentration, and temperature, and can identify the impacts of different factors on the control parameters, thereby generating stable control prediction values, which helps to maintain the stable operation of the system during the gas drainage process.

[0113] Through the embodiments of this application, using the gas drainage pressure control model to accurately predict future gas flow rate and pressure can finely regulate the rotation speed of the drainage pump and the opening degree of the valve, adjust the drainage rate according to actual needs, avoid unnecessary energy consumption or over-drainage, and significantly improve the economic benefits of the overall system.

[0114] The details of the training process for the gas drainage pressure control model will be specifically described below:

[0115] First, construct a data sample set for the gas drainage pressure control model. The data set should be organized in a time series format, that is, for each time step, collect the corresponding sensor data and control parameters. In each sample, the input features at each time step include: gas flow rate, gas concentration, pressure, temperature, rotation speed of the drainage pump, opening degree of the valve, etc. In addition, set the label g for each future time step t which includes the control parameters (rotation speed and opening degree) of the future drainage pump in the corresponding situation. Then, divide the training set, validation set, and test set.

[0116] Then, initialize each layer of the gas drainage pressure control model and set the optimizer, such as Adam or SGD. Then, batch input the data samples at each time step in the training set into the model to optimize the training of the prediction task.

[0117] Subsequently, calculate the model loss based on the output prediction value and the true value of the model to minimize the model loss through iterative training, so as to achieve better prediction performance.

[0118] It should be noted that in the process of gas drainage control, the core goal of the system is to accurately predict and control the rotation speed and opening degree of the future drainage pump to ensure the stability and safety of the drainage volume. However, the gas flow rate and concentration are affected by multiple factors such as environmental conditions such as temperature and pressure, resulting in strong system dynamics. Therefore, an effective loss function design needs to be introduced to guide the model learning to ensure that the system can make predictions in complex scenarios and maintain the smoothness of the control parameters.

[0119] In view of this, in some examples of the embodiments of this application, the loss function L of the gas drainage pressure control modeltotal It is expressed by the following formula:

[0120] L total = λ 1 L MSE + λ 2 L smooth , Equation (24)

[0121]

[0122] Wherein, L MSE and L smooth respectively represent the prediction error loss term and the change rate constraint loss term, λ 1 and λ 2 respectively represent the weight coefficients of the corresponding loss terms; N represents the total number of samples in the data sample set, T g represents the total number of prediction time steps corresponding to the u-th sample, and respectively represent the predicted values of the drainage pump speed at the future time steps t g and t g -1 for the u-th sample; represents the label of the drainage pump speed at the future time step t g for the u-th sample; and respectively represent the predicted values of the valve opening at the future time steps t g and t g -1 for the u-th sample; represents the label of the valve opening at the future time step t g for the u-th sample.

[0123] In the loss function provided in this application, on the one hand, by introducing the mean square error (MSE) as the main loss term, the model can learn how to accurately predict the drainage pump speed and valve opening at future time steps, ensuring that the model can generate high-precision prediction values in various gas drainage scenarios and avoiding excessive prediction errors. In addition, due to the great differences that may exist in different mine conditions, MSE optimizes the prediction error of each sample one by one, enabling the model to maintain robustness in different environments and adapt to changes in different gas concentrations, temperatures, pressures, etc.

[0124] On the other hand, to ensure the stable operation of the extraction pump, the rate-of-change constraint loss term limits the parameter changes between adjacent time steps. When there are sudden changes in gas flow or fluctuations in environmental conditions, the smoothing loss makes the changes in control parameters tend to be gradual adjustments rather than instantaneous large changes, enhancing the smoothness of the system control parameters, reducing the drastic fluctuations in control parameters, thereby making the gas extraction system more stable and reliable during operation, avoiding safety risks caused by overloading of mechanical equipment or sudden increase in gas concentration, and at the same time reducing equipment wear and extending the service life of the equipment.

[0125] Through this embodiment, the MSE and the smoothing loss are combined according to the weights λ 1 and λ 2 Combined, the comprehensive loss function can prevent drastic changes in control parameters while ensuring prediction accuracy, ensuring that the model can not only generate accurate prediction results but also smoothly adjust the control parameters during the extraction process. The comprehensive loss function helps the model optimize these objectives simultaneously through multiple constraints, achieving efficient and safe gas extraction. In addition, by adjusting the values of λ 1 and λ 2 , the system can flexibly adapt to different gas extraction scenarios. In scenarios where high-precision prediction is required, the proportion of λ 1 can be increased accordingly. Additionally, when the system stability requirement is high, the proportion of λ 2 can be increased accordingly, enabling the model to optimize different objectives for different scenarios.

[0126] Figure 5 FIG. shows an operation flowchart of an example of the on-line metering control method for borehole gas extraction according to an embodiment of the present application.

[0127] As Figure 5 shown, in step S510, the extraction pump control timing data and the pipeline gas sensing timing data are acquired.

[0128] Here, the pipeline gas sensing timing data includes a plurality of gas sensing data for a corresponding adjacent first time period at the sampling position in the borehole gas extraction pipeline, and the gas sensing data includes gas flow rate, gas concentration, pressure, and temperature; the extraction pump control timing data includes a plurality of extraction pump control parameters for the corresponding first time period, and the extraction pump control parameters include extraction pump speed and extraction valve opening.

[0129] In step S520, the extraction pump control timing data and the pipeline gas sensing timing data are input into the gas extraction flow prediction model to predict the gas flow prediction timing data for a corresponding future second time period, and the backbone network of the gas extraction flow prediction model adopts an LSTM model.

[0130] In step S530, the pipeline gas sensing time series data, the gas flow prediction time series data, and the extraction pump control time series data are input into the gas extraction pressure control model to determine the extraction pump control parameter prediction time series data corresponding to the second time period. The gas extraction pressure control model uses a Transformer model based on the attention mechanism.

[0131] Figure 6 FIG. shows a field installation diagram of an example of the installation module of the high-level drill field according to an embodiment of the present application.

[0132] As Figure 6 shown, there are 12 boreholes in the high-level drill field, and 1 confluence pipe is set for each drill field. Therefore, 12 single-hole gas drainage pipeline comprehensive parameter measuring instruments, 12 single-hole gas pipeline electric valves, 1 confluence pipe gas drainage pipeline comprehensive parameter measuring instrument, and 1 confluence pipe electric valve are set for each drill field; in order to achieve better data transmission and remote control, 6 mine-intrinsic safety type wireless gateways are configured for each drill field, of which 2 are used for wirelessly transmitting monitoring data and 4 are used for controlling electric valves.

[0133] Combined with Figure 7 the screenshot of the terminal interface of the borehole gas extraction online metering control system according to the embodiment of the present application shown, by using on-line measuring instruments for parameters such as CH 4 concentration, CO concentration, O 2 concentration, temperature, pipeline pressure, ambient pressure, relative pressure, flow velocity, and pipeline flow rate (mixed flow rate, pure flow rate) in the extraction pipeline, accurate monitoring of gas boreholes and high-level drill fields is realized.

[0134] Here, by deploying borehole pipeline monitoring points in the high-level drill field, the gas extraction effect of the boreholes is analyzed and evaluated, and intelligent valves are deployed on the extraction pipeline to perform intelligent control on the borehole extraction pipeline. Further, unit measuring points and intelligent valves can also be deployed at the pipeline aggregation point of the high-level drill field to perform intelligent control on the extraction pipeline of the evaluation unit.

[0135] For more details and technical effects of the borehole gas extraction online metering control method provided by the embodiment of the present application, reference can be made to and combined with the description of the processing details of the borehole gas extraction online metering control system in other embodiments above, and the corresponding technical effects can be achieved.

[0136] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of combined actions. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be carried out in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application. In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] In some embodiments, the embodiments of this application provide a non-volatile computer-readable storage medium, in which one or more programs including execution instructions are stored. The execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to be used for executing the steps of any one of the above-mentioned online metering control methods for borehole gas drainage of this application.

[0138] In some embodiments, the embodiments of this application also provide a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer is enabled to execute the steps of any one of the above-mentioned online metering control methods for borehole gas drainage.

[0139] In some embodiments, the embodiments of this application also provide an electronic device, which includes: at least one processor, and a memory communicatively connected to the at least one processor. Among them, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the online metering control method for borehole gas drainage.

[0140] Figure 8 FIG. is a schematic hardware structure diagram of an electronic device for executing the online metering control method for borehole gas drainage provided by another embodiment of this application. As Figure 8 shown, the device includes:

[0141] One or more processors 810 and a memory 820, Figure 8 Taking one processor 810 as an example.

[0142] The device for executing the online metering control method for borehole gas drainage may further include: an input device 830 and an output device 840.

[0143] The processor 810, the memory 820, the input device 830, and the output device 840 can be connected through a bus or other means. Figure 8Take the bus connection as an example.

[0144] As a non-volatile computer-readable storage medium, the memory 820 can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the on-line metering control method for borehole gas drainage in the embodiments of the present application. By running the non-volatile software programs, instructions, and modules stored in the memory 820, the processor 810 executes various functional applications and data processing of the server, that is, implements the on-line metering control method for borehole gas drainage in the above method embodiments.

[0145] The memory 820 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the electronic device. In addition, the memory 820 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 820 may optionally include a memory remotely set relative to the processor 810, and these remote memories can be connected to the electronic device through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The input device 830 can receive input digital or character information, and generate signals related to the user settings and function control of the electronic device. The output device 840 may include a display device such as a display screen.

[0147] The one or more modules are stored in the memory 820 and, when executed by the one or more processors 810, execute the on-line metering control method for borehole gas drainage in any of the above method embodiments.

[0148] The above product can execute the method provided in the embodiments of the present application, and has the corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided in the embodiments of the present application.

[0149] The electronic device in the embodiments of the present application exists in various forms, including but not limited to:

[0150] (1) Mobile communication devices: These devices are characterized by having mobile communication functions and mainly aim to provide voice and data communication. Such terminals include: smart phones, multimedia phones, functional phones, and low-end phones, etc.

[0151] (2) Ultra-mobile personal computer devices: Such devices fall within the category of personal computers, have computing and processing capabilities, and generally also have the feature of mobile Internet access. Such terminals include: PDA, MID, UMPC devices, etc.

[0152] (3) Portable entertainment devices: Such devices can display and play multimedia content. Such devices include: audio and video players, handheld game consoles, e-books, as well as smart toys and portable in-vehicle navigation devices.

[0153] (4) Other on-board electronic devices with data interaction functions, such as in-vehicle device installed on vehicles.

[0154] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solutions, or the part that contributes to the related technologies, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0156] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. An online metering control system for drilling gas extraction, comprising: A data acquisition unit, used to acquire the extraction pump control timing data and pipeline gas sensor timing data; The pipeline gas sensor time series data includes a plurality of gas sensor data corresponding to a first adjacent time period of a sampling position in a borehole gas extraction pipeline, and the gas sensor data includes gas flow, gas concentration, pressure and temperature; the extraction pump control time series data includes a plurality of extraction pump control parameters corresponding to the first time period, and the extraction pump control parameters include extraction pump speed and extraction valve opening; A flow prediction unit, used for inputting the extraction pump control time series data and the pipeline gas sensor time series data into the gas extraction flow prediction model to predict the gas flow prediction time series data corresponding to the second time period in the future; the backbone network of the gas extraction flow prediction model adopts an LSTM model; A drainage control unit, used for inputting the pipeline gas sensor time series data, the gas flow prediction time series data and the drainage pump control time series data into a gas drainage pressure control model to determine the drainage pump control parameter prediction time series data corresponding to the second time period; the gas drainage pressure control model adopts a Transformer model based on an attention mechanism; The gas extraction flow prediction model adopts a Bi-LSTM model based on an attention mechanism, which includes a cascaded TCN layer, a Bi-LSTM layer, an attention layer, and an output layer; The TCN layer is used to capture short-term and long-term dependencies in the extraction pump control time series data and the pipeline gas sensor time series data at different time scales through multiple convolutional layers: In the formula, Indicates the time step t of historical sampling p The multi-scale feature vector extracted by the TCN layer, TCN represents the feature processing process of the multi-scale temporal convolutional network; Represents the time step t p -n+1 to time step t p The input feature sequence is n, where n represents the time window length; The Bi-LSTM layer is used to capture the bidirectional dependencies of multi-scale feature vectors: In the formula, Indicates that at time step t p The forward LSTM hidden state of It is a forward LSTM unit, which is used to process the forward dependency of time series; Indicates that at the previous time step t p -1 forward LSTM hidden state; Indicates that at time step t p The backward LSTM hidden state; It is a backward LSTM unit, which is used to process the backward dependency of time series; is at the next time step t p +1 backward LSTM hidden state; Indicates that at time step t p The comprehensive hidden state of The attention layer uses an adaptive multi-head attention mechanism to dynamically adjust the weight of each time step: MultiHead(Q,K,V)=Concat(head1,…,head H )W A +b A , In the formula, Attention(Q,K,V) represents the output of the attention mechanism, Q, K and V represent The query vector, key vector and value vector obtained by linear transformation, d k represents the dimension of the key vector; Denotes the corresponding time step t p The adaptive bias term, softmax represents the softmax activation function; W b and b b Represent the weight matrix and bias term of the adaptive weight adjustment module respectively, Denotes the corresponding time step t p The input feature vector of head i represents the output of the i-th attention head, W i Q , W i K and W i V Represents the query transformation matrix, key transformation matrix and value transformation matrix of the i-th attention head respectively; Concat(head1,…,head H ) means concatenating the outputs of all H attention heads by dimension, and MultiHead(Q,K,V) means the corresponding time step t p The final output of the multi-head attention mechanism, W A and b A Represent the linear transformation weight matrix and bias vector of the multi-head attention output respectively; The output layer is used to predict the gas flow at each future time step: In the formula, represents the future time step t s The predicted value of gas flow, t s =t p +△t,△t means t s With t p The time interval between o and b o They represent the weight matrix and bias term of the linear output layer respectively.

2. The system according to claim 1, wherein: The system also includes a drainage volume monitoring unit, which is used to perform the following operations: A correction coefficient is calculated according to the pressure and temperature in each of the gas sensor data, and an actual gas extraction volume sequence corresponding to the first time period is calculated according to the correction coefficient and the gas flow and gas concentration in each of the gas sensor data.

3. The system according to claim 2, wherein: The actual gas extraction volume sequence is calculated by the following formula: V k (t)=Q(t-k·△t)×C g (t-k·△t)×C(t-k·△t)×△t, Where β1, β2 and β3 represent the corresponding calibration coefficients, which are preset according to the coal seam characteristics and experimental data; P(t) and θ(t) are the pressure and temperature sampled and detected at time step t; m represents the total number of historical time steps in the first time period relative to time step t; P0 and θ0 represent the standard pressure and standard temperature, respectively; C(t) represents the correction coefficient at time step t; V k (t) represents the actual gas extraction volume corresponding to the kth historical time step relative to time step t; w k Represents the weight coefficient of the kth historical time step, w0>w1>…>w m-1 , where w0 represents the weight coefficient of time step t; V(t) represents the actual gas extraction volume at time step t, Q(tk·△t) represents the gas flow rate at time step tk·△t, △t represents the time interval between adjacent time steps; C(tk·△t) represents the correction coefficient corresponding to time step tk·△t, C g (tk·△t) represents the gas concentration corresponding to the time step tk·△t.

4. The system according to claim 1, further comprising an alarm monitoring unit configured to: Monitoring whether the gas sensor data in the second time period meets a preset safety sensing range; When the monitored gas sensor data does not conform to the safety sensor interval, the extraction pump speed of the current borehole gas extraction pipeline is reduced and the extraction valve is gradually closed, and the extraction pump of the standby extraction pipeline is started to enter the standby state; at this time, the extraction valve of the standby extraction pipeline is in a closed state, and the sensor of the standby extraction pipeline is controlled to start collecting data; After the extraction valve of the current borehole gas extraction pipeline is completely closed, the extraction valve of the backup extraction pipeline is opened, and the extraction pump speed and valve opening of the backup extraction pipeline are adjusted to switch to the backup extraction pipeline to respond to the gas extraction task.

5. The system according to any one of claims 1 to 4, wherein: The gas extraction flow prediction model adopts a hybrid model including a SARIMA model module and a LSTM model module.

6. The system according to claim 1, wherein: The gas extraction pressure control model comprises an input layer, an encoder layer, a decoder layer and an output layer; The input layer is used to receive the pipeline gas sensor time series data, the gas flow prediction time series data and the extraction pump control time series data, and after linear embedding and position encoding, a comprehensive sequence representation containing time and feature information is formed: In the formula, Represents the input information of the t1th time step corresponding to the sampling detection in the input data, and its dimension is d input ; W emb Represents a linear embedding matrix with dimension d model ×d input ; Represents the input feature representation at the t1th time step, with a dimension of d model ; Represents the position encoding vector corresponding to the t1th time step, which is used to inject position information in the time series into the model, with a dimension of d model ; j represents the dimension index of the position encoding; The encoder layer is used to process the comprehensive sequence representation to capture the dependency between each time step through the self-attention mechanism, thereby generating a corresponding context feature vector; wherein the encoder layer includes a plurality of encoding units, each of which includes a cascaded self-attention mechanism layer and a feedforward neural network layer; the feature processing process of the encoding unit is expressed by the following formula: In the formula, is the output feature vector calculated by the encoding unit for the input information at the t1th time step, representing the context information after being processed by the self-attention mechanism and the feedforward neural network; represents the attention weight of the historical sampling time step t1 to the time step τ, z τ represents the input feature representation at the τth time step, T1 represents the total number of time steps corresponding to the input data; W enc1 ,W enc2 represents the weight matrix of the feedforward neural network layer in the encoding unit, b enc1 ,b enc2 Represents the bias term of the feedforward neural network layer in the encoding unit; ReLU represents the RELU nonlinear activation function; The decoder layer is used to process the context feature vector to generate a control parameter feature sequence corresponding to the prediction of the future time step through a multi-head self-attention mechanism combined with a mask mechanism; the decoder layer includes a plurality of decoding units, each of which includes a cascaded self-attention mechanism layer based on a mask mechanism and a feedforward neural network layer; the feature processing process of the decoding unit is expressed by the following formula: In the formula, represents the control parameter features generated by the decoding unit at the future time step t2; h enc,ξ represents the context feature vector calculated by the encoder layer for the input information of the ξ-th time step of the historical sampling; represents the dependency of the decoder at time step t2 on time step ξ, which is the attention weight obtained by the multi-head self-attention mechanism; W dec1 ,W dec2 represents the weight matrix of the feedforward neural network layer in the decoding unit, b dec1 ,b dec2 represents the bias term of the feedforward neural network layer in the decoding unit; The output layer is used to perform linear layer processing on the predicted control parameter feature sequence to output predicted values ​​of the drainage pump control parameters at each time step in the second time period in the future: In the formula, represents the control parameter features generated by the decoder layer for the future time step t2; They represent the pump speed and valve opening predicted at the corresponding time step t2 respectively; W rpm ,W valve represents the linear transformation matrix of the output layer, b rpm ,b valve Represents the bias term of the output layer.

7. The system according to claim 6, wherein: The loss function L of the gas extraction pressure control model is total It is expressed by the following formula: L total =λ1L MSE +λ2L smooth , Where, L MSE and L smooth They represent the prediction error loss term and the change rate constraint loss term respectively, λ1 and λ2 represent the weight coefficients of the corresponding loss terms respectively; N represents the total number of samples in the data sample set, T g represents the total number of predicted time steps corresponding to the u-th sample, and Respectively represent the u-th sample in the future time step t g and t g -1 is the predicted value of the pump speed; Represents the u-th sample at the future time step t g The extraction pump speed label; and Respectively represent the u-th sample in the future time step t g and t g -1 is the predicted value of valve opening; Represents the u-th sample at the future time step t g Valve opening label.

Images