Goaf coal spontaneous combustion dynamic early warning method and system based on optical fiber temperature measurement

Abstract

The invention relates to the technical field of coal mining, and provides a goaf coal spontaneous combustion dynamic early warning method and system based on optical fiber temperature measurement. The method comprises the following steps: preprocessing time sequence temperature original data of different preset temperature measurement points in a goaf obtained in real time based on distributed temperature sensing optical fibers arranged in the goaf, and predicting and evaluating the coal temperature of each temperature measurement point in the goaf in a future time period based on an STGCN goaf temperature prediction model according to time sequence temperature standard data of the goaf; thirdly, generating a temperature cloud picture of the goaf according to the predicted coal temperature value of each temperature measurement point in the goaf in the future time period, and performing iterative updating on the temperature cloud picture based on a gradient optimization algorithm to determine the maximum coal temperature value in the goaf; and finally, calculating a trend fluctuation index of a temperature point corresponding to the maximum coal temperature value in the goaf, and performing dynamic early warning on coal spontaneous combustion in the goaf according to the trend fluctuation index and the corresponding maximum coal temperature value on the basis of a predetermined early warning grade triggering condition.

Description

Technical Field

[0001] The present application relates to the field of coal mining technology, and in particular to a method and system for dynamic early warning of spontaneous combustion of coal in goaf areas based on optical fiber temperature measurement. Background Art

[0002] Goaf refers to the area where all coal has been mined and the supporting equipment has been withdrawn during the coal mining process. Since a large amount of unmined coal or coal powder has accumulated in these areas, these coal or coal powder are prone to spontaneous combustion under certain conditions. The occurrence of spontaneous combustion will not only lead to a waste of coal resources, but may also cause disasters such as fire and explosion, seriously threatening the safety of the mine.

[0003] Spontaneous combustion of coal in goaf is a complex and dangerous process. As the depth and intensity of coal mining increase, the mining geological conditions become more complex, and there is a relative increase in spontaneous combustion accidents of coal in goaf, which seriously threatens the safe production of coal mines.

[0004] Therefore, there is an urgent need to provide a technical solution to the above-mentioned deficiencies in the prior art. Summary of the invention

[0005] The purpose of this application is to provide a method and system for dynamic early warning of spontaneous combustion of coal in goaf areas based on optical fiber temperature measurement, so as to solve or alleviate the problems existing in the above-mentioned prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The present application provides a method for dynamic early warning of spontaneous combustion of coal in goafs based on optical fiber temperature measurement, comprising: step S101, preprocessing the original time-series temperature data of different preset temperature measurement points in the goaf acquired in real time by distributed temperature-sensing optical fibers arranged in the goaf, to obtain the time-series temperature standard data of the goaf; wherein the preprocessing includes: missing value filling, outlier removal and data standardization; step S102, constructing a goaf temperature prediction model based on STGCN, and predicting the coal temperature of each temperature measurement point in the goaf in the future time period according to the time-series temperature standard data , and evaluate the prediction results based on preset evaluation indicators; step S103, generate a temperature cloud map of the goaf according to the predicted coal temperature of each temperature measuring point in the goaf in the future time period, and iteratively update the temperature cloud map based on the gradient optimization algorithm to determine the maximum coal temperature in the goaf; step S104, calculate the trend fluctuation index of the temperature point corresponding to the maximum coal temperature in the goaf, and according to the trend fluctuation index and the corresponding maximum coal temperature, based on the predetermined warning level trigger condition, perform dynamic warning on spontaneous combustion of coal in the goaf.

[0008] Preferably, in step S101, according to the formula:

[0009]

[0010] The distributed temperature-sensing optical fiber is arranged in the goaf; wherein a is the number of the distributed temperature-sensing optical fibers arranged in the goaf, D is the integer width of the goaf; m is the number of the temperature measuring points; L is the distance between two adjacent temperature measuring points on the distributed temperature-sensing optical fiber

[0011] Preferably, in step S102, the time series temperature standard data at different positions are converted based on the adjacency matrix to obtain graph structure data; a graph convolution layer based on a graph convolutional neural network is constructed, and the spatial features of each data node in the graph structure data are extracted through a graph convolution operation, and the extracted spatial features of the data nodes are updated; a time series convolution layer based on a gated convolutional neural network is constructed, and the convolution kernel is slid on the time series of the time series temperature standard data, and a dot product operation is performed on a subsequence of the time series of the time series temperature standard data to extract the time features of each data node, and the evolution pattern of each data node is captured based on the time series convolution operation; a global pooling operation is performed on the extracted spatial features and time features of all the data nodes to obtain the global spatiotemporal features of the graph structure data, and the coal temperature prediction value of each temperature measuring point in the goaf in the future time period is determined based on the evolution pattern of the data nodes.

[0012] Preferably, the updating of the extracted spatial features of the data nodes comprises: according to the formula:

[0013]

[0014] The extracted spatial features of the data nodes are updated; wherein, is the spatial feature obtained for the data node i in the l-th graph convolution operation of the graph convolution layer; is an adjacency matrix, representing the connection relationship between the data node i and the data node j in the l-th layer graph convolution operation of the graph convolution layer; is the spatial convolution weight matrix in the l-th graph convolution operation of the graph convolution layer; is the updated spatial feature of the data node i in the l-th graph convolution operation of the graph convolution layer; σ is the activation function.

[0015] Preferably, the capturing of the evolution pattern of each of the data nodes based on the time series convolution operation includes: according to the formula:

[0016]

[0017] capturing an evolution pattern of the data nodes;

[0018] in, is the time feature obtained for the data node i in the l+1th layer of the temporal convolution operation of the temporal convolution layer; is the input feature of the data node i in the lth layer of the temporal convolution operation of the temporal convolution layer; σ is the activation function; k is the temporal convolution kernel in the lth layer of the temporal convolution operation of the temporal convolution layer , p is the step size of the l-th layer of temporal convolution operation of the temporal convolution layer; d is the dimension of the input features of the data node i in the l-th layer of temporal convolution operation of the temporal convolution layer; D is the number of data channels of the l-th layer of temporal convolution operation of the temporal convolution layer; K is the maximum value of the convolution kernel of the l-th layer of temporal convolution operation of the temporal convolution layer; P is the maximum step size of the l-th layer of temporal convolution operation of the temporal convolution layer.

[0019] Preferably, according to the formula:

[0020]

[0021] The spatial features of all the extracted data nodes Time characteristics Perform global pooling operation; where z (l+1) is the global spatiotemporal feature obtained after the global pooling operation; is the feature representation of the data node i, N is the number of the data nodes, and N is a positive integer.

[0022] Preferably, in step S103, based on the preset coordinate system of the goaf, the spatial coordinates of each temperature measuring point are defined; based on the inverse distance weighted method, the predicted coal temperature values ​​of the future time periods at each temperature measuring point in the goaf are interpolated to construct a continuous temperature field of the goaf to generate a temperature cloud map of the goaf; based on the preset objective function, the coal temperature distribution in the goaf is updated according to the temperature gradient of each temperature measuring point in the temperature cloud map to determine the highest coal temperature in the goaf.

[0023] Preferably, according to the formula:

[0024]

[0025] The predicted coal temperature values ​​of the future time periods of each temperature measuring point in the goaf are interpolated to obtain the coal temperature value z0 of the target position in the goaf; wherein z i is the value of the bth temperature measuring point around the target position; B is the number of the temperature measuring points around the target position, and b and B are both positive integers; d b pis the distance between the target position and the bth temperature measuring point; p is a constant.

[0026] Preferably, step S104 includes:

[0027] According to the formula:

[0028]

[0029] Determine the trend fluctuation index of the temperature point corresponding to the maximum value of the coal temperature in the goaf;

[0030] Among them, A is the change rate of the temperature point corresponding to the maximum value of coal temperature in the goaf, A t A is the coal temperature value at the temperature point t corresponding to the maximum coal temperature in the goaf; t-1 is the coal temperature value at the temperature point t-1 corresponding to the maximum coal temperature in the goaf; A t With A t-1 B is the time interval between the two; B is the deviation rate of the temperature point corresponding to the maximum value of the coal temperature in the goaf; B t The value at the temperature point t corresponding to the maximum coal temperature in the goaf; is the value at the temperature point t-1 corresponding to the maximum value of the coal temperature in the goaf; R OSC The time interval of the temperature point corresponding to the maximum coal temperature in the goaf The vibration amplitude of the internal temperature change; C Tmax The temperature point corresponding to the maximum coal temperature in the goaf in the time interval Maximum coal temperature in the Tmin The temperature point corresponding to the maximum coal temperature in the goaf in the time interval Minimum coal temperature within R OFC is the number of temperature changes at the temperature point corresponding to the maximum coal temperature in the goaf; f(C t″ , C t″ ) indicates the temperature point corresponding to the maximum value of coal temperature in the goaf in the time interval The number of different internal temperature values; C t′ , C t″ They are the temperature points corresponding to the maximum coal temperature in the goaf at the time interval Temperature value C at time t′ t′ and the temperature value C at time t″ t″ .

[0031] The embodiment of the present application also provides a goaf area coal spontaneous combustion dynamic early warning system based on optical fiber temperature measurement, including: a data preprocessing unit, configured to preprocess the time series temperature raw data of different preset temperature measuring points in the goaf acquired in real time based on the distributed temperature sensing optical fiber arranged in the goaf, to obtain the time series temperature standard data of the goaf; wherein the preprocessing includes: missing value filling, outlier removal and data standardization; a coal temperature prediction unit, configured to construct a goaf area temperature prediction model based on STGCN, and according to the time series temperature standard data, predict the coal temperature of each temperature measuring point in the goaf in the future time period. Prediction, and based on preset evaluation indicators, evaluate the prediction results; the highest point temperature unit is configured to generate a temperature cloud map of the goaf according to the predicted coal temperature of each temperature measuring point in the goaf in the future time period, and iteratively update the temperature cloud map based on the gradient optimization algorithm to determine the maximum value of the coal temperature in the goaf; the trend warning unit is configured to calculate the trend fluctuation index of the temperature point corresponding to the maximum value of the coal temperature in the goaf, and according to the trend fluctuation index and the corresponding maximum value of the coal temperature, based on the predetermined warning level trigger condition, dynamically warn of the spontaneous combustion of coal in the goaf.

[0032] Beneficial effects:

[0033] In the method for dynamic early warning of spontaneous combustion of coal in goaf based on optical fiber temperature measurement provided in the embodiment of the present application, first, the original time-series temperature data of different preset temperature measuring points in the goaf acquired in real time by the distributed temperature-sensing optical fiber arranged in the goaf are preprocessed to obtain the time-series temperature standard data of the goaf; then, a goaf temperature prediction model based on STGCN is constructed, and the coal temperature of each temperature measuring point in the goaf in the future time period is predicted based on the time-series temperature standard data, and the prediction result is evaluated based on the preset evaluation index; then, a temperature cloud map of the goaf is generated based on the predicted coal temperature of each temperature measuring point in the goaf in the future time period, and the temperature cloud map is iteratively updated based on the gradient optimization algorithm to determine the maximum value of the coal temperature in the goaf; finally, the trend fluctuation index of the temperature point corresponding to the maximum value of the coal temperature in the goaf is calculated, and according to the trend fluctuation index and the corresponding maximum value of the coal temperature, a dynamic early warning of spontaneous combustion of coal in the goaf is performed based on the predetermined early warning level trigger condition.

[0034] Therefore, by collecting temperature time series data from a limited number of temperature measuring points, the coal temperature at each temperature measuring point in the goaf in the future time period is dynamically predicted and evaluated through the spatiotemporal graph convolutional neural network, and the prediction results are dynamically iterated and updated in real time through the gradient optimization algorithm, thereby determining the maximum value of the coal temperature in the entire goaf in the future time period, realizing effective monitoring and early warning of coal spontaneous combustion accidents in the goaf, and providing technical support for safe production in coal mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0036] in:

[0037] Figure 1 A schematic flow chart of a method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to some embodiments of the present application;

[0038] Figure 2 A schematic diagram of graph data conversion provided according to some embodiments of the present application;

[0039] Figure 3 A schematic structural diagram of a dynamic early warning system for spontaneous combustion of coal in goaf areas based on optical fiber temperature measurement according to some embodiments of the present application. DETAILED DESCRIPTION

[0040] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. Each example is provided by way of explanation of the present application and does not limit the present application. In fact, it will be clear to those skilled in the art that modifications and variations may be made in the present application without departing from the scope or spirit of the present application. For example, a feature shown or described as a part of an embodiment may be used in another embodiment to produce yet another embodiment. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the embodiments of the present invention should belong to the scope of protection of the embodiments of the present invention.

[0041] like Figure 1 , Figure 2 As shown, the method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement provided in the embodiment of the present application includes:

[0042] Step S101, pre-processing the original time-series temperature data of different preset temperature measurement points in the goaf area acquired in real time by the distributed temperature sensing optical fiber arranged in the goaf area, to obtain the time-series temperature standard data of the goaf area.

[0043] In this application, the temperature of a limited number of temperature measurement points in the goaf is monitored in real time through the distributed temperature-sensitive optical fibers arranged in the goaf. Specifically, parallel temperature-sensitive optical fibers are arranged at intervals of 5 meters on the return air side and the air inlet side of the goaf, and temperature measurement points are arranged at intervals of 1 meter on each temperature-sensitive optical fiber to achieve real-time monitoring of the temperature in the goaf. According to the formula:

[0044]

[0045] Distributed temperature sensing optical fibers are laid in the goaf. Where a is the number of distributed temperature sensing optical fibers in the goaf, D is the integer width of the goaf, m is the number of temperature measurement points, and L is the distance between two adjacent temperature measurement points on the distributed temperature sensing optical fiber.

[0046] The distributed temperature-sensing optical fiber is used to obtain the original time-series temperature data of different temperature measurement points in the goaf in real time, and transmits it to the edge device through the transmission optical fiber. The edge device performs missing value filling, outlier removal and data standardization on the original time-series temperature data of each temperature measurement point of the temperature-sensing optical fiber. Among them, the missing values ​​of the original time-series temperature data are filled by the approximate average method, and the entire row of the filled original time-series temperature data is removed by the box plot analysis method.

[0047] Then, the original data of the time series temperature after data removal is calculated according to the formula:

[0048]

[0049] Perform data standardization. Among them, u is the standardized data, that is, the time series temperature standard data, x is the time series temperature original data after data elimination, μ is the average value of the time series temperature original data after data elimination, and s is the variance of the time series temperature original data after data elimination.

[0050] Step S102: construct a goaf temperature prediction model based on STGCN, and predict the coal temperature of each temperature measuring point in the goaf in the future time period according to the time series temperature standard data, and evaluate the prediction results based on preset evaluation indicators.

[0051] In the present application, the temperature time series standard data at different positions are converted based on the adjacency matrix to generate graph structure data. Among them, the nodes in the graph structure data represent the spatial positions of the temperature measuring points corresponding to each temperature time series standard data, and the edges of the graph structure data represent the connection relationship between the nodes, that is, the relationship between the temperature measuring points corresponding to each temperature time series standard data. In other words, each temperature monitoring point in the mine is taken as a node, and the connection relationship between the nodes is represented by the adjacency matrix to capture the spatial relationship of each temperature monitoring point. The adjacency matrix is ​​combined with the standard data, and the temperature time series standard data is converted into graph data in combination with the node feature matrix.

[0052] A temperature prediction model based on Spatio-Temporal Graph Convolutional Networks (STGCN) is proposed. The temperature prediction model contains two spatio-temporal convolution blocks and a global pooling layer. The spatial domain features and temporal domain features of each data node in the graph structure data are fused through the two spatio-temporal convolution blocks, and the spatial domain features and temporal domain features of all nodes are globally pooled through the global pooling layer to obtain the global spatio-temporal features of the temperature in the goaf.

[0053] Each spatiotemporal convolution block contains two graph convolution layers (Spatial Graph-Cony) and one temporal convolution layer (Temporal Gated-Conv), and the temporal convolution layer is located between the two graph convolution layers. Among them, the graph convolution layer is built based on the graph convolution neural network (Spatial Graph-Cony), and extracts the spatial features of each data node in the graph structure data through the graph convolution operation, and updates the spatial features of the extracted data nodes through the graph convolution operation to reflect the spatial relationship between the temperature measurement points in the goaf. Specifically, according to the formula:

[0054]

[0055] Update the spatial features of the extracted data nodes;

[0056] in, is the spatial feature obtained for data node i in the l-th graph convolution operation of the graph convolution layer; is the adjacency matrix, which represents the connection relationship between data node i and data node j in the l-th layer graph convolution operation of the graph convolution layer; is the spatial convolution weight matrix in the l-th graph convolution operation of the graph convolution layer; is the updated spatial feature of data node i in the l-th graph convolution operation of the graph convolution layer; σ is the Leaky ReLU activation function.

[0057] The temporal convolution layer in the spatiotemporal convolution block is constructed based on a gated convolutional neural network, and the convolution kernel slides on the time series of the time series temperature standard data, performs dot product operations on the subsequences of the time series of the time series temperature standard data, extracts the time features of each data node, and captures the evolution pattern of each data node based on the temporal convolution operation. Among them, the data of a continuous time step on the time series of the time series temperature standard data is selected through the temporal convolution operation to obtain the subsequence of the time series of the time series temperature standard data.

[0058] Specifically, according to the formula:

[0059]

[0060] Capture the evolution pattern of data nodes. is the temporal feature obtained for data node i in the l+1th temporal convolution operation of the temporal convolution layer; is the input feature of the data node i in the l-th layer of the temporal convolution operation of the temporal convolution layer; σ is the Leaky ReLU activation function; k is the temporal convolution kernel in the l-th layer of the temporal convolution operation of the temporal convolution layer , p is the step size of the l-th layer of temporal convolution operation of the temporal convolution layer; d is the dimension of the input features of data node i in the l-th layer of temporal convolution operation of the temporal convolution layer; D is the number of data channels of the l-th layer of temporal convolution operation of the temporal convolution layer; K is the maximum value of the convolution kernel of the l-th layer of temporal convolution operation of the temporal convolution layer; P is the maximum step size of the l-th layer of temporal convolution operation of the temporal convolution layer.

[0061] Next, the global pooling layer performs global pooling operations on the spatial and temporal features of all extracted data nodes, aggregates all information in the graph structure data, and obtains the global spatiotemporal features of the graph structure data. Specifically, according to the formula:

[0062]

[0063] Spatial features of all extracted data nodes Time characteristics Perform global pooling operation. Among them, z (l+1) is the global spatiotemporal feature obtained after the global pooling operation; is the feature representation of data node i, N is the number of data nodes, and N is a positive integer.

[0064] Finally, according to the change of temperature in the goaf over time, the coal temperature of each temperature measuring point is inferred from the extracted global spatiotemporal features. That is, the predicted value of the coal temperature of each temperature measuring point in the goaf in the future time period is determined based on the evolution pattern of the data node, and the predicted value of the coal temperature of each temperature measuring point in the future time period is output through the output layer of the temperature prediction model, so as to realize the real-time dynamic display of the dynamic change of the coal temperature of each temperature measuring point in the goaf in space over time.

[0065] In this application, after the coal temperature prediction values ​​of each temperature measuring point in the future time period are output through the output layer, the mean absolute error MAE, root mean square error RMSE and determination coefficient R 2 , evaluate the prediction results of the goaf temperature prediction model. Specifically, according to the formula:

[0066]

[0067] Determine the evaluation indicators of the prediction results of the goaf temperature prediction model - mean absolute error MAE, root mean square error RMSE and determination coefficient R 2 Among them, Y h is the hth coal temperature prediction value of the goaf temperature prediction model, y h For Y h The actual value of the coal temperature in the corresponding goaf; H is a positive integer, is the average value of H coal temperature prediction values.

[0068] Step S103, generating a temperature cloud map of the goaf according to the predicted coal temperature of each temperature measuring point in the goaf in the future time period, and iteratively updating the temperature cloud map based on the gradient optimization algorithm to determine the maximum value of the coal temperature in the goaf.

[0069] In this application, based on the preset coordinate system of the goaf, the spatial coordinates of each temperature measuring point are defined; then, based on the inverse distance weighted method, the predicted coal temperature values ​​of each temperature measuring point in the goaf in the future time period are interpolated to construct a continuous temperature field of the goaf, and the contourf function is used to draw the continuous temperature field data into a temperature cloud map of the goaf. The temperature cloud map of the goaf can be used to divide the heat dissipation zone, oxidation warming zone and asphyxiation zone of the goaf, and obtain the dynamic development law of the "three zones" of the goaf.

[0070] Specifically, according to the formula:

[0071]

[0072] The predicted coal temperature values ​​of each temperature measuring point in the goaf in the future time period are interpolated to obtain the coal temperature value z0 at the target position in the goaf. i is the value of the bth temperature measurement point around the target position; B is the number of temperature measurement points around the target position, and both b and B are positive integers; d b p is the distance between the target position and the bth temperature measurement point; p is an adjustable parameter, and its value is constant 1 or constant 2.

[0073] Finally, based on the preset objective function, the coal temperature distribution in the goaf is updated according to the temperature gradient of each temperature measuring point in the temperature cloud map to determine the maximum coal temperature in the goaf. Specifically, the preset objective function is:

[0074]

[0075] Among them, T′ eu is the temperature T of the temperature measuring point with spatial coordinates (e, u) in the goaf eu Updated temperature; is the temperature gradient of the temperature measuring point with spatial coordinates (e, u) in the goaf; T is a variable that represents the temperature distribution in the goaf.

[0076] By deriving the preset objective function, the temperature gradient of each temperature measurement point and the impact of temperature change on the objective function are calculated. The direction of the temperature gradient is along the direction of the maximum temperature increase. Specifically, according to the formula:

[0077]

[0078] The temperature gradient of the temperature measuring point with spatial coordinates (e, u) in the goaf is determined, and then the coal temperature distribution in the goaf is updated using the temperature gradient to determine the maximum coal temperature f(T) in the goaf.

[0079] Through the above steps, the temperature cloud map is continuously iterated and updated, the temperature of each point in the temperature cloud map is adjusted, and a continuous final temperature field of the goaf is generated. Through the final temperature field, the coordinates and temperature value of the highest coal temperature point in the entire goaf in the future time period can be accurately determined.

[0080] Step S104, calculate the trend fluctuation index of the temperature point corresponding to the maximum coal temperature in the goaf, and according to the trend fluctuation index and the corresponding maximum coal temperature, based on the predetermined warning level trigger conditions, perform dynamic warning on spontaneous combustion of coal in the goaf.

[0081] Specifically, according to the formula:

[0082]

[0083] Determine the trend fluctuation index of the temperature point corresponding to the maximum coal temperature in the goaf.

[0084] Among them, A is the change rate of the temperature point corresponding to the maximum value of coal temperature in the goaf, A t A is the coal temperature value at the temperature point t corresponding to the maximum coal temperature in the goaf; t-1 is the coal temperature value at the temperature point t-1 corresponding to the maximum coal temperature in the goaf; A t With A t-1 The time interval between them; B is the deviation rate of the temperature point corresponding to the maximum value of coal temperature in the goaf; B t is the value at the temperature point t corresponding to the maximum coal temperature in the goaf; is the value at the temperature point t-1 corresponding to the maximum coal temperature in the goaf; R OSC The time interval of the temperature point corresponding to the maximum coal temperature in the goaf The vibration amplitude of the internal temperature change; C Tmax The temperature point corresponding to the maximum coal temperature in the goaf in the time interval Maximum coal temperature in the Tmin The temperature point corresponding to the maximum coal temperature in the goaf in the time interval Minimum coal temperature within R OFC is the number of temperature changes at the temperature point corresponding to the highest coal temperature in the goaf; f(C t′ , C t″ ) indicates the temperature point corresponding to the maximum value of coal temperature in the goaf in the time interval The number of different internal temperature values; C t′ , C t″ They are the temperature points corresponding to the maximum coal temperature in the goaf at the time interval Temperature value C at time t′ t′ and the temperature value C at time t″ t″ .

[0085] By constructing the trend of the highest temperature point in the goaf, the possible development trend of the current goaf state can be effectively reflected, so as to realize the early perception of the goaf fire disaster. At the same time, based on the coal sample temperature rise test, the warning level trigger threshold of different coal mines and coal qualities is determined, and the trend fluctuation index is compared with the warning level trigger threshold, and different levels of warning are given for the future state of the goaf, so as to adjust the response measures in a timely and effective manner.

[0086] like Figure 3 As shown, the embodiment of the present application also provides a goaf area coal spontaneous combustion dynamic early warning system based on optical fiber temperature measurement, comprising:

[0087] The data preprocessing unit 301 is configured to preprocess the original time-series temperature data of different preset temperature measurement points in the goaf area acquired in real time by the distributed temperature sensing optical fiber arranged in the goaf area, so as to obtain the time-series temperature standard data of the goaf area; wherein the preprocessing includes: missing value filling, outlier elimination and data standardization;

[0088] The coal temperature prediction unit 302 is configured to construct a goaf temperature prediction model based on STGCN, and predict the coal temperature of each temperature measuring point in the goaf in the future time period according to the time series temperature standard data, and evaluate the prediction results based on the preset evaluation index;

[0089] The highest point temperature unit 303 is configured to generate a temperature cloud map of the goaf according to the predicted values ​​of the coal temperature of each temperature measuring point in the goaf in the future time period, and iteratively update the temperature cloud map based on the gradient optimization algorithm to determine the highest value of the coal temperature in the goaf;

[0090] The trend warning unit 304 is configured to calculate the trend fluctuation index of the temperature point corresponding to the maximum coal temperature in the goaf, and based on the trend fluctuation index and the corresponding maximum coal temperature and based on the predetermined warning level trigger conditions, dynamically warn of spontaneous combustion of coal in the goaf.

[0091] The dynamic early warning system for spontaneous combustion of coal in goafs based on optical fiber temperature measurement provided in the embodiment of the present application can implement the steps and processes of the dynamic early warning method for spontaneous combustion of coal in goafs based on optical fiber temperature measurement of any of the above-mentioned embodiments, and achieve the same technical effects, which will not be repeated here one by one.

[0092] In the description of the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0093] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement, characterized in that: include: Step S101, preprocessing the original time-series temperature data of different preset temperature measurement points in the goaf acquired in real time by the distributed temperature sensing optical fiber arranged in the goaf, to obtain the time-series temperature standard data of the goaf; wherein the preprocessing includes: missing value filling, outlier removal and data standardization; Step S102, constructing a goaf temperature prediction model based on STGCN, and predicting the coal temperature of each temperature measuring point in the goaf in the future time period according to the time series temperature standard data, and evaluating the prediction results based on preset evaluation indicators; Step S103, generating a temperature cloud map of the goaf according to the predicted values ​​of the coal temperature of each temperature measuring point in the goaf in the future time period, and iteratively updating the temperature cloud map based on a gradient optimization algorithm to determine the maximum value of the coal temperature in the goaf; Step S104, calculate the trend fluctuation index of the temperature point corresponding to the maximum coal temperature in the goaf, and according to the trend fluctuation index and the corresponding maximum coal temperature, based on the predetermined warning level trigger condition, perform dynamic warning on spontaneous combustion of coal in the goaf.

2. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 1 is characterized in that: In step S101, According to the formula: Laying the distributed temperature-sensing optical fiber in the goaf; Among them, a is the number of distributed temperature-sensitive optical fibers arranged in the goaf, D is the integer width of the goaf; m is the number of the temperature measuring points; and L is the distance between two adjacent temperature measuring points on the distributed temperature-sensitive optical fiber.

3. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 1 is characterized in that: In step S102, Convert the time series temperature standard data at different positions based on the adjacency matrix to obtain graph structure data; Constructing a graph convolution layer based on a graph convolutional neural network, extracting the spatial features of each of the data nodes in the graph structure data through a graph convolution operation, and updating the extracted spatial features of the data nodes; Constructing a time series convolution layer based on a gated convolutional neural network, sliding a convolution kernel on the time series of the time series temperature standard data, performing a dot product operation on a subsequence of the time series of the time series temperature standard data, extracting the time feature of each of the data nodes, and capturing the evolution pattern of each of the data nodes based on the time series convolution operation; A global pooling operation is performed on the spatial features and temporal features of all the extracted data nodes to obtain the global spatiotemporal features of the graph structure data, and the predicted coal temperature of each temperature measuring point in the goaf in the future time period is determined based on the evolution pattern of the data nodes.

4. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 3 is characterized in that: The updating of the extracted spatial features of the data nodes includes: According to the formula: Updating the extracted spatial features of the data nodes; in, is the spatial feature obtained for the data node i in the l-th graph convolution operation of the graph convolution layer; is an adjacency matrix, representing the connection relationship between the data node i and the data node j in the l-th layer graph convolution operation of the graph convolution layer; is the spatial convolution weight matrix in the l-th graph convolution operation of the graph convolution layer; is the updated spatial feature of the data node i in the l-th graph convolution operation of the graph convolution layer; σ is the activation function.

5. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 3 is characterized in that: The temporal convolution operation is based on capturing the evolution pattern of each data node, including, according to the formula: capturing an evolution pattern of the data nodes; in, is the time feature obtained for the data node i in the l+1th layer of the temporal convolution operation of the temporal convolution layer; is the input feature of the data node i in the lth layer of the temporal convolution operation of the temporal convolution layer; σ is the activation function; k is the temporal convolution kernel in the lth layer of the temporal convolution operation of the temporal convolution layer The size of p is the step size of the l-th layer of temporal convolution operation of the temporal convolution layer; d is the dimension of the input feature of the data node i in the l-th layer of temporal convolution operation of the temporal convolution layer; D is the number of data channels of the lth layer of temporal convolution operation of the temporal convolution layer; K is the maximum value of the convolution kernel of the lth layer of temporal convolution operation of the temporal convolution layer; P is the maximum value of the step size of the lth layer of temporal convolution operation of the temporal convolution layer.

6. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 3 is characterized in that: According to the formula: The spatial features of all the extracted data nodes Time characteristics Perform global pooling operations; Among them, z (l+1) is the global spatiotemporal feature obtained after the global pooling operation; is the feature representation of the data node i, N is the number of the data nodes, and N is a positive integer.

7. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 1 is characterized in that: In step S103, Based on the preset coordinate system of the goaf, define the spatial coordinates of each of the temperature measurement points; Based on the inverse distance weighted method, the predicted coal temperature values ​​of the future time periods at the temperature measuring points in the goaf are interpolated to construct a continuous temperature field of the goaf to generate a temperature cloud map of the goaf; Based on a preset objective function, the coal temperature distribution in the goaf is updated according to the temperature gradient of each temperature measuring point in the temperature cloud map to determine the maximum coal temperature in the goaf.

8. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 7 is characterized in that: According to the formula: Interpolate the predicted coal temperature values ​​of each temperature measuring point in the goaf in the future time period to obtain the coal temperature value z0 of the target position in the goaf; Among them, z i is the value of the bth temperature measuring point around the target position; B is the number of the temperature measuring points around the target position, and b and B are both positive integers; d b p is the distance between the target position and the bth temperature measuring point; p is a constant.

9. The method for dynamic early warning of spontaneous combustion of coal in goaf area based on optical fiber temperature measurement according to claim 1 is characterized in that: Step S104 includes: According to the formula: Determine the trend fluctuation index of the temperature point corresponding to the maximum value of the coal temperature in the goaf; Among them, A is the change rate of the temperature point corresponding to the maximum value of coal temperature in the goaf, A t A is the coal temperature value at the temperature point t corresponding to the maximum coal temperature in the goaf; t-1 is the coal temperature value at the temperature point t-1 corresponding to the maximum coal temperature in the goaf; A t With A t-1 the time interval between B is the deviation rate of the temperature point corresponding to the maximum value of coal temperature in the goaf; B t is the value at the temperature point t corresponding to the maximum value of the coal temperature in the goaf; is the value at the temperature point t-1 corresponding to the maximum value of the coal temperature in the goaf; R OSC The time interval of the temperature point corresponding to the maximum coal temperature in the goaf The vibration amplitude of the internal temperature change; C Tmax The temperature point corresponding to the maximum coal temperature in the goaf in the time interval Maximum coal temperature in the Tmin The temperature point corresponding to the maximum coal temperature in the goaf in the time interval Minimum coal temperature within R OFC is the number of temperature changes at the temperature point corresponding to the maximum coal temperature in the goaf; f(C t′ ,C t″ ) indicates the temperature point corresponding to the maximum value of coal temperature in the goaf in the time interval The number of times the internal temperature value is different; C t′ ,C t″ They are the temperature points corresponding to the maximum coal temperature in the goaf at the time interval Temperature value C at time t′ t′ and the temperature value C at time t″ t″ .

10. A dynamic early warning system for spontaneous combustion of coal in goaf area based on optical fiber temperature measurement, characterized in that: include: The data preprocessing unit is configured to preprocess the original time-series temperature data of different preset temperature measurement points in the goaf, which is acquired in real time by the distributed temperature-sensing optical fiber arranged in the goaf, to obtain the time-series temperature standard data of the goaf; wherein the preprocessing includes: missing value filling, outlier elimination and data standardization; A coal temperature prediction unit is configured to construct a goaf temperature prediction model based on STGCN, and predict the coal temperature of each temperature measuring point in the goaf in a future time period according to the time series temperature standard data, and evaluate the prediction result based on a preset evaluation index; The highest point temperature unit is configured to generate a temperature cloud map of the goaf according to the predicted coal temperature values ​​of each temperature measuring point in the goaf in the future time period, and iteratively update the temperature cloud map based on a gradient optimization algorithm to determine the highest value of the coal temperature in the goaf; The trend warning unit is configured to calculate the trend fluctuation index of the temperature point corresponding to the maximum coal temperature in the goaf, and based on the trend fluctuation index and the corresponding maximum coal temperature and based on the predetermined warning level trigger conditions, dynamically warn of spontaneous combustion of coal in the goaf.

Images