Method and device for dividing support area of fully mechanized coal mining face based on multiple factors

Abstract

The application provides a support area division method and device for a fully mechanized coal mining face based on multiple factor parameters. The method comprises the following steps: obtaining support parameter historical data of multiple hydraulic supports in a preset time length, and performing corresponding processing on time stamps and support numbers to obtain support parameter vectors of the multiple hydraulic supports in the same time period; taking the support parameter vectors as input parameters of a clustering analysis algorithm to perform three-dimensional clustering analysis and obtain clustering results; taking a support area of the hydraulic support corresponding to each clustering category as a kind of support area of the hydraulic support of the coal mining face to obtain an initial support area division result; reconfirming the support area of the hydraulic support whose support area has not been determined, and updating the initial support area division result to obtain a final support area division result. The application improves the poor support effect of the hydraulic support caused by the lack of area division of the fully mechanized coal mining face, and improves the implementability of the differentiated and accurate support of the hydraulic support of the fully mechanized coal mining face.

Description

Technical Field

[0001] This application relates to the field of automated monitoring and data mining analysis technology for coal mine working faces, and in particular to a method and device for dividing the support area of ​​a fully mechanized mining face based on multi-factor parameters. Background Technology

[0002] Rock stabilization support in fully mechanized mining faces is a primary condition for safe production in underground coal mines, and hydraulic supports are the main support system for accomplishing this task.

[0003] During normal mining operations, conventional working faces experience roof subsidence, collapse, and fracture, exhibiting a single-peak, periodic pattern of mine pressure manifestation. However, in ultra-long working faces exceeding 350m, the dynamic characteristics of surrounding rock zonal fracture, pressure migration, and impact become more pronounced, resulting in a triple-peak mine pressure manifestation. Conventional working faces, with their strong supports like hydraulic supports, cannot meet the requirements of refined and differentiated support in ultra-long working faces. Generally, supports at the peak pressure point in the middle of a fully mechanized mining face are in a resistance-increasing phase, with a high proportion of safety valve opening, significant roof subsidence, and a high probability of dynamic load impact. Supports at the ends of the fully mechanized mining face are generally in the initial support phase, bearing eccentric loads, with less roof subsidence. The posture of the hydraulic supports affects the effect of overlying loads on the supports. Different postures result in different forces exerted on different parts of the supports, and also different reaction forces exerted by the supports on the overlying strata, thus affecting the support effectiveness of the hydraulic supports. Therefore, support posture data and load data are equally important. Therefore, having all supports with the same parameters in a fully mechanized mining face will result in uneven stress on each support along the length of the face, making it difficult to achieve the best support effect for the working face.

[0004] Patent application CN202111041028.6 discloses a method for dividing the support area and providing precise support for fully mechanized coal mining faces. It uses cluster analysis based on the obtained support column pressure and support number to divide the hydraulic support area of ​​the working face. While this method improves upon the current lack of area division in fully mechanized mining faces, which leads to poor support performance, it does not consider the influence of the hydraulic support's posture, i.e., the inclination angle of the top beam and the base, on the support. Summary of the Invention

[0005] This application aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the first objective of this application is to propose a method for dividing the support area of ​​a fully mechanized mining face based on multiple factors, which can improve the problem of poor support effect caused by the lack of area division or unreasonable area division of the current fully mechanized mining face, thereby improving the feasibility of differentiated and precise support for fully mechanized mining faces.

[0007] The second objective of this application is to propose a support area division device for fully mechanized mining faces based on multi-factor parameters.

[0008] The third objective of this application is to propose a computer device.

[0009] The fourth objective of this application is to provide a non-transitory computer-readable storage medium.

[0010] To achieve the above objectives, the first aspect of this application proposes a method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters, including:

[0011] The historical support parameter data of multiple hydraulic supports within a preset time period is obtained, and the historical support parameter data is processed to match the timestamp and support number to obtain the support parameter vector of multiple hydraulic supports within the same time period.

[0012] The support parameter vector includes historical data of column pressure, historical data of tilt angle after dimensionality reduction, and the corresponding support number;

[0013] The support parameter vector is used as the input parameter for a clustering analysis algorithm to perform three-dimensional clustering analysis, and the clustering results are obtained. The clustering results include cluster categories and the cluster centers of each cluster category.

[0014] The initial support area division result is obtained by taking the support area of ​​the hydraulic support corresponding to each cluster category as a support area of ​​the hydraulic support of the working face.

[0015] Among them, there are hydraulic supports whose support areas have not yet been determined in the initial support area division results. The hydraulic supports whose support areas have not yet been determined are hydraulic supports whose support areas are different in the early and late stages of clustering.

[0016] Based on the initial support area division results, the support areas of hydraulic supports whose support areas have not yet been determined are reconfirmed, and the initial support area division results are updated based on the confirmation results to obtain the final support area division results.

[0017] Optionally, in one embodiment of this application, the historical support parameter data includes historical column pressure data, historical top beam inclination angle data, and historical base inclination angle data. Before performing timestamp and support number mapping on the historical support parameter data to obtain the support parameter vectors for multiple hydraulic supports within the same time period, the following steps are included:

[0018] Principal component analysis was used to reduce the historical data of the top beam inclination angle and the base inclination angle to one dimension, thus obtaining the dimension-reduced historical data of the inclination angle.

[0019] Optionally, in one embodiment of this application, principal component analysis is used to reduce the historical data of the top beam inclination angle and the historical data of the base inclination angle to one-dimensional data, resulting in the dimensionality-reduced historical inclination angle data, including:

[0020] Standardize the historical data of the top beam inclination angle and the base inclination angle.

[0021] Calculate the covariance matrix of the standardized historical data of the top beam inclination angle and the base inclination angle;

[0022] Eigenvalue decomposition of the covariance matrix yields eigenvalues ​​and corresponding eigenvectors;

[0023] The eigenvectors are sorted according to the size of their eigenvalues, and the eigenvectors corresponding to the largest preset number of eigenvalues ​​are selected to form the projection matrix.

[0024] The historical data of the top beam inclination angle and the historical data of the base inclination angle are reduced in dimension using a projection matrix to obtain the dimension-reduced historical data of the inclination angle.

[0025] Optionally, in one embodiment of this application, after updating the initial support area division result based on the confirmation result to obtain the final support area division result, the method further includes:

[0026] Real-time data collection of column pressure, top beam tilt angle, and base tilt angle of multiple hydraulic supports; and dimensionality reduction of the top beam tilt angle and base tilt angle data to obtain dimensionality-reduced tilt angle data.

[0027] Based on the column pressure data, the reduced tilt angle data, and the corresponding support number, the real-time support parameter vectors of multiple hydraulic supports are obtained, and the spatial distance from the real-time support parameter vectors to the cluster centers of each cluster category is calculated.

[0028] Based on the spatial distance from the real-time support parameter vector of each hydraulic support to the cluster center of each cluster category, the support area to which each hydraulic support belongs is determined in real time, and the support area division result of the hydraulic support is dynamically updated.

[0029] Optionally, in one embodiment of this application, the support area to which each hydraulic support belongs is determined in real time based on the spatial distance from the real-time support parameter vector of each hydraulic support to the cluster center of each cluster category, including:

[0030] By comparing the spatial distances from the real-time support parameter vectors of each hydraulic support to the cluster centers of each cluster category, the cluster category corresponding to the smallest spatial distance obtained from the comparison is determined as the support area to which the hydraulic support belongs.

[0031] Optionally, in one embodiment of this application, the support area of ​​the hydraulic support whose support area has not yet been determined is reconfirmed based on the initial support area division result, including:

[0032] The support area to which the hydraulic support belongs is determined based on the initial support area division results and the average value of all data points of the hydraulic support whose support area has not yet been determined.

[0033] Optionally, in one embodiment of this application, determining the support area to which the hydraulic support belongs based on the initial support area division results and the average value of all data points of the hydraulic support whose support area has not yet been determined includes:

[0034] Calculate the historical data of column pressure, the historical data of tilt angle after dimensionality reduction, and the average value of the corresponding support number for the hydraulic supports in the undetermined support area;

[0035] The support area to which the hydraulic support belongs is determined by the support area in which the calculated average point is located in the initial support area division result.

[0036] To achieve the above objectives, a second aspect of this application proposes a device for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters, comprising:

[0037] The acquisition module is used to acquire historical support parameter data of multiple hydraulic supports within a preset time period, and to perform timestamp and support number matching processing on the historical support parameter data to obtain the support parameter vector of multiple hydraulic supports within the same time period. The support parameter vector includes historical column pressure data, dimensionality-reduced tilt angle historical data and corresponding support number.

[0038] The clustering module is used to perform three-dimensional clustering analysis by taking the support parameter vector as the input parameter of the clustering analysis algorithm, and to obtain the clustering results, which include cluster categories and the cluster centers of each cluster category.

[0039] The initial support area division module is used to obtain the initial support area division result by taking the support area of ​​the hydraulic support corresponding to each cluster category as a support area of ​​the hydraulic support of the working face. Among the hydraulic supports corresponding to the initial support area division result, there are hydraulic supports whose support areas have not yet been determined. The hydraulic supports whose support areas have not yet been determined are hydraulic supports whose support areas are different in the early stage of clustering and the later stage of clustering.

[0040] The final support area division module is used to reconfirm the support area of ​​hydraulic supports whose support areas have not yet been determined based on the initial support area division results, and update the initial support area division results based on the confirmation results to obtain the final support area division results.

[0041] To achieve the above objectives, a third aspect of this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters as described in the above embodiment.

[0042] To achieve the above objectives, the fourth aspect of this application proposes a non-transitory computer-readable storage medium that, when the instructions in the storage medium are executed by a processor, can perform a method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters.

[0043] The method, apparatus, computer equipment, and non-temporary computer-readable storage medium for dividing the support area of ​​fully mechanized mining faces based on multi-factor parameters in this application can improve the problem of poor support effect caused by the lack of area division or unreasonable area division of fully mechanized mining faces, thereby improving the feasibility of differentiated and precise support for fully mechanized mining faces.

[0044] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0045] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0046] Figure 1 This is a flowchart of a method for dividing the support area of ​​a fully mechanized mining face based on multiple factors, provided in Embodiment 1 of this application;

[0047] Figure 2 This is another flowchart of the method for dividing the support area of ​​a fully mechanized mining face based on multiple factors according to an embodiment of this application;

[0048] Figure 3 This is another flowchart of the method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters, as described in this application.

[0049] Figure 4 This is a schematic diagram of a fully mechanized mining face support area division device based on multiple factor parameters, provided in Embodiment 2 of this application. Detailed Implementation

[0050] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0051] The following describes, with reference to the accompanying drawings, a method and apparatus for dividing the support area of ​​a fully mechanized mining face based on multiple parameters.

[0052] Figure 1 This is a flowchart illustrating a method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters, as provided in Embodiment 1 of this application.

[0053] like Figure 1 As shown, the method for dividing the support area of ​​a fully mechanized mining face based on multiple factors includes the following steps:

[0054] Step 101: Obtain historical support parameter data of multiple hydraulic supports within a preset time period, and perform timestamp and support number correspondence processing on the historical support parameter data to obtain support parameter vectors of multiple hydraulic supports within the same time period. The support parameter vector includes historical column pressure data, dimensionality-reduced tilt angle historical data and corresponding support number.

[0055] Step 102: Use the support parameter vector as the input parameter of the clustering analysis algorithm to perform three-dimensional clustering analysis and obtain the clustering results, which include cluster categories and the cluster centers of each cluster category.

[0056] Step 103: By taking the support area of ​​the hydraulic support corresponding to each cluster category as a support area of ​​the hydraulic support of the working face, the initial support area division result is obtained. Among the hydraulic supports corresponding to the initial support area division result, there are hydraulic supports whose support areas have not yet been determined. The hydraulic supports whose support areas have not yet been determined are hydraulic supports whose support areas are different in the early stage of clustering and the later stage of clustering.

[0057] Step 104: Based on the initial support area division results, reconfirm the support area of ​​the hydraulic supports whose support areas have not yet been determined, and update the initial support area division results based on the confirmation results to obtain the final support area division results.

[0058] The method for dividing the support area of ​​a fully mechanized mining face based on multi-factor parameters in this application embodiment obtains historical support parameter data of multiple hydraulic supports within a preset time period, and performs timestamp and support number mapping on the historical support parameter data to obtain support parameter vectors for multiple hydraulic supports within the same time period. The support parameter vector includes historical column pressure data, dimensionality-reduced tilt angle historical data, and the corresponding support number. The support parameter vector is then used as input parameters for a clustering analysis algorithm to perform three-dimensional clustering analysis, obtaining clustering results. These clustering results include cluster categories and the clusters within each cluster category. The method involves dividing the hydraulic supports of each cluster category into support areas for the working face hydraulic supports, resulting in an initial support area division. This initial division includes hydraulic supports with undetermined support areas, specifically those belonging to different support areas in the early and later stages of clustering. Based on the initial division, the support areas of these undetermined hydraulic supports are re-confirmed, and the initial division is updated accordingly to obtain the final support area division. This approach addresses the problem of inadequate support effects in fully mechanized mining faces due to lack of or unreasonable area division, thereby improving the feasibility of differentiated and precise support for fully mechanized mining faces.

[0059] This application provides a method for dividing the support area of ​​a fully mechanized coal mining face. During the mining of fully mechanized coal mining faces, especially ultra-long faces, the method collects and utilizes historical data on the actual load intensity and posture of the supports, as well as support position data (i.e., historical data on hydraulic support column pressure, roof beam inclination angle, base inclination angle, and corresponding support number). Based on data clustering analysis, the final support area of ​​the fully mechanized coal mining face is determined. Dividing the support area of ​​the fully mechanized coal mining face into different types of support areas can significantly improve the current problem of poor support effect in some areas when using the same support parameters for hydraulic supports in fully mechanized coal mining faces. Furthermore, based on this divided support area, it is easier to implement more differentiated and refined support for the working face, improving the feasibility of differentiated and precise support for fully mechanized coal mining face supports, thereby improving the overall support effect of the fully mechanized coal mining face supports.

[0060] In this embodiment of the application, historical data of support parameters of multiple hydraulic supports within a preset time period are obtained. The historical data of support parameters of multiple hydraulic supports within the preset time period can be the data of the supports collected between two pressure cycles, or it can be the support data within any selected longer period of time (including at least three pressure cycles). The historical data of support parameters includes historical data of column pressure, historical data of top beam inclination angle, and historical data of base inclination angle.

[0061] In this embodiment, the historical data of the top beam inclination angle and the historical data of the base inclination angle are first reduced to one dimension using the principal component analysis method to obtain the historical data of the inclination angle after dimensionality reduction. Then, the historical data of the support parameters are processed to correspond to the timestamp and the support number to obtain the support parameter vector of multiple hydraulic supports in the same time period. The support parameter vector includes the historical data of the column pressure, the historical data of the inclination angle after dimensionality reduction and the corresponding support number.

[0062] In this embodiment of the application, the support parameter vector is used as the input parameter of the clustering analysis algorithm to perform three-dimensional clustering analysis and obtain the clustering result. The clustering analysis algorithm can be the K-means algorithm, etc.

[0063] In this embodiment, by rationally dividing the support area of ​​the fully mechanized mining face into different types of support areas, and implementing more targeted and refined support based on the divided support areas, compared with the existing support method based on uniform support parameters, it can adapt to the differentiated support needs of different areas of the entire fully mechanized mining face, improve the feasibility of differentiated and precise support of the fully mechanized mining face support, and thus improve the overall support effect of the fully mechanized mining face support.

[0064] Furthermore, in this embodiment of the application, the historical support parameter data includes historical data of column pressure, historical data of top beam inclination angle, and historical data of base inclination angle. Before processing the historical support parameter data for timestamp and support number correspondence to obtain the support parameter vectors of multiple hydraulic supports within the same time period, the following steps are included:

[0065] Principal component analysis was used to reduce the historical data of the top beam inclination angle and the base inclination angle to one dimension, thus obtaining the dimension-reduced historical data of the inclination angle.

[0066] In this embodiment, the inclination angles of the top beam and the base are both perpendicular to the coal face of the working face.

[0067] Furthermore, in this embodiment of the application, principal component analysis is used to reduce the historical data of the top beam inclination angle and the historical data of the base inclination angle to one-dimensional data, resulting in the dimensionality-reduced historical inclination angle data, including:

[0068] Standardize the historical data of the top beam inclination angle and the base inclination angle.

[0069] Calculate the covariance matrix of the standardized historical data of the top beam inclination angle and the base inclination angle;

[0070] Eigenvalue decomposition of the covariance matrix yields eigenvalues ​​and corresponding eigenvectors;

[0071] The eigenvectors are sorted according to the size of their eigenvalues, and the eigenvectors corresponding to the largest preset number of eigenvalues ​​are selected to form the projection matrix.

[0072] The historical data of the top beam inclination angle and the historical data of the base inclination angle are reduced in dimension using a projection matrix to obtain the dimension-reduced historical data of the inclination angle.

[0073] In this embodiment of the application, the preset quantity can be 1, that is, the feature vector corresponding to the largest feature value is selected to form the projection matrix.

[0074] In this embodiment of the application, the steps for dimensionality reduction using principal component analysis are as follows:

[0075] Standardized data: The original top beam inclination angle data and base inclination angle data are standardized to ensure that the data in each dimension has the same scale.

[0076] Calculate the covariance matrix: Calculate the covariance matrix of the standardized data to measure the correlation between two dimensions.

[0077] Calculate eigenvalues ​​and eigenvectors: Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors.

[0078] Eigenvalue sorting: Sort the eigenvectors according to the size of the eigenvalues, and select the eigenvectors corresponding to the largest k eigenvalues ​​(k is the number of dimensions to be retained, and k = 1 in this application).

[0079] Constructing the projection matrix: The selected feature vectors are combined to form a projection matrix, which is used to project the original data onto a new low-dimensional space.

[0080] Data dimensionality reduction: The original data is reduced in dimensionality using a projection matrix to obtain the dimensionality-reduced data.

[0081] Understandably, the hydraulic support frame type of the fully mechanized mining face can be specifically divided into two types based on the number of columns: two-column and four-column. Therefore, hydraulic supports include two-column and / or four-column hydraulic supports.

[0082] When the hydraulic support is a two-column hydraulic support, the column pressure data of the hydraulic support is the pressure data of the left column or the right column.

[0083] When the hydraulic support is a four-column hydraulic support, the column pressure data of the hydraulic support is the data of the left front column and the right rear column or the right front column and the left rear column.

[0084] It is understandable that when the hydraulic support is a four-column hydraulic support, before processing the historical data of the support parameters by timestamp and support number to obtain the support parameter vector of multiple hydraulic supports in the same time period, the pressure data of the left front column, right rear column or right front column and left rear column of the four-column hydraulic support is reduced to one-dimensional pressure data by using the principal component analysis method.

[0085] The steps involved in dimensionality reduction using principal component analysis include:

[0086] Standardize the pressure data of the left front column and right rear column or the right front column and left rear column of the four-column hydraulic support.

[0087] Calculate the covariance matrix of the pressure data of the left front column and right rear column or the right front column and left rear column of the standardized four-column hydraulic support.

[0088] Eigenvalue decomposition of the covariance matrix yields eigenvalues ​​and corresponding eigenvectors;

[0089] The eigenvectors are sorted according to the size of their eigenvalues, and the eigenvectors corresponding to the largest preset number of eigenvalues ​​are selected to form the projection matrix.

[0090] The pressure data of the left front column and right rear column or the right front column and left rear column of the four-column hydraulic support are reduced in dimension by using a projection matrix to obtain the reduced column pressure data.

[0091] The preset quantity can be 1, that is, the eigenvector corresponding to the largest eigenvalue is selected to form the projection matrix.

[0092] The reduced pressure history data and reduced tilt angle history data are processed by timestamp and support number mapping to obtain support parameter vectors for multiple hydraulic supports within the same time period. The support parameter vectors include the reduced pressure history data, the reduced tilt angle history data and the corresponding support number.

[0093] Furthermore, in this embodiment of the application, after updating the initial support area division result based on the confirmation result to obtain the final support area division result, the method further includes:

[0094] Real-time data collection of column pressure, top beam tilt angle, and base tilt angle of multiple hydraulic supports; and dimensionality reduction of the top beam tilt angle and base tilt angle data to obtain dimensionality-reduced tilt angle data.

[0095] Based on the column pressure data, the reduced tilt angle data, and the corresponding support number, the real-time support parameter vectors of multiple hydraulic supports are obtained, and the spatial distance from the real-time support parameter vectors to the cluster centers of each cluster category is calculated.

[0096] Based on the spatial distance from the real-time support parameter vector of each hydraulic support to the cluster center of each cluster category, the support area to which each hydraulic support belongs is determined in real time, and the support area division result of the hydraulic support is dynamically updated.

[0097] Understandably, due to the dynamic changes in the surrounding rock condition of the working face, it is necessary to redetermine the area of ​​each support for real-time acquisition of new data.

[0098] In this embodiment, the column pressure data, top beam inclination angle data, and base inclination angle data of the hydraulic support of the fully mechanized mining face are monitored in real time. Based on the cluster centers of each cluster category, the spatial distance from the new data points of each support collected in real time to the cluster centers of each cluster category is calculated. Based on the calculated spatial distance from the new data points of each support to the cluster centers of each cluster category, the support area to which the support belongs is determined in real time, and the support area division results of the support to which the support belongs are dynamically updated. The calculation of the spatial distance from the new data points of each support collected in real time to the center of each category includes: calculating the Euclidean distance from the new data coordinates of each support to the coordinates of each cluster center.

[0099] In this embodiment, the steps of calculating spatial distance and dynamically updating are repeated to dynamically update the support area of ​​the support under changing load intensity in real time until the next cycle of pressure is applied.

[0100] In this embodiment, by dynamically updating the support area of ​​the support under changing load intensity during two pressure cycles, and implementing precise support based on the dynamically updated support area, the overall support effect of the fully mechanized mining face before the next pressure cycle can be effectively improved.

[0101] Furthermore, in this embodiment of the application, the support area to which each hydraulic support belongs is determined in real time based on the spatial distance from the real-time support parameter vector of each hydraulic support to the cluster center of each cluster category, including:

[0102] By comparing the spatial distances from the real-time support parameter vectors of each hydraulic support to the cluster centers of each cluster category, the cluster category corresponding to the smallest spatial distance obtained from the comparison is determined as the support area to which the hydraulic support belongs.

[0103] In this embodiment of the application, the support area to which the stent belongs is determined in real time based on the calculated spatial distance from the new data point of each stent to the center of each category. This includes: comparing the calculated Euclidean distances with each other, and determining the cluster category corresponding to the smallest Euclidean distance as the support area to which the new data point of the stent belongs, i.e., the new support area of ​​the stent.

[0104] In this embodiment, by calculating the Euclidean distance between the data coordinates of the hydraulic support and the coordinates of each cluster center, the cluster category to which the corresponding support belongs is adjusted according to the distance from the center of each cluster category, thereby dynamically updating the support area of ​​the support to improve the accuracy of subsequent precise support. The data coordinates of the hydraulic support are the coordinate points corresponding to the three-dimensional data (column pressure, tilt angle, support number) used for clustering.

[0105] Furthermore, in this embodiment of the application, the support area of ​​the hydraulic support whose support area has not yet been determined is reconfirmed based on the initial support area division results, including:

[0106] The support area to which the hydraulic support belongs is determined based on the initial support area division results and the average value of all data points of the hydraulic support whose support area has not yet been determined.

[0107] In this embodiment, after determining the initial support area type based on the clustering results, some hydraulic supports may initially be in one type of support area but later change to another. These hydraulic supports are those whose support areas have not yet been determined. For such supports whose area division is not yet determined, the final support area can be determined based on the average value of all data points of the hydraulic supports whose support areas have not yet been determined. That is, the average value of all data points of the hydraulic supports whose support areas have not yet been determined is calculated, and the support belongs to the area where the average value point is located, thereby determining the final support area of ​​the entire working face.

[0108] Therefore, for stents whose support areas have not yet been determined, the final support area is confirmed, and the initial support area type is updated to obtain the following final support area types:

[0109] The final support area to which the hydraulic support belongs is determined by averaging all data points of the hydraulic support for which the support area has not yet been determined.

[0110] Further, in this embodiment of the application, determining the support area to which the hydraulic support belongs based on the initial support area division results and the average value of all data points of the hydraulic support whose support area has not yet been determined includes:

[0111] Calculate the historical data of column pressure, the historical data of tilt angle after dimensionality reduction, and the average value of the corresponding support number for the hydraulic supports in the undetermined support area;

[0112] The support area to which the hydraulic support belongs is determined by the support area in which the calculated average point is located in the initial support area division result.

[0113] In this embodiment of the application, determining the final support area of ​​the hydraulic support based on the average value of all data points of the hydraulic support whose support area has not yet been determined includes: calculating the average value of all data points of the hydraulic support whose support area has not yet been determined; and determining the support area where the calculated average value point is located as the final support area of ​​the hydraulic support.

[0114] In this embodiment of the application, by confirming the cluster category to which the calculated average point belongs, the support area in which the average point is located in the initial support area division result is obtained.

[0115] This application discloses a method for dividing the support area of ​​a fully mechanized mining face based on multi-factor parameters, relating to the field of coal mine face equipment monitoring and automation control technology. The method for dividing the hydraulic support area includes: collecting hydraulic support column pressure data, top beam inclination angle data, and base inclination angle data; using principal component analysis to reduce the top beam inclination angle data and base inclination angle data to one-dimensional data; using the column pressure data, the reduced inclination angle data, and the support number as input parameters for a clustering analysis algorithm to perform three-dimensional clustering analysis and obtain clustering results; the clustering results include cluster categories and cluster centers for each category; each cluster category serves as a support area for the working face support, resulting in an initial number of support area types equal to the number of cluster categories; based on the obtained initial support area types, the remaining supports are identified for final area confirmation, updating the initial support area types to obtain the final support area types. This application can improve the problem of poor support effect caused by the lack of area division or unreasonable area division in current fully mechanized mining faces, thereby improving the feasibility of differentiated and precise support for fully mechanized mining faces.

[0116] The following section details the method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters.

[0117] The overall technical concept flow of the coal mine fully mechanized mining face support area division method in this application is as follows: Figure 2As shown, step S10: Real-time monitoring of the column pressure data, top beam inclination angle data, and base inclination angle data of the hydraulic supports in the fully mechanized mining face; step S20: Collection of multiple sets of historical data on the column pressure, top beam inclination angle, and base inclination angle of the hydraulic supports, and processing of timestamps and support numbers to obtain multiple sets of data within the same time period for multiple supports; step S30: Reduction of the top beam inclination angle and base inclination angle to one-dimensional data using principal component analysis, selecting the column pressure data, the reduced inclination angle data, and the support number from step S20 as inputs to the clustering analysis algorithm. The parameters are used to perform three-dimensional cluster analysis to obtain clustering results; the clustering results include cluster categories and cluster centers of each category; Step S40: Each cluster category of the clustering results obtained in step S30 is used as a support area of ​​the working face support to obtain the same number of initial support area types as the number of cluster categories; there are supports with undetermined support areas in the initial support area types; Step S50: Based on the initial support area types obtained in step S40, the supports with undetermined support areas are finally confirmed, the initial support area types are updated, and the final support area types are obtained.

[0118] like Figure 3 As shown, after step S50, the method further includes: step S60: based on the cluster centers of each category obtained in step S30, calculate the spatial distance from the new data points of each stent collected in real time to each category center; based on the calculated spatial distance from the new data points of each stent to each category center, determine the support area to which the stent belongs in real time, and dynamically update the support area division result to which the stent belongs.

[0119] Continue reading Figure 3 As shown, the method also includes: step S70, repeating step S60, dynamically updating the support area of ​​the support under changing load intensity in real time until the next cycle of pressure.

[0120] In this embodiment, by dynamically updating the support area of ​​the support under changing load intensity in real time during two pressure cycles, and implementing precise support based on the dynamically updated support area, the overall support effect of the fully mechanized mining face before the next pressure cycle can be effectively improved.

[0121] Understandably, the hydraulic support frame type of the fully mechanized mining face can be specifically divided into two types based on the number of columns: two-column and four-column. Therefore, hydraulic supports include two-column and / or four-column hydraulic supports.

[0122] When the hydraulic support is a two-column hydraulic support, the column pressure data of the hydraulic support that needs to be monitored in real time in steps S10 and S60 is the pressure data of the left column or the right column.

[0123] When the hydraulic support is a four-column hydraulic support, the column pressure data of the hydraulic support that needs to be monitored in real time in steps S10 and S60 are the data of the left front column and the right rear column or the right front column and the left rear column.

[0124] Similarly, principal component analysis is used to reduce the dimensionality of the left front column, right rear column, or right front column and left rear column of the four-column hydraulic support to one-dimensional pressure data. In step S20, multiple sets of data from multiple supports within the same time period are a three-dimensional vector, including the reduced column pressure data, the reduced tilt angle data, and the corresponding support number.

[0125] When the hydraulic support is a two-column hydraulic support, in step S30, only the principal component analysis method needs to be applied to the top beam inclination angle and the base inclination angle.

[0126] When the hydraulic support is a four-column hydraulic support, in step S30, principal component analysis is required to be applied to the top beam inclination angle, the base inclination angle, and the data of the left front column, right rear column, or right front column and left rear column of the support.

[0127] When the hydraulic support includes two-column hydraulic support and four-column hydraulic support, the data that needs to be monitored in real time in steps S10 and S60 of the two cases of two-column hydraulic support and four-column hydraulic support shall be monitored accordingly.

[0128] Clustering analysis algorithms can include K-means algorithm, etc.

[0129] Since some hydraulic supports may initially be in one type of support area after the clustering results obtained in step S30 determine the initial support area type, but later change to another type, these hydraulic supports are those whose support areas have not yet been determined. For such supports whose area division has not yet been determined, the final support area can be determined based on the average value of all data points of the hydraulic supports whose support areas have not yet been determined. That is, the average value of all data points of the hydraulic supports whose support areas have not yet been determined is calculated, and the support belongs to the area where the average value point is located, thereby determining the final support area of ​​the entire working face.

[0130] Therefore, in step S50, the final support area is confirmed for the support that has not yet been determined, and the initial support area type is updated. The final support area type is determined by: determining the final support area to which the hydraulic support belongs based on the average value of all data points of the hydraulic support that has not yet been determined.

[0131] The final support area to which the hydraulic support belongs is determined based on the average of all data points of the hydraulic support for which the support area has not yet been determined, including:

[0132] Calculate the average value of all data points for the hydraulic support in the undefined support area;

[0133] The final support area of ​​the hydraulic support is determined by the support area where the average value point is located.

[0134] It is understandable that, due to the dynamic changes in the surrounding rock condition of the working face, it is necessary to redetermine the region for the new data collected in real time for each support. Optionally, in step S60, calculating the spatial distance from the new data points of each support to the center of each category includes: calculating the Euclidean distance from the new data coordinates of each support to the coordinates of each cluster center; and determining the support area to which the support belongs in real time based on the calculated spatial distance from the new data points of each support to the center of each category includes: comparing the calculated Euclidean distances with each other, and determining the cluster category corresponding to the smallest Euclidean distance as the support area to which the new data points of the support belong, i.e., the new support area of ​​the support.

[0135] In this embodiment, by calculating the Euclidean distance between the data coordinates and the coordinates of each cluster center, the cluster category to which the corresponding stent belongs is adjusted according to the distance from the center of each cluster category, thereby dynamically updating the support area of ​​the stent to improve the accuracy of subsequent precise support.

[0136] In steps S10 to S50, the stent data is the stent data collected within a period of time between two pressure cycles; alternatively, stent data within a longer period of time (containing at least three pressure cycles) can be selected for cluster analysis to obtain the cluster category and cluster center.

[0137] Figure 4 This is a schematic diagram of a fully mechanized mining face support area division device based on multiple factor parameters, provided in Embodiment 2 of this application.

[0138] like Figure 4 As shown, the fully mechanized mining face support area division device based on multi-factor parameters includes:

[0139] The acquisition module 10 is used to acquire historical support parameter data of multiple hydraulic supports within a preset time period, and to perform time stamp and support number correspondence processing on the historical support parameter data to obtain the support parameter vector of multiple hydraulic supports within the same time period. The support parameter vector includes historical column pressure data, dimensionality-reduced tilt angle historical data and corresponding support number.

[0140] Clustering module 20 is used to perform three-dimensional clustering analysis by taking the support parameter vector as the input parameter of the clustering analysis algorithm to obtain the clustering results, wherein the clustering results include cluster categories and the cluster centers of each cluster category;

[0141] The initial support area division module 30 is used to obtain the initial support area division result by taking the support area of ​​the hydraulic support corresponding to each cluster category as a support area of ​​the hydraulic support of the working face. Among the hydraulic supports corresponding to the initial support area division result, there are hydraulic supports whose support areas have not yet been determined. The hydraulic supports whose support areas have not yet been determined are hydraulic supports whose support areas are different in the early stage of clustering and the later stage of clustering.

[0142] The final support area division module 40 is used to reconfirm the support area of ​​the hydraulic support whose support area has not yet been determined based on the initial support area division result, and update the initial support area division result based on the confirmation result to obtain the final support area division result.

[0143] The fully mechanized mining face support area division device based on multi-factor parameters in this application includes an acquisition module for acquiring historical support parameter data of multiple hydraulic supports within a preset time period, and performing timestamp and support number mapping on the historical support parameter data to obtain support parameter vectors for multiple hydraulic supports within the same time period. The support parameter vectors include historical column pressure data, dimensionality-reduced tilt angle historical data, and the corresponding support number. A clustering module is used to perform three-dimensional clustering analysis using the support parameter vectors as input parameters for a clustering analysis algorithm to obtain clustering results. The clustering results include cluster categories and cluster centers for each cluster category. Initial support... The region segmentation module is used to obtain initial support region segmentation results by treating the support area of ​​the hydraulic supports corresponding to each cluster category as a support area for the hydraulic supports in the working face. Among the hydraulic supports corresponding to the initial support region segmentation results, there are hydraulic supports whose support areas have not yet been determined. These hydraulic supports belong to different support areas in the early and later stages of clustering. The final support region segmentation module is used to reconfirm the support areas of the hydraulic supports whose support areas have not yet been determined based on the initial support region segmentation results, and update the initial support region segmentation results based on the confirmation results to obtain the final support region segmentation results. This can improve the problem of poor support effect caused by the lack of region segmentation or unreasonable region segmentation in the current fully mechanized mining face, thereby improving the feasibility of differentiated and precise support for fully mechanized mining faces.

[0144] To implement the above embodiments, this application also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for dividing the support area of ​​a fully mechanized mining face based on multiple factor parameters as described in the above embodiments.

[0145] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method for dividing the support area of ​​a fully mechanized mining face based on multi-factor parameters as described in the above embodiments.

[0146] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0147] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0148] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0149] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0150] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0151] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0152] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0153] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for dividing the support area of ​​a fully mechanized mining face based on multiple factors, characterized in that, Includes the following steps: The historical support parameter data of multiple hydraulic supports within a preset time period is obtained, and the historical support parameter data is processed to correspond to timestamps and support numbers to obtain the support parameter vector of the multiple hydraulic supports within the same time period. The support parameter vector includes historical column pressure data, dimensionality-reduced tilt angle historical data and corresponding support numbers. The support parameter vector is used as the input parameter for a clustering analysis algorithm to perform three-dimensional clustering analysis, and the clustering results are obtained, wherein the clustering results include cluster categories and cluster centers of each cluster category; By taking the support area of ​​the hydraulic support corresponding to each cluster category as a support area of ​​the hydraulic support of the working face, the initial support area division result is obtained. Among the hydraulic supports corresponding to the initial support area division result, there are hydraulic supports whose support areas have not yet been determined. The hydraulic supports whose support areas have not yet been determined are hydraulic supports whose support areas are different in the early stage of clustering and the later stage of clustering. Based on the initial support area division results, the hydraulic supports whose support areas have not yet been determined are re-confirmed, and the initial support area division results are updated based on the confirmation results to obtain the final support area division results. The historical support parameter data includes historical data on column pressure, top beam inclination angle, and base inclination angle. Before processing the historical support parameter data for timestamp and support number correspondence to obtain the support parameter vector for the same time period of the multiple hydraulic supports, the following steps are included: Principal component analysis was used to reduce the historical data of the top beam inclination angle and the base inclination angle to one-dimensional data, thus obtaining the dimensionality-reduced historical data of the inclination angle. The method of using principal component analysis to reduce the historical data of the top beam inclination angle and the base inclination angle to one-dimensional data yields the dimensionality-reduced historical inclination angle data, including: The historical data of the top beam inclination angle and the historical data of the base inclination angle are standardized. Calculate the covariance matrix of the standardized historical data of the top beam inclination angle and the base inclination angle; The covariance matrix is ​​decomposed into eigenvalues ​​to obtain eigenvalues ​​and corresponding eigenvectors. The feature vectors are sorted according to the size of the feature values, and the feature vectors corresponding to the largest preset number of feature values ​​are selected to form a projection matrix; The historical data of the top beam tilt angle and the historical data of the base tilt angle are reduced in dimension using the projection matrix to obtain the dimension-reduced historical data of the tilt angle. After updating the initial support area division result based on the confirmation result to obtain the final support area division result, the method further includes: Real-time data collection of column pressure, top beam tilt angle, and base tilt angle of multiple hydraulic supports; and dimensionality reduction of the top beam tilt angle and base tilt angle data to obtain dimensionality-reduced tilt angle data. Based on the column pressure data, the reduced tilt angle data, and the corresponding support number, the real-time support parameter vector of the multiple hydraulic supports is obtained, and the spatial distance from the real-time support parameter vector to the cluster center of each cluster category is calculated. Based on the spatial distance from the real-time support parameter vector of each hydraulic support to the cluster center of each cluster category, the support area to which each hydraulic support belongs is determined in real time, and the support area division result of the hydraulic support is dynamically updated.

2. The method as described in claim 1, characterized in that, The method of determining the support area of ​​each hydraulic support in real time based on the spatial distance from the real-time support parameter vector of each hydraulic support to the cluster center of each cluster category includes: By comparing the spatial distances from the real-time support parameter vectors of each hydraulic support to the cluster centers of each cluster category, the cluster category corresponding to the smallest spatial distance obtained from the comparison is determined as the support area to which the hydraulic support belongs.

3. The method as described in claim 1, characterized in that, The step of reconfirming the support area of ​​the hydraulic support whose support area has not yet been determined based on the initial support area division results includes: The support area to which the hydraulic support belongs is determined based on the initial support area division results and the average value of all data points of the hydraulic support whose support area has not yet been determined.

4. The method as described in claim 3, characterized in that, The step of determining the support area to which the hydraulic support belongs based on the initial support area division results and the average value of all data points of the hydraulic support whose support area has not yet been determined includes: Calculate the average value of the historical column pressure data and the historical tilt angle data of the hydraulic support for the undetermined support area; The support area to which the hydraulic support belongs is determined by the support area in which the calculated average point is located in the initial support area division result.

5. A device for dividing the support area of ​​a fully mechanized mining face based on multiple parameters, characterized in that, The apparatus implements the method as described in claim 1, the apparatus comprising: The acquisition module is used to acquire historical support parameter data of multiple hydraulic supports within a preset time period, and to perform timestamp and support number correspondence processing on the historical support parameter data to obtain the support parameter vector of the multiple hydraulic supports within the same time period. The support parameter vector includes historical column pressure data, dimensionality-reduced tilt angle historical data and corresponding support number. The clustering module is used to perform three-dimensional clustering analysis by using the support parameter vector as input parameters of the clustering analysis algorithm to obtain clustering results, wherein the clustering results include cluster categories and cluster centers of each cluster category; The initial support area division module is used to obtain the initial support area division result by taking the support area of ​​the hydraulic support corresponding to each cluster category as a support area of ​​the hydraulic support of the working face. Among the hydraulic supports corresponding to the initial support area division result, there are hydraulic supports whose support areas have not yet been determined. The hydraulic supports whose support areas have not yet been determined are hydraulic supports whose support areas are different in the early stage of clustering and the later stage of clustering. The final support area division module is used to reconfirm the support area of ​​the hydraulic support whose support area has not yet been determined based on the initial support area division result, and update the initial support area division result based on the confirmation result to obtain the final support area division result.

6. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method as described in any one of claims 1-4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images