Coal rock failure precursor prediction method and related equipment

Abstract

The invention provides a coal rock failure precursor prediction method and related equipment, and relates to the technical field of image processing. The method comprises the following steps: acquiring displacement field information in a plurality of coal rock images within a preset duration, the displacement field information being used for relative displacement of pixel points in the coal rock images; generating a deformation early warning signal based on the displacement field information, wherein the deformation early warning signal is used for representing coal rock surface deformation distribution characteristics; and predicting whether the coal rock is in a failure precursor or not based on the signal frequency of the deformation early warning signal. By implementing the technical scheme provided by the invention, the change characteristics of the coal rock surface can be comprehensively obtained, and the accuracy of early warning is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method for predicting coal-rock damage precursors and related equipment. Background Art

[0002] Coal and rock failure prediction and early warning are important aspects of rock mechanics research. In engineering fields such as coal mining and tunnel construction, the stability of rock mass structure is directly related to engineering safety and the safety of life and property. Accurately predicting the occurrence time of coal and rock failure is of great significance for taking preventive measures in time and avoiding major safety accidents. Therefore, how to effectively monitor the precursor characteristics of coal and rock failure and achieve accurate early warning of coal and rock failure has become a key issue that needs to be solved in this field.

[0003] At present, the prediction of coal and rock damage mainly adopts technical means such as acoustic emission method and strain monitoring method. Among them, the acoustic emission method judges the degree of rock damage by detecting the acoustic signal released when the microcracks inside the rock expand; the strain monitoring method uses strain gauges to measure the strain changes on the surface of coal and rock to evaluate its damage state. These methods predict coal and rock damage by collecting and analyzing the changes in different physical parameters.

[0004] However, existing prediction methods often have the problem of low early warning accuracy in practical applications. This is because these methods require the installation of a large number of sensors on the surface of coal and rock, which not only increases the engineering cost, but also makes it difficult to fully obtain the overall change characteristics of coal and rock due to the limited installation locations of sensors. Especially at the critical moment when coal and rock are about to be destroyed, due to the limitations of monitoring methods, the accuracy and reliability of early warning results are greatly reduced, and it is difficult to meet the requirements for early warning accuracy in engineering practice. Summary of the invention

[0005] The present application provides a method and related equipment for predicting coal-rock damage precursors, which can comprehensively obtain the changing characteristics of the coal-rock surface and improve the accuracy of early warning.

[0006] The present application provides a method for predicting coal-rock failure precursors, comprising: Acquire displacement field information in a plurality of coal and rock images within a preset time period, wherein the displacement field information is used for relative displacement of pixel points in the coal and rock images; Generating a deformation warning signal based on the displacement field information, wherein the deformation warning signal is used to characterize the deformation distribution characteristics of the coal rock surface; Based on the signal frequency of the deformation warning signal, it is predicted whether the coal rock is in the state of being a precursor to destruction.

[0007] Optionally, the displacement field information includes a plurality of displacement fields, each of which is used to characterize the relative displacement of pixels in any two of the coal and rock images, and the generating of the deformation warning signal based on the displacement field information includes: Generating binary images of the displacement fields respectively; Calculating the shortest distance of a connected region in each of the binary images, wherein the connected region is used to represent a group of adjacent pixels in the binary image; A deformation warning signal corresponding to each displacement field is determined based on the shortest distance.

[0008] Optionally, the determining, based on the shortest distance, a deformation warning signal corresponding to each displacement field includes: Determine whether the shortest distance is greater than a threshold; If the shortest distance is greater than a threshold, determining that the deformation warning signal of the displacement field corresponding to the shortest distance is 1; If the shortest distance is less than or equal to the threshold, it is determined that the deformation warning signal of the displacement field corresponding to the shortest distance is 0.

[0009] Optionally, after respectively generating the binary images of the displacement fields, the method further includes: The binary image is preprocessed, and the preprocessing includes burr removal, morphological closing operation and hole filling.

[0010] Optionally, the predicting whether the coal rock is in a state of destruction precursor based on the signal frequency of the deformation warning signal includes: A signal probability density map is generated based on the signal frequency of the deformation warning signal, and whether the coal rock is in a state of precursor to destruction is predicted based on the signal probability density map. The signal probability density map is used to characterize the frequency distribution of the warning signal at each moment within the preset time length.

[0011] Optionally, the obtaining of displacement field information in a plurality of coal and rock images within a preset time period includes: Acquire multiple coal and rock images within a preset time period; Taking two of the plurality of coal-rock images as one image group, to obtain a plurality of image groups; The displacement field of each of the image groups is obtained through DICNet to obtain displacement field information.

[0012] The present application also provides a coal-rock failure precursor prediction device, comprising: A displacement field information acquisition module, used to acquire displacement field information in a plurality of coal and rock images within a preset time period, wherein the displacement field information is used for relative displacement of pixel points in the coal and rock images; A deformation warning signal generating module, used to generate a deformation warning signal based on the displacement field information, wherein the deformation warning signal is used to characterize the deformation distribution characteristics of the coal rock surface; The deformation warning signal prediction module is used to predict whether the coal rock is in a state of destruction precursor based on the signal frequency of the deformation warning signal.

[0013] The present application also provides an electronic device, including 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, the method for predicting coal-rock failure precursors as described above is implemented.

[0014] The present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for predicting coal-rock failure precursors as described in any one of the above is implemented.

[0015] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting coal-rock failure precursors.

[0016] By acquiring the displacement field information from multiple coal and rock images within a preset time, the relative displacement changes of various positions on the coal and rock surface can be characterized without installing sensors; a deformation warning signal is generated based on the acquired displacement field information, which can fully reflect the overall deformation distribution characteristics of the coal and rock surface; and the signal frequency of the deformation warning signal is used to predict whether the coal and rock are in a state of destruction, thereby achieving high-precision early warning of coal and rock destruction. This method does not require the installation of sensors on the coal and rock surface, avoids the monitoring blind spots caused by the limited installation position of the sensor, can fully obtain the change characteristics of the coal and rock surface, and improves the accuracy of the early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flow chart of a method for predicting coal-rock failure precursors provided in an embodiment of the present application; Figure 2 A schematic diagram of a sample image captured by a camera provided in an embodiment of the present application; Figure 3 A schematic diagram of image displacement calculation provided in an embodiment of the present application; Figure 4 A schematic diagram of a binary displacement field of the same sample at different times provided in an embodiment of the present application; Figure 5 A schematic diagram of calculating a warning signal distribution diagram provided in an embodiment of the present application; Figure 6 A warning signal distribution diagram provided in an embodiment of the present application; Figure 7 A probability density diagram of early warning signals based on sample statistics provided in an embodiment of the present application; Figure 8 A schematic diagram of the structure of a coal-rock failure precursor prediction device provided in an embodiment of the present application; Fig. 9 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for predicting coal-rock damage precursors provided by an embodiment of the present application. The method can be implemented by a computer program, a single-chip microcomputer, or a coal-rock damage precursor prediction system based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application. Specifically, the method may include the following steps: S101. Obtain displacement field information in a plurality of coal and rock images within a preset time period, where the displacement field information is used for relative displacement of pixel points in the coal and rock images.

[0021] The displacement field information refers to a data set that characterizes the relative displacement of each pixel point on the surface of the coal rock sample between adjacent moments. In the embodiment of the present application, it can be understood as a series of two-dimensional numerical matrices obtained by calculation, and each matrix element records the displacement value of the corresponding position pixel point in the target frame relative to the reference frame, where a positive value indicates that the point is shifted to the right, a negative value indicates that the point is shifted to the left, and a zero value indicates that the point has not shifted.

[0022] Furthermore, the displacement field information is used to quantitatively describe the microscopic deformation characteristics of the coal rock surface during the stress process. By analyzing these deformation characteristics, the precursor information of coal rock failure can be discovered in time. For example, when the coal rock is in the elastic stage, the displacement of each point on the surface is relatively uniform; when it is about to be destroyed, there will be obvious displacement concentration in a specific area. The change law of displacement distribution can be used as a basis for predicting coal rock failure.

[0023] Based on the above embodiment, as an optional embodiment, in S101: obtaining the displacement field information in a plurality of coal and rock images within a preset time period may further include the following steps: S201, obtaining a plurality of coal and rock images within a preset time period.

[0024] Specifically, in order to obtain the complete process data of coal rock surface deformation, it is first necessary to obtain multiple coal rock images within a preset time. The preset time refers to the entire process from the beginning of applying pressure to the coal rock sample to the complete rupture of the sample, which usually lasts for several minutes.

[0025] Please refer to Figure 2 , Figure 2 A schematic diagram of a sample image captured by a camera provided in an embodiment of the present application. Figure 2 (a) is the image before the sample breaks. Figure 2 (b) is the image of the sample after rupture.

[0026] Specifically, first select a rectangular coal-rock sample of uniform specifications and place it on a pressure testing machine. Set up an industrial camera directly in front of the sample, and adjust the camera bracket to keep the lens at a fixed distance from the surface of the coal-rock sample to ensure that the entire sample surface is within the camera's shooting range. At the same time, in order to ensure image quality, the camera's aperture and focal length need to be adjusted to make the captured image clear and of moderate brightness. The shooting frequency of the industrial camera is set to 5 frames per second, which is determined based on full consideration of the coal-rock deformation rate, image storage capacity, and subsequent processing efficiency.

[0027] Before starting to collect images, the coal and rock samples are pre-pressed to make them fully contact with the upper and lower plates of the pressure testing machine. At the same time as the image collection is started, the pressure testing machine begins to apply pressure evenly. The entire loading process maintains a stable loading rate, and the industrial camera continues to capture images of the surface of the coal and rock samples until obvious cracks or complete rupture of the sample are observed. All collected images are automatically numbered and saved in the order of shooting time. Usually, about 700 coal and rock images can be obtained within the preset time.

[0028] S202. Take two coal-rock images from the plurality of coal-rock images as one image group to obtain a plurality of image groups.

[0029] Specifically, in order to calculate the displacement field information of the coal rock surface, it is necessary to organize multiple coal rock images acquired within a preset time into multiple image groups. Each image group contains two coal rock images at different times, which are used to calculate the deformation characteristics of the coal rock surface between the two times.

[0030] Specifically, first of all, it is necessary to set a suitable step size step, and the selection of the step size needs to make a trade-off between time resolution and computational efficiency. If the step value is too small, although a more detailed deformation process can be obtained, the amount of calculation will be significantly increased; if the step value is too large, important deformation information may be missed. Through a large number of experimental verifications, the embodiment of the present application selects step=5 as the preferred solution. For the acquired coal rock image sequence, starting from the first image in chronological order, a pair of images is selected every step images to form an image group. Specifically, the i-step frame image is used as the reference frame, and the i-step frame image is used as the target frame, and the two constitute an image group. By means of a sliding window, image pairs are continuously selected backwards, and multiple image groups are finally obtained. For example, when step=5, the 1st frame and the 6th frame constitute a group, the 6th frame and the 11th frame constitute a group, and so on, until all images are processed.

[0031] Furthermore, by setting a fixed step size, the time interval between adjacent image groups is guaranteed to be consistent, which is beneficial to the subsequent analysis of the temporal evolution characteristics of the deformation; secondly, there is an appropriate time interval between the reference frame and the target frame, which can ensure that sufficiently obvious deformations are captured without losing important information of the intermediate process due to excessive intervals.

[0032] S203 , obtaining the displacement field of each image group through DICNet to obtain displacement field information.

[0033] Specifically, in order to accurately calculate the deformation characteristics of the coal and rock surface, it is necessary to calculate the displacement field of the constructed image group through the DICNet deep learning network. DICNet is a deep neural network specially used for digital image correlation calculation, which can automatically extract image features and calculate pixel-level displacement information.

[0034] For details, please refer to Figure 3 , Figure 3 A schematic diagram of image displacement calculation provided for an embodiment of the present application. First, a pre-trained DICNet model is deployed in a computing environment. For each image group, the reference frame and the target frame are input into the DICNet network. The network automatically extracts the features of the two frames through multi-layer convolution operations, and calculates the displacement field of the target frame relative to the reference frame. The displacement field is a two-dimensional numerical matrix with the same size as the input image, in which each element represents the displacement value of the corresponding pixel point in the horizontal direction, a positive value indicates movement to the right, a negative value indicates movement to the left, and a zero value indicates that the point has not been displaced. By processing all image groups in turn, a displacement field information sequence covering the entire preset time length is finally obtained.

[0035] S102. Generate a deformation warning signal based on the displacement field information, where the deformation warning signal is used to characterize the deformation distribution characteristics of the coal rock surface.

[0036] Among them, the deformation warning signal refers to a binary indicator that characterizes whether the deformation distribution on the surface of the coal rock sample shows an abnormal concentration trend. In the embodiment of the present application, it can be understood as a quantitative evaluation result of the deformation characteristics of the coal rock surface at each moment, and its value is 0 or 1, where 1 means that the surface deformation distribution at the current moment shows an obvious concentration trend, indicating that damage may occur, and 0 means that the surface deformation distribution at the current moment is relatively uniform, and no obvious signs of damage have appeared. The deformation warning signal is used to monitor the surface deformation evolution characteristics of the coal rock sample during the stress process. By analyzing the change law of its time series, the precursor information of coal rock damage can be discovered in time.

[0037] Specifically, since the displacement field information is a continuous numerical matrix, it is difficult to use it directly for early warning analysis, and it needs to be converted into a form that is easier to analyze. To this end, the embodiment of the present application first performs binarization processing on the displacement field to simplify the subsequent deformation feature analysis.

[0038] Based on the above embodiment, as an optional embodiment, each displacement field is used to characterize the relative displacement of pixels in any two coal-rock images. In S102, the step of generating a deformation warning signal based on the displacement field information may further include the following steps: S301, generating a binary image of each displacement field respectively.

[0039] Specifically, in order to simplify the analysis process of the displacement field and highlight the main features of the surface deformation, it is necessary to convert the continuous displacement field values ​​into discrete binary images. Each element in the displacement field records the horizontal displacement value of the corresponding pixel point. Through the binary processing, the areas moving to the left and moving to the right can be intuitively distinguished, which helps to identify the spatial distribution pattern of coal rock surface deformation.

[0040] Please refer to Figure 4 , Figure 4 A schematic diagram of a binary displacement field of the same sample at different times provided in an embodiment of the present application. Figure 4 (a) is a schematic diagram of the binary surface deformation in the early stage of pressure application. Figure 4 (b) Schematic diagram of the binary surface deformation at the late stage of pressure application (close to rupture).

[0041] Specifically, for each displacement field, a binary processing is first performed with a zero value as the threshold. Pixels with a displacement value greater than zero (indicating a rightward shift) are marked as 1, and pixels with a displacement value less than or equal to zero (indicating a leftward shift or stationary) are marked as 0, thereby obtaining the corresponding binary image. This processing method selects zero as the threshold based on the physical characteristics of surface displacement during coal and rock failure. When coal and rock are about to fail, the areas on both sides of the crack will move in opposite directions. The binary processing with a zero value threshold can clearly reflect the boundary characteristics of this movement trend.

[0042] Furthermore, due to the inevitable existence of measurement noise and local errors in the displacement field calculation process, the image obtained by direct binarization often contains some abnormal areas that do not conform to the actual physical characteristics. These areas will affect the accuracy of subsequent connected region analysis. Therefore, a series of preprocessing operations are required to optimize the quality of the binary image.

[0043] On the basis of the above embodiment, as an optional embodiment, in order to improve the quality of the binary image, the embodiment of the present application also preprocesses the binary image, and the preprocessing includes burr removal, morphological closing operation and hole filling.

[0044] Specifically, the burr removal process is first performed by scanning each pixel in the binary image to determine its relationship with the surrounding neighboring pixels. When the value of a pixel is different from the values ​​of most of its neighboring pixels, it is regarded as a burr point and its value is corrected. This process can effectively eliminate local mutations caused by random noise and make the image edge smoother. Then the morphological closing operation process is performed, which is composed of a sequential combination of erosion and dilation operations. The erosion operation can remove smaller isolated areas and small connecting bridges, and the dilation operation can restore the eroded edges while maintaining the shape of the main area. The combination of these two operations can effectively remove noise points and small areas in the image while keeping the large-scale structural features unchanged. Finally, the hole filling process is performed to detect and fill the hole area inside the binary area to make the shape of the connected area more complete and continuous.

[0045] Furthermore, the optimality of the processing effect can be ensured through preprocessing. First, burr removal can eliminate the most basic noise interference and provide a clearer image for subsequent processing; secondly, morphological closing operation can optimize the image structure on a larger scale; finally, filling holes can improve the integrity of the region. This processing order not only ensures the effect of preprocessing, but also avoids mutual interference between processing steps. Through the above preprocessing operations, the quality of the binary image is significantly improved, noise and local anomalies are effectively suppressed, the regional boundaries are smoother, and the internal structure is more complete.

[0046] S302, calculating the shortest distance of the connected regions in each binary image, where the connected regions are used to represent adjacent pixel groups in the binary image.

[0047] Among them, the connected region refers to a set of pixels in the binary image that have the same pixel value and are interconnected in the eight-neighborhood direction. In the embodiment of the present application, it can be understood as a group of pixels in the binary image that have the same movement trend (moving to the left or moving to the right) and are adjacent in spatial position, where the connected region with a pixel value of 1 represents an area that moves to the right as a whole, and the connected region with a pixel value of 0 represents an area that moves to the left as a whole or is stationary. The connected region is used to characterize the spatial aggregation characteristics of the surface displacement distribution of coal and rock.

[0048] Specifically, the connected regions of the preprocessed binary image are first marked. The eight-neighborhood connectivity criterion is used to mark the pixel sets with the same pixel value and connected to each other in the eight-neighborhood direction as the same connected region. In this way, the pixels in the binary image can be divided into several independent connected regions. For each connected region, the coordinate information of its boundary pixels is recorded for subsequent distance calculation. Then, for the connected regions with pixel values ​​of 1 and the connected regions with pixel values ​​of 0, the shortest distance between them is calculated respectively. The shortest distance is calculated using the Euclidean distance formula, that is, the minimum distance value between the boundary pixels of two different types of connected regions is calculated.

[0049] Furthermore, since there may be multiple connected areas in a binary image, it is necessary to calculate all possible distance combinations between different types of connected areas and select the minimum value as the characteristic distance of the image. This shortest distance calculation method has important physical significance: when the coal rock is in a stable state, the surface displacement distribution is relatively uniform, and the areas with different movement trends are closely connected. At this time, the calculated shortest distance is small; when the coal rock is about to be destroyed, the areas with different movement trends will gradually separate and form a clear dividing zone. At this time, the shortest distance will increase significantly.

[0050] By calculating the shortest distance between connected areas, it is not only possible to quantitatively describe the spatial distribution characteristics of coal rock surface deformation, but also to effectively identify abnormal changes in deformation distribution. This analysis method based on spatial characteristics not only takes into account the continuity characteristics of surface displacement during coal rock failure, but also can capture the mutation characteristics of displacement distribution in a timely manner.

[0051] S303: Determine deformation warning signals corresponding to each displacement field based on the shortest distance.

[0052] Specifically, since the shortest distance can quantitatively characterize the degree of separation between different motion trend areas in the binary image, by comparing the shortest distance with the preset threshold, it can be determined whether the coal rock surface deformation at the current moment shows an abnormal concentration trend. This threshold-based judgment method can convert continuous distance values ​​into discrete warning signals, which is convenient for subsequent warning analysis.

[0053] Based on the above embodiment, as an optional embodiment, in S303: the step of determining the deformation warning signal corresponding to each displacement field based on the shortest distance may further include the following steps: S401: Determine whether the shortest distance is greater than a threshold.

[0054] S402: If the shortest distance is greater than a threshold, determine that the deformation warning signal of the displacement field corresponding to the shortest distance is 1.

[0055] S403: If the shortest distance is less than or equal to the threshold, determine that the deformation warning signal of the displacement field corresponding to the shortest distance is 0.

[0056] Specifically, first determine whether the calculated shortest distance is greater than the preset threshold. The selection of the threshold is based on a large number of experimental statistics and professional experience, and a balance needs to be struck between sensitivity and reliability. When the shortest distance is greater than the threshold, it indicates that an obvious separation zone has appeared between the connected areas of different movement trends. This separation phenomenon usually indicates that large cracks have occurred inside the coal rock and it is in a critical state of imminent destruction. At this time, the deformation warning signal of the corresponding displacement field is set to 1. On the contrary, when the shortest distance is less than or equal to the threshold, it indicates that the displacement distribution on the surface of the coal rock is still relatively uniform, and the areas with different movement trends remain closely connected, indicating that the internal structure of the coal rock is still stable. At this time, the deformation warning signal of the corresponding displacement field is set to 0.

[0057] Furthermore, the above-mentioned warning signal generation method based on threshold judgment has clear physical meaning and practical application value. When the warning signal value is 1, it indicates that the coal rock surface deformation at the current moment has shown abnormal characteristics and needs to be highly valued; when the warning signal value is 0, it indicates that the coal rock surface deformation at the current moment is still within the normal range. This simple and clear judgment mechanism not only improves the automation level of the warning process, but also facilitates the staff to quickly understand and make decisions. At the same time, since the judgment process only involves simple numerical comparisons, the calculation efficiency is very high and can meet the needs of real-time monitoring.

[0058] Through the above threshold-based warning signal generation method, complex surface deformation features can be simplified into intuitive binary signals, which not only retains key warning information but also improves processing efficiency. In particular, in the continuous monitoring process, by observing the changing trend of the warning signal, the precursor characteristics of coal and rock damage can be discovered in time. When the warning signal changes from 0 to 1, it means that the coal and rock have entered a dangerous state and corresponding protective measures need to be taken immediately.

[0059] S103. Predict whether the coal rock is in the process of being destroyed based on the signal frequency of the deformation warning signal.

[0060] Specifically, in order to systematically analyze the time evolution law of the early warning signal during the coal-rock failure process, it is necessary to first construct the early warning signal distribution map of a single sample, and then obtain the frequency characteristics of the early warning signal through statistical analysis. This analysis method from individual to statistical can more comprehensively reveal the early warning characteristics of the coal-rock failure process.

[0061] For details, please refer to Figure 5 , Figure 5 A schematic diagram of the calculation of a warning signal distribution diagram provided in the embodiment of the present application. For a single coal rock sample, firstly, the time when it is completely broken is taken as the time origin (recorded as time T), and the observed time series (T-t1, T-t2, ..., Tt n ). At these time points, the warning indicator WID is calculated based on the acquired binary surface deformation. The time series is used as the horizontal axis and the WID value at the corresponding moment is used as the vertical axis to draw the warning signal distribution diagram of the sample. This time series distribution diagram intuitively shows the evolution characteristics of the warning signal of a single sample during the destruction process, and the transition process from sporadic to intensive appearance of the warning signal can be clearly observed.

[0062] For further information, please refer to Figure 6 , Figure 6 A warning signal distribution diagram is provided in the embodiment of the present application. Based on the warning signal distribution diagram of a single sample, the frequency of the warning signal (WID=1) in the preset time window is counted. The frequency characteristics of the warning signal are obtained by calculating the ratio of the number of occurrences of the warning signal per unit time to the total number of observations.

[0063] The experimental results show that as the coal-rock sample approaches the moment of failure, the frequency of the warning signal increases significantly. Especially in the critical stage before failure, the warning signal will show obvious aggregation characteristics. This frequency mutation phenomenon can be used as an important basis for predicting coal-rock failure.

[0064] On the basis of the above embodiment, as an optional embodiment, a signal probability density map can be generated based on the signal frequency of the deformation warning signal, and whether the coal rock is in the precursor of destruction can be predicted based on the signal probability density map. The signal probability density map is used to characterize the frequency distribution of the warning signal at each moment within a preset time length.

[0065] Specifically, the distribution characteristics of the warning signal of a single sample may be random and uncertain, and it is necessary to establish a more universal prediction model by statistically analyzing the warning signals of a large number of samples during the destruction process. By generating a signal probability density map, the statistical laws of the occurrence of warning signals at different times can be quantitatively described, providing a more reliable basis for predicting coal and rock failure.

[0066] For details, please refer to Figure 7 , Figure 7 A probability density diagram of warning signals based on sample statistics is provided in an embodiment of the present application. First, the warning signal distribution data of multiple coal and rock samples are collected, and the time coordinate system is unified with the time origin of each sample rupture. At the same time node, the frequency of the warning signal (WID=1) appearing in all samples is counted, and the probability of the warning signal at that moment is calculated. The signal probability density diagram is drawn using the time series as the horizontal coordinate and the probability of the warning signal at the corresponding moment as the vertical coordinate. This probabilistic statistical method takes into account the warning characteristics of a large number of samples, which can effectively eliminate the random fluctuations caused by individual differences and reveal the more essential statistical laws of the warning signals.

[0067] Furthermore, by analyzing the distribution characteristics of the signal probability density map, it is possible to accurately determine whether the coal rock is in a state of precursor to failure. Experimental data show that about 90% of the samples began to frequently release warning signals 20 seconds before complete rupture, and the probability of the occurrence of warning signals increased significantly as the rupture moment approached. This probability distribution feature has important physical significance: when the observed warning signal frequency matches the high probability area in the probability density map, it indicates that the coal rock is likely to be in a critical state before failure, and protective measures need to be taken in time.

[0068] The coal-rock damage precursor prediction device provided in the present application is described below. The coal-rock damage precursor prediction device described below and the coal-rock damage precursor prediction method described above can be referenced to each other.

[0069] Please refer to Figure 8 , Figure 8 A schematic diagram of a device for predicting coal-rock failure precursors provided in an embodiment of the present application is provided. Specifically, the device may include: A displacement field information acquisition module, used to acquire displacement field information in a plurality of coal and rock images within a preset time period, wherein the displacement field information is used for relative displacement of pixel points in the coal and rock images; A deformation warning signal generating module, used to generate a deformation warning signal based on the displacement field information, wherein the deformation warning signal is used to characterize the deformation distribution characteristics of the coal rock surface; The deformation warning signal prediction module is used to predict whether the coal rock is in a state of destruction precursor based on the signal frequency of the deformation warning signal.

[0070] On the basis of the above embodiments, as an optional embodiment, the displacement field information includes multiple displacement fields, each of the displacement fields is used to characterize the relative displacement of pixel points in any two of the coal and rock images, and the deformation warning signal generation module is also used to generate binary images of each of the displacement fields respectively; calculate the shortest distance of the connected area in each of the binary images, and the connected area is used to characterize adjacent pixel groups in the binary image; determine the deformation warning signal corresponding to each displacement field based on the shortest distance.

[0071] On the basis of the above embodiment, as an optional embodiment, the deformation warning signal generating module is also used to determine whether the shortest distance is greater than a threshold value; if the shortest distance is greater than the threshold value, the deformation warning signal of the displacement field corresponding to the shortest distance is determined to be 1; if the shortest distance is less than or equal to the threshold value, the deformation warning signal of the displacement field corresponding to the shortest distance is determined to be 0.

[0072] On the basis of the above embodiment, as an optional embodiment, the deformation warning signal generating module is further used to preprocess the binary image, and the preprocessing includes burr removal, morphological closing operation and hole filling.

[0073] On the basis of the above embodiments, as an optional embodiment, the deformation warning signal prediction module is also used to generate a signal probability density map based on the signal frequency of the deformation warning signal, and predict whether the coal rock is in the precursor of destruction based on the signal probability density map. The signal probability density map is used to characterize the frequency distribution of the warning signal at each moment within the preset time length.

[0074] On the basis of the above embodiments, as an optional embodiment, the displacement field information acquisition module is also used to acquire multiple coal rock images within a preset time length; two of the multiple coal rock images are used as an image group to obtain multiple image groups; the displacement field of each of the image groups is acquired through DICNet to obtain the displacement field information.

[0075] Please refer to Fig. 9 , Fig. 9 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application, such as Fig. 9As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the coal-rock damage precursor prediction method.

[0076] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0077] On the other hand, the present application also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the coal and rock damage precursor prediction method provided by the above-mentioned methods.

[0078] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the coal-rock damage precursor prediction method provided by the above-mentioned methods.

[0079] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting coal-rock failure precursors, characterized in that: include: Acquire displacement field information in a plurality of coal and rock images within a preset time period, wherein the displacement field information is used for relative displacement of pixel points in the coal and rock images; Generating a deformation warning signal based on the displacement field information, wherein the deformation warning signal is used to characterize the deformation distribution characteristics of the coal rock surface; Based on the signal frequency of the deformation warning signal, it is predicted whether the coal rock is in the state of being a precursor to destruction.

2. The method for predicting coal-rock failure precursors according to claim 1, characterized in that: The displacement field information includes a plurality of displacement fields, each of which is used to characterize the relative displacement of pixels in any two of the coal and rock images. The generation of a deformation warning signal based on the displacement field information includes: Generating binary images of the displacement fields respectively; Calculating the shortest distance of a connected region in each of the binary images, wherein the connected region is used to represent a group of adjacent pixels in the binary image; A deformation warning signal corresponding to each displacement field is determined based on the shortest distance.

3. The method for predicting coal-rock failure precursors according to claim 2, characterized in that: The step of determining the deformation warning signal corresponding to each displacement field based on the shortest distance includes: Determine whether the shortest distance is greater than a threshold; If the shortest distance is greater than a threshold, determining that the deformation warning signal of the displacement field corresponding to the shortest distance is 1; If the shortest distance is less than or equal to the threshold, it is determined that the deformation warning signal of the displacement field corresponding to the shortest distance is 0.

4. The method for predicting coal-rock failure precursors according to claim 2, characterized in that: After the binary images of the displacement fields are generated respectively, the method further includes: The binary image is preprocessed, and the preprocessing includes burr removal, morphological closing operation and hole filling.

5. The method for predicting coal-rock failure precursors according to claim 1, characterized in that: The predicting whether the coal rock is in a state of destruction precursor based on the signal frequency of the deformation warning signal includes: A signal probability density map is generated based on the signal frequency of the deformation warning signal, and whether the coal rock is in a state of precursor to destruction is predicted based on the signal probability density map. The signal probability density map is used to characterize the frequency distribution of the warning signal at each moment within the preset time length.

6. The method for predicting coal-rock failure precursors according to claim 1, characterized in that: The step of obtaining the displacement field information of a plurality of coal and rock images within a preset time period includes: Acquire multiple coal and rock images within a preset time period; Taking two of the plurality of coal-rock images as one image group, to obtain a plurality of image groups; The displacement field of each of the image groups is obtained through DICNet to obtain displacement field information.

7. A device for predicting precursors of coal and rock failure, characterized in that: include: A displacement field information acquisition module, used to acquire displacement field information in a plurality of coal and rock images within a preset time period, wherein the displacement field information is used for relative displacement of pixel points in the coal and rock images; A deformation warning signal generating module, used to generate a deformation warning signal based on the displacement field information, wherein the deformation warning signal is used to characterize the deformation distribution characteristics of the coal rock surface; The deformation warning signal prediction module is used to predict whether the coal rock is in a state of destruction precursor based on the signal frequency of the deformation warning signal.

8. An electronic device comprising 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, the method for predicting coal-rock failure precursors as described in any one of claims 1 to 6 is implemented.

9. 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, the method for predicting coal-rock failure precursors as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting coal-rock failure precursors as described in any one of claims 1 to 6 is implemented.

Images