A coal geological intensity index image detection method based on a mobile terminal

Abstract

The present application relates to a kind of coal geology intensity index image detection method based on mobile terminal, belong to coal geology intensity index detection field.Method includes: obtaining the image of coal rock mass to be measured;Extract the fracture joint parameters of the image of coal rock mass to be measured;According to the fracture joint parameters of the coal rock mass to be measured, the coal geology intensity index of the coal rock mass to be measured is detected using the optimized BP neural network model, and the coal geology intensity index is obtained to carry out coal rock cutting planning and drilling.The present application improves the detection accuracy of coal geology intensity index.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of coal geological strength index detection, in particular to a coal geological strength index image detection method based on a mobile terminal. BACKGROUND

[0002] The coal geological strength index is an important parameter in rock mechanics, and the geological strength index needs to be used for coal rock cutting planning and drilling in coal mine drilling and anchoring engineering. According to the complexity of the fissure joint of the coal rock mass, the coal geological strength index is represented as 0-100, and the higher the coal geological strength index, the simpler the fissure joint of the coal rock mass and the more stable the structure. There is no fixed calculation formula for the coal geological strength index, and the coal geological strength index is often estimated by experienced engineering personnel according to the geological strength index reference table. The coal geological strength index obtained in this way is prone to errors due to human subjective factors, so it is particularly important to quantitatively characterize the coal geological strength index. SUMMARY

[0003] The purpose of the present application is to provide a coal geological strength index image detection method based on a mobile terminal, so as to solve the problem that the coal geological strength index obtained by engineering personnel estimating the coal geological strength index according to the coal geological strength index reference table is prone to errors due to human subjective factors.

[0004] To achieve the above-mentioned purpose, the present application provides the following scheme:

[0005] A coal geological strength index image detection method based on a mobile terminal, comprising:

[0006] Obtaining a coal rock mass image to be detected;

[0007] Image processing the coal rock mass image to be detected to extract fissure joint parameters of the coal rock mass to be detected;

[0008] According to the fissure joint parameters of the coal rock mass to be detected, the coal rock mass to be detected is detected by using an optimized BP neural network model to obtain a coal geological strength index, so as to perform coal rock cutting planning and drilling; the optimized BP neural network model comprises a fissure joint parameter input layer, a hidden layer and a geological strength index output layer.

[0009] Optionally, the construction process of the optimized BP neural network model specifically comprises:

[0010] Obtaining a coal rock mass original image;

[0011] Image processing the coal rock mass original image to extract fissure joint parameters of the coal rock mass;

[0012] construct a data set and a BP neural network model; the data set comprises fissure joint parameters of the coal rock mass and an estimated coal geological strength index;

[0013] train the BP neural network model by taking the fissure joint parameters of the coal rock mass as input and the estimated coal geological strength index as output, to obtain a trained BP neural network model;

[0014] optimize the trained BP neural network model by using an improved particle swarm algorithm, to obtain an optimized BP neural network model.

[0015] Optionally, the fissure joint parameters comprise fissure joint quantity, fissure width, fissure length and occupancy.

[0016] Optionally, the image processing on the to-be-detected coal rock mass image to extract fissure joint parameters of the to-be-detected coal rock mass comprises:

[0017] graying, edge detection and denoising processing are performed on the to-be-detected coal rock mass image, to obtain a processed coal rock mass image;

[0018] the fissure joint quantity of the coal rock mass is extracted from the processed coal rock mass image;

[0019] the fissure length of the coal rock mass is calculated by using a formula ; wherein L represents the fissure length, n represents the number of horizontally or vertically adjacent pixel points on the center line of the processed coal rock mass image, m represents the number of 45° adjacent pixel points on the center line of the processed coal rock mass image, and ε represents the length of a single pixel point;

[0020] the fissure width of the coal rock mass is calculated by using a formula ; wherein D represents the fissure width, p represents the number of horizontally or vertically adjacent pixel points on the vertical line of the processed coal rock mass image, and q represents the number of 45° adjacent pixel points on the vertical line of the processed coal rock mass image;

[0021] the occupancy is determined according to the number of fissure joint pixel points and the number of non-fissure joint pixel points in the processed coal rock mass image.

[0022] Optionally, the extraction of the fissure joint quantity of the coal rock mass from the processed coal rock mass image comprises:

[0023] the gradient amplitude of the pixel points in the processed coal rock mass image is calculated;

[0024] non-maximum suppression is performed according to the gradient amplitude, to determine the fissure edge points of the processed coal rock mass image, to obtain a coal rock mass image containing the fissure edge points;

[0025] The coal rock mass image containing the crack edge points is processed by using a double threshold method to obtain a coal rock mass image containing a crack joint;

[0026] The number of crack joints is determined according to the coal rock mass image containing the crack joint.

[0027] Optionally, the mobile terminal is used to acquire the coal rock mass image to be detected.

[0028] A mobile terminal is used to implement the mobile terminal-based coal geological strength index image detection method, and the mobile terminal comprises a front-end UI interface and a back-end running module; the front-end UI interface comprises a login unit, an image acquisition unit and a data output unit; and the back-end running module comprises an image processing unit and a neural network unit.

[0029] The login unit is used to log in a user account.

[0030] The image acquisition unit is used to acquire a coal rock mass image to be detected.

[0031] The data output unit is used to transmit the coal rock mass image to be detected to the image processing unit.

[0032] The image processing unit is used to perform image processing on the coal rock mass image to be detected and extract crack joint parameters of the coal rock mass to be detected.

[0033] The neural network unit comprises an optimized BP neural network model, and is used to detect the coal rock mass to be detected according to the crack joint parameters of the coal rock mass to be detected by using the optimized BP neural network model, obtain a coal geological strength index, and perform coal rock cutting planning and drilling; the optimized BP neural network model comprises a crack joint parameter input layer, a hidden layer and a geological strength index output layer.

[0034] A mobile terminal-based coal geological strength index image detection system comprises:

[0035] An image acquisition module is used to acquire a coal rock mass image to be detected.

[0036] An image processing module is used to perform image processing on the coal rock mass image to be detected and extract crack joint parameters of the coal rock mass to be detected.

[0037] An index detection module is used to detect the coal rock mass to be detected according to the crack joint parameters of the coal rock mass to be detected by using an optimized BP neural network model, obtain a coal geological strength index, and perform coal rock cutting planning and drilling; the optimized BP neural network model comprises a crack joint parameter input layer, a hidden layer and a geological strength index output layer.

[0038] An electronic device, comprising: a memory for storing a computer program, and a processor for running the computer program to make the electronic device execute the mobile terminal-based coal geological strength index image detection method described above.

[0039] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the mobile terminal-based coal geological strength index image detection method described above.

[0040] According to the specific embodiments of the present application, the following technical effects are disclosed:

[0041] The mobile terminal-based coal geological strength index image detection method, mobile terminal, system and device of the present application obtain the image of the coal rock mass to be detected, extract the fracture joint parameters of the coal rock mass to be detected, detect the coal rock mass to be detected by using the optimized BP neural network model according to the fracture joint parameters of the coal rock mass to be detected, and obtain the coal geological strength index for coal rock cutting planning and drilling. The present application trains and optimizes the BP neural network model, detects the coal geological strength index of the coal rock mass by using the optimized BP neural network model, avoids manual estimation of the coal geological strength index, eliminates the error caused by human subjective factors, and improves the detection accuracy of the coal geological strength index. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 The flowchart of the mobile terminal-based coal geological strength index image detection method provided by the present application is shown in the figure.

[0044] Figure 2 The coal rock mass original image provided by the present application is shown in the figure.

[0045] Figure 3 The coal rock mass image with edge discontinuity provided by the present application is shown in the figure.

[0046] Figure 4 The coal rock mass image containing fracture joints provided by the present application is shown in the figure.

[0047] Figure 5 The geological strength index reference diagram provided by the present application is shown in the figure.

[0048] Figure 6 A BP neural network model structure diagram provided by the present application is shown in Figure 1.

[0049] Figure 7 A mobile terminal application program login interface diagram provided by the present application is shown in Figure 2.

[0050] Figure 8 A geological strength index detection method flowchart in the embodiment provided by the present application is shown in Figure 3.

[0051] Figure 9 A mobile terminal application program main interface schematic diagram provided by the present application is shown in Figure 4. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0053] The purpose of the present application is to provide a coal geological strength index image detection method based on a mobile terminal, which eliminates the errors caused by artificial subjective factors and improves the detection accuracy of the coal geological strength index.

[0054] The original image is obtained by photographing the coal rock mass with a mobile phone, and the geological strength index of the rock mass to be measured is calculated through image processing algorithms and BP neural network, so that the geological strength index can be quickly and effectively quantitatively represented.

[0055] With the development of 5G and intelligent mine construction, explosion-proof smart phones are gradually applied in coal mines, and smart phone mobile terminals have gained popularity due to their small size and easy operation. In recent years, with the popularization of smart phones, more and more users have participated in the experience of smart phones. The powerful functions of smart phones make them applied in various aspects and have achieved good results. Compared with PC, smart phones have the advantages of low cost, easy operation, strong convenience, and independence from the environment in the field of industrial engineering, and the user base is large and the update is fast, so they will have a broader application prospect in the future industrial control field.

[0056] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0057] Embodiment one

[0058] Figure 1The flow chart of the coal geological strength index image detection method based on a mobile terminal provided by the present application is shown in Figure 1 The method of the present application comprises:

[0059] Step 101: Obtain the image of the coal rock mass to be measured. In actual application, there are two methods to obtain the surface photo of the coal rock mass, one is to obtain it by taking a photo on site through a mobile phone, and the other is to download the photo of the coal rock mass on the network. It is required that the fissure joint of the obtained coal rock mass is clear and visible. Figure 2

[0060] Step 102: Perform image processing on the image of the coal rock mass to be measured, and extract the fissure joint parameters of the coal rock mass to be measured. The fissure joint parameters include the number of fissure joints, fissure width, fissure length and occupancy rate.

[0061] Further, the step 102 specifically comprises:

[0062] Step 1021: Perform gray-scale processing, edge detection and denoising processing on the image of the coal rock mass to be measured, and obtain the processed image of the coal rock mass.

[0063] In actual application, after obtaining the image of the coal rock mass to be measured through step 101, it is required to perform gray-scale processing on the image of the coal rock mass to be measured. Image gray-scale processing is the process of converting a color image into a gray-scale image. A color image usually includes R, G and B components, which display various colors such as red, green and blue. Gray-scale processing is the process of making the R, G and B components of a color image equal.

[0064] Gray = R*0.299 + G*0.587 + B*0.114 (1)

[0065] The original image of the coal rock mass is gray-scaled by using formula (1), wherein Gray represents the red, green and blue components after gray-scale processing, and R, G and B represent the red, green and blue components before image gray-scale processing.

[0066] After gray-scale processing, edge detection is performed on the gray-scale image to highlight the features of the fissure joint of the image. In addition, a Gaussian filter is used to perform denoising processing on the gray-scale image after edge detection to reduce the influence of noise on the image processing result, that is, the image is convolved by using a Gaussian function to obtain the processed image of the coal rock mass.

[0067] Step 1022: Extract the number of fissure joints of the coal rock mass according to the processed image of the coal rock mass.

[0068] ​Specifically, the pixel gradient amplitude and angle of the processed coal rock mass image are calculated, x, y represent the pixel coordinates, and the gradients in the x and y directions can be obtained according to the pixel coordinates by using formulas (2) and (3):

[0069]

[0070]

[0071] wherein G x , G y are the gradients of the pixel in the x and y directions respectively; S is the convolution template of the pixel.

[0072] Then, the gradient amplitude and angle of the pixel can be calculated by using formulas (4) and (5) according to the gradients in the x and y directions:

[0073]

[0074]

[0075] wherein P and θ are the gradient amplitude and angle of the pixel respectively.

[0076] Non-maximum suppression is performed on the gradient amplitude, the fissure region is marked as a region of interest, and local maximum values are searched in the region of interest. The gray value corresponding to the non-maximum value point is set to 0, so that the influence of a part of non-edge pixel points can be eliminated. The pixel points in the region of interest are traversed, and for each fissure pixel point, the center pixel point and the two pixel points along the gradient direction in a 3x3 neighborhood are compared. If the gray value of the pixel point along the gradient direction is greater than the gray value of the center pixel point, the center pixel point in the region is an edge point. If the gray value of the pixel point along the gradient direction is less than the gray value of the center pixel point, the center pixel point in the region is not an edge point. The image is processed by using a double-threshold method, the image edge points are detected and connected, and due to the influence of noise, the problem of discontinuity in the continuous edge may occur, as shown in FIG. 2. Figure 3 To solve this problem, two thresholds are set, a high threshold TH and a low threshold TL. If the gradient amplitude of the pixel is greater than TH, the pixel is an edge pixel; if the gradient value of the pixel is less than TL, the pixel is a non-edge pixel; if the gradient amplitude of the pixel is between TL and TH, the 8 points in the neighborhood of the pixel need to be detected. If one or more of the 8 points have a gradient value greater than TH, the pixel is an edge pixel, otherwise it is not an edge pixel. Thus, the problem of discontinuity in the continuous edge is solved, and the coal rock mass image containing fissure joints is obtained, as shown in FIG. 3. Figure 4

[0077] ​The connected domain in the image of the coal rock mass containing fissure joints is extracted, a threshold is set, small area regions (connected domains) smaller than the set threshold are eliminated, and the number S of fissure joints in the image is calculated, wherein the number S of fissure joints in the image is the number of lines with continuous gray values, and the length of the line needs to be greater than a set length threshold.

[0078] Step 1023: the formula is used The fissure length of the coal rock mass is calculated; wherein L represents the fissure length, n represents the number of horizontally or vertically adjacent pixel points on the skeleton center line of the fissure joint, m represents the number of 45° adjacent pixel points on the skeleton center line of the fissure joint, and ε represents the length of a single pixel point.

[0079] In actual application, the skeleton is refined, the length is measured, and the proportional relationship between the actual size of the image and the pixel size can be determined through the calibration of the camera, so that the pixel size of the image fissure calculated can correspond to the actual size of the fissure joint. The length of each pixel point ε is known, the distance between horizontally or vertically adjacent pixels is 1 pixel interval, and the distance between 45° adjacent pixels is pixel interval, and the length of the fissure joint is the product of the number of the center points of the contour skeleton and the length of a single pixel.

[0080] Step 1024: the formula is used The fissure width of the coal rock mass is calculated; wherein D represents the fissure width, p represents the number of horizontally or vertically adjacent pixel points on the perpendicular line of the skeleton center line of the fissure joint, and q represents the number of 45° adjacent pixel points on the perpendicular line of the skeleton center line of the fissure joint.

[0081] In actual application, the perpendicular line is drawn on the skeleton center line of the fissure joint, and the fissure width is the product of the number of the perpendicular line of the contour skeleton center line and the length of a single pixel.

[0082] Step 1025: the occupancy is determined according to the number of the pixel points of the fissure joint and the number of the pixel points of the non-fissure joint in the processed image of the coal rock mass. In actual application, the occupancy can reflect the complexity of the fissure joint in the image, and is determined by the ratio of the number of the pixel points of the fissure joint to the number of the pixel points of the non-fissure joint on the image.

[0083] Step 103: the coal rock mass is detected by using the optimized BP neural network model according to the fissure joint parameters of the coal rock mass to be detected, and the coal geological strength index is obtained to perform coal rock cutting planning and drilling.

[0084] The construction process of the optimized BP neural network model is as follows:

[0085] 2000 groups of original images of coal rock mass are acquired, and the fissure joint parameters of the coal rock mass are acquired using the image processing method, including four parameters of fissure joint number, fissure width, fissure length and occupancy rate. In addition, the corresponding geological strength index is estimated by referring to the geological strength index reference diagram as shown in Figure 5 , and a data set is constructed, in which the 2000 groups of fissure joint parameters and the estimated coal geological strength index are taken as the data set, of which 1500 groups are taken as the training set and 500 groups are taken as the test set.

[0086] The data set includes the fissure joint parameters of the coal rock mass and the estimated coal geological strength index.

[0087] A BP neural network model is established, as shown in Figure 6 , the input layer is four parameters of fissure joint number, fissure width (i.e. the average width in Figure 6 ), fissure length (i.e. the average length in Figure 6 ) and occupancy rate, the output layer is the geological strength index, the hidden layer is set to 9 according to the formula, the training function selected is the adaptive lr gradient descent training function traingda, the activation function of the hidden layer is the logarithmic S-shaped activation function logsig, and the activation function of the output layer is the linear activation function purelin. The target error of training is set to 1x10 －6 , which is much higher than the requirement of the recognition accuracy of coal rock fissure joint in engineering, the maximum number of iterations is set to 1000, and the learning rule of the network is the error gradient descent method.

[0088] The fissure joint parameters of the coal rock mass are taken as the input, and the estimated coal geological strength index is taken as the output, and the BP neural network model is trained to obtain the trained BP neural network model.

[0089] The improved particle swarm optimization algorithm is used to optimize the trained BP neural network model to obtain the optimized BP neural network model. In actual application, the improved particle swarm optimization algorithm is used to optimize the trained BP neural network model, the dimension of the particle swarm calculated in the improved particle swarm optimization algorithm is 56, the learning factor is set to 2, the maximum value w max and the minimum value w min of the inertia weight are 0.9 and 0.4 respectively, the maximum limited speed v max is 1, and the number of iterations is 1000.

[0090] The other 500 groups of data are used to verify and test the optimized BP neural network model, and the results show that the optimized BP neural network model has great improvement in output accuracy, calculation speed and reliability.

[0091] Example Two

[0092] The optimized BP neural network model is applied to a mobile terminal application program composed of a front-end UI interface and a back-end running program (a back-end running module). The front-end UI interface mainly includes a login unit, an image acquisition unit, and a data output unit, and the back-end running program mainly includes an image processing unit and a neural network unit. The mobile terminal application program is developed using Android Stuidio software and programmed using JAVA language, and has the advantages of high detection accuracy, fast speed, and beautiful interface.

[0093] The use method of the mobile terminal application program is as follows:

[0094] After opening the mobile terminal application program, a login operation is required. Before login, an account password registration is required, as shown in Figure 7 The registered account password is stored in the MySql database.

[0095] After logging into the mobile terminal application program, the use method flow chart is as shown in Figure 8 Clicking the "take a photo" button on the main interface can open the phone camera and collect the image of the coal rock to display on the interface. Clicking the "album" button on the main interface can call the phone album and select the coal rock photo stored in the album to display on the interface.

[0096] The image processing unit mainly calls the OpenCV vision library and uses the built-in image processing algorithm of OpenCV to detect the coal rock fracture joint, and calculates the number, average length, average width, and occupancy rate of the fracture joint in the coal rock image.

[0097] The calculated four parameters are imported into the BP neural network model trained after optimization to detect the geological strength index, and the detection result is displayed on the main interface, as shown in Figure 9 .

[0098] The mobile terminal application program is built-in with various communication modules, including TCP / IP, WiFi, Bluetooth, MQTT communication, which can send and receive the detected geological strength index data.

[0099] Example Three

[0100] In order to perform the method corresponding to the above-mentioned example one to realize the corresponding functions and technical effects, a coal geological strength index image detection system based on a mobile terminal is provided, comprising:

[0101] An image acquisition module for acquiring a coal rock image to be measured.

[0102] An image processing module is configured to perform image processing on the image of the coal rock mass to be detected and extract a fissure joint parameter of the coal rock mass to be detected.

[0103] An index detection module is configured to detect the coal rock mass to be detected by using the optimized BP neural network model according to the fissure joint parameter of the coal rock mass to be detected, and obtain a coal geological strength index for coal rock cutting planning and drilling.

[0104] Embodiment four

[0105] The application further provides an electronic device, including a memory and a processor, the memory is used for storing a computer program, and the processor runs the computer program to make the electronic device execute the mobile terminal-based coal geological strength index image detection method of embodiment one.

[0106] Embodiment five

[0107] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the mobile terminal-based coal geological strength index image detection method of embodiment one.

[0108] Compared with the prior art, the application can quickly and effectively obtain a coal fissure joint parameter, quantitatively represent a coal geological strength index, and has the advantages of convenient operation, high efficiency and high precision.

[0109] The convenient operation is mainly reflected in that the detection is performed by photographing by using a mobile phone, and the detection is easy to operate and easy to carry. The high efficiency is mainly reflected in that the previous geological strength index is obtained by an engineering personnel by referring to a table, while the application adopts image detection to quantitatively represent the geological strength index, so that the detection speed is high, and the error caused by artificial subjective factors is eliminated. The high precision is mainly reflected in that 2000 groups of data sets are used in the application, a BP neural network model is established to detect the coal geological strength index, and an improved particle swarm algorithm is used to optimize the BP neural network, so that the detection precision is greatly improved.

[0110] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other. For the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can be referred to the method part.

[0111] The principles and implementation manners of the present application are described by using specific examples in the present application, and the above examples are only used to help understand the method of the present application and its core idea; meanwhile, for the general technical personnel in the art, the specific implementation manners and application ranges will be changed according to the idea of the present application. In conclusion, the content of the present specification should not be understood as the limitation of the present application.

Claims

1. A mobile terminal-based coal geological strength index image detection method, characterized in that, The method comprises the following steps: acquiring a coal rock mass image to be tested; performing image processing on the coal rock mass image to be tested to extract crack joint parameters of the coal rock mass to be tested, wherein the crack joint parameters include crack joint quantity, crack width, crack length, and occupancy rate; performing image processing on the coal rock mass image to be tested to extract crack joint parameters of the coal rock mass to be tested, and the specific steps include: performing grayscale, edge detection, and denoising processing on the coal rock mass image to be tested to obtain a processed coal rock mass image; extracting crack joint quantity of the coal rock mass from the processed coal rock mass image; Using formula Calculate the fracture length of the coal rock mass; where, Indicates the crack length. This indicates the number of horizontally or vertically adjacent pixels along the center line of the processed coal and rock mass image. This indicates the number of pixels adjacent to each other at 45° along the center line of the processed coal and rock mass image. Indicates the length of a single pixel; The fracture width of the coal rock mass is calculated by using the formula wherein, represents the fracture width, represents the number of horizontally or vertically adjacent pixel points on the vertical line of the processed coal rock mass image, represents the number of 45° adjacent pixel points on the vertical line of the processed coal rock mass image; determining the occupancy rate according to the quantity of crack joint pixel points and the quantity of non-crack joint pixel points in the processed coal rock mass image; extracting crack joint quantity of the coal rock mass from the processed coal rock mass image, and the specific steps include: calculating gradient amplitude of pixel points in the processed coal rock mass image; performing non-maximum suppression according to the gradient amplitude to determine crack edge points of the processed coal rock mass image to obtain a coal rock mass image containing crack edge points; processing the coal rock mass image containing crack edge points by using a double-threshold method to obtain a coal rock mass image containing crack joints; determining the crack joint quantity according to the coal rock mass image containing crack joints; detecting the coal rock mass to be tested by using an optimized BP neural network model according to the crack joint parameters of the coal rock mass to be tested to obtain a coal geological strength index for coal rock cutting planning and drilling, wherein the optimized BP neural network model comprises a crack joint parameter input layer, a hidden layer, and a geological strength index output layer.

2. The mobile terminal-based coal geologic strength index image detection method of claim 1, wherein, The construction process of the optimized BP neural network model specifically includes: acquiring a coal rock mass original image; performing image processing on the coal rock mass original image to extract crack joint parameters of the coal rock mass; constructing a data set and a BP neural network model, wherein the data set comprises the crack joint parameters of the coal rock mass and an estimated coal geological strength index; training the BP neural network model by taking the crack joint parameters of the coal rock mass as input and taking the estimated coal geological strength index as output to obtain a trained BP neural network model; optimizing the trained BP neural network model by using an improved particle swarm algorithm to obtain an optimized BP neural network model. 3.The mobile terminal-based coal geologic strength index image detection method of claim 1, wherein, The mobile terminal is used to acquire the coal rock mass image to be tested.

4. A mobile terminal, characterized by The mobile terminal is used to implement the coal geological strength index image detection method based on the mobile terminal according to any one of claims 1-3, and the mobile terminal comprises a front-end UI interface and a back-end running module; the front-end UI interface comprises a login unit, an image acquisition unit, and a data output unit; and the back-end running module comprises an image processing unit and a neural network unit. The login unit is used to log in a user account. The image acquisition unit is used to acquire a coal rock mass image to be tested. The data output unit is used to transmit the coal rock mass image to be tested to the image processing unit. The image processing unit is used to perform image processing on the coal rock mass image to be tested to extract crack joint parameters of the coal rock mass to be tested. The neural network unit comprises an optimized BP neural network model, and is configured to detect the coal rock mass to be measured according to the fracture joint parameters of the coal rock mass to be measured, and obtain a coal geological strength index by using the optimized BP neural network model, so as to perform coal rock cutting planning and drilling.

5. A mobile terminal-based coal geological strength index image detection system, characterized by, Comprise: An image acquisition module configured to acquire an image of a coal rock mass to be measured; An image processing module configured to perform image processing on the image of the coal rock mass to be measured, and extract fracture joint parameters of the coal rock mass to be measured; the fracture joint parameters comprise a fracture joint number, a fracture width, a fracture length and an occupancy rate; The image processing on the image of the coal rock mass to be measured and the extraction of the fracture joint parameters of the coal rock mass to be measured specifically comprise: Performing grayscale, edge detection and denoising processing on the image of the coal rock mass to be measured to obtain a processed coal rock mass image; Extracting the fracture joint number of the coal rock mass according to the processed coal rock mass image; The fracture length of the coal rock mass is calculated by using the formula wherein, represents the fracture length, represents the number of horizontally or vertically adjacent pixel points on the center line of the processed coal rock mass image, represents the number of 45° adjacent pixel points on the center line of the processed coal rock mass image, represents the length of a single pixel point; The fracture width of the coal rock mass is calculated by using the formula wherein, represents the fracture width, represents the number of horizontally or vertically adjacent pixel points on the vertical line of the processed coal rock mass image, represents the number of 45° adjacent pixel points on the vertical line of the processed coal rock mass image; Determining the occupancy rate according to the number of fracture joint pixel points and the number of non-fracture joint pixel points in the processed coal rock mass image; The extraction of the fracture joint number of the coal rock mass according to the processed coal rock mass image specifically comprises: Calculating gradient amplitudes of pixel points in the processed coal rock mass image; Performing non-maximum suppression according to the gradient amplitudes to determine fracture edge points of the processed coal rock mass image, and obtaining a coal rock mass image containing the fracture edge points; Processing the coal rock mass image containing the fracture edge points by using a double-threshold method to obtain a coal rock mass image containing fracture joints; Determining the fracture joint number according to the coal rock mass image containing the fracture joints; An index detection module configured to detect the coal rock mass to be measured according to the fracture joint parameters of the coal rock mass to be measured by using an optimized BP neural network model, and obtain a coal geological strength index to perform coal rock cutting planning and drilling; the optimized BP neural network model comprises a fracture joint parameter input layer, a hidden layer and a geological strength index output layer.

6. An electronic device, comprising: Comprise: A memory configured to store a computer program, and a processor configured to run the computer program to enable the electronic device to perform the mobile terminal-based coal geological strength index image detection method according to any one of claims 1-3.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the mobile terminal-based coal geological strength index image detection method according to any one of claims 1-3.

Images