Mining conveyor belt tear detection system, method, equipment and medium

Abstract

The present application proposes a mining conveyor belt tear detection system, method, equipment and medium, and constructs a mining conveyor belt tear detection system including a camera array, a gyroscope, a control module, an image processing module and a detection module. The camera array, gyroscope and other sensors are arranged at appropriate positions. The image processing module performs grayscale conversion, splicing and fusion, edge enhancement on the several images taken, and performs corresponding contour extraction and fusion. Then, the detection module calculates the area, the angle with the running direction of the conveyor belt, the edge gradient mean, etc. according to the fused contour. When the calculation result meets the conditions, it is judged that the conveyor belt is torn. In this way, the specific tear position of the conveyor belt can be detected in real time and at a fixed point, meeting the real-time and accurate detection and early warning requirements, thereby indirectly improving the production efficiency of the mine.

Description

Technical Field

[0001] The present application relates to the field of industrial visual inspection technology, and in particular to a mining conveyor belt tear detection system, method, equipment and medium. Background Art

[0002] Belt conveyors are widely used for transporting materials underground in mines. However, when operating underground, idler rollers bear the dual pressures of material load and belt friction. If idler rollers become damaged or bearings become stuck due to material fatigue or improper installation, their sharp edges can directly contact the belt's bearing surface, causing localized stress concentration. As the belt continues to operate, this friction can gradually expand the damage, eventually causing longitudinal or transverse tears.

[0003] It is difficult to detect the specific tearing location using tear detection devices such as weighing sensor detection devices, and they cannot meet the needs of real-time detection and early warning. As a result, a lot of time will be spent on searching for the fault point. Usually, the difficulty in finding the fault point will lead to long shutdowns, seriously affecting the production efficiency of the mine. Summary of the Invention

[0004] The present application proposes a mining conveyor belt tear detection system, method, equipment and medium, which can solve the problem of the inability to accurately and real-time detect conveyor belt tears in the background art.

[0005] To achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a mining conveyor belt tear detection system is provided, the system comprising:

[0007] A camera array is installed at the intervals between the rollers of a mining belt conveyor;

[0008] Gyroscope, used to dynamically monitor the real-time belt inclination of mining belt conveyors;

[0009] A control module, configured to control the camera array to adjust to a target pitch angle for shooting based on the real-time belt plane inclination angle and the camera array pitch angle adjustment strategy;

[0010] an image processing module, configured to convert an original image captured by the camera array into a plurality of grayscale images, perform stitching and fusing of the plurality of grayscale images to generate a panoramic image, perform edge enhancement processing on the panoramic image to obtain an enhanced image, extract connected domain closed contours from the enhanced image, and perform morphological closing operation fusion on adjacent closed contours whose distances meet a first preset condition; and

[0011] The detection module is used to calculate the area of ​​the fused contour, the angle between the main axis direction of the fused contour and the running direction of the conveyor belt, and the average edge gradient of the fused contour. When the area, angle and average edge gradient of the fused contour meet the second condition, it is determined that the conveyor belt is torn.

[0012] In a possible design of the first aspect, the system further includes: a circularly polarized light source, wherein the installation position of the circularly polarized light source satisfies: ,in, is the position of the circularly polarized light source on the slide rail, is the belt width, and α is the divergence angle of the light source to eliminate the interference of reflections on the metal surface.

[0013] In a possible design manner of the first aspect, the camera array pitch angle adjustment strategy is: ,in, is the target inclination angle, is the real-time belt surface inclination angle, k is the proportional coefficient, ensuring that the viewing angle covers the full width of the belt. is the current pitch angle of the camera array, is the target pitch angle.

[0014] In a possible design of the first aspect, the image processing module is specifically configured to: extract SIFT feature points of adjacent grayscale images and perform bidirectional matching, and use a RANSAC algorithm to eliminate mismatched points;

[0015] Solving the matched homography matrix; and

[0016] Based on the homography matrix, a weighted fusion algorithm is applied to eliminate stitching gaps to generate the panoramic image.

[0017] In a possible design manner of the first aspect, the image processing module is specifically configured to:

[0018] Performing grayscale mapping on the panoramic image to obtain a grayscale image;

[0019] Applying the Laplace operator to perform second-order derivative edge detection on the grayscale image to obtain the second-order derivative;

[0020] Normalizing the second-order derivative to obtain a normalized image;

[0021] Performing Gaussian smoothing on the normalized image to obtain a smoothed image;

[0022] Performing grayscale transformation on the smoothed image to enhance edge areas and suppress non-edge areas, thereby obtaining a transformed image;

[0023] Binarizing the transformed image to obtain a binarized image; and

[0024] The closed contour in the binarized image is extracted based on connected component analysis of the binarized image.

[0025] In a possible design manner of the first aspect, the image processing module is further configured to:

[0026] Calculating the closed contour area or the closed contour aspect ratio; and

[0027] When the closed contour area or the closed contour aspect ratio meets a third preset condition, the noise contour is removed.

[0028] In a possible design manner of the first aspect, the detection module is specifically configured to:

[0029] The tearing position of the conveyor belt is calibrated jointly by the encoder reference time, the real-time speed of the conveyor belt and the image time stamp.

[0030] In a second aspect, a method for detecting tearing of a mining conveyor belt is provided. The method is based on the above-mentioned system and comprises:

[0031] Dynamically monitor the real-time belt surface inclination angle of a conveyor belt of a mining belt conveyor; based on the real-time belt surface inclination angle and the camera array pitch angle adjustment strategy, control the camera array to adjust to the target pitch angle for shooting;

[0032] converting an original image captured by the camera array into a plurality of grayscale images, performing splicing and fusing the plurality of grayscale images to generate a panoramic image, performing edge enhancement processing on the panoramic image to obtain an enhanced image, extracting connected domain closed contours from the enhanced image, and performing morphological closing operation fusion on adjacent closed contours whose distances meet a first preset condition; and

[0033] Calculate the area of ​​the fused contour, the angle between the main axis direction of the fused contour and the running direction of the conveyor belt, and the average edge gradient of the fused contour. When the area, angle and average edge gradient of the fused contour meet the second condition, it is determined that the conveyor belt is torn.

[0034] In a third aspect, an electronic device is provided, comprising: a processor, and a memory coupled to the processor, the memory being used to store a computer program; and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the method as any possible implementation in the second aspect.

[0035] In a fourth aspect, a computer-readable storage medium is provided, comprising a computer program or instructions, which, when executed on a computer, causes the computer to execute the method of any possible implementation of the second aspect.

[0036] In a fifth aspect, a computer program product is provided, comprising: a computer program or instructions, which, when the computer program or instructions are run on a computer, causes the computer to execute the method of any possible implementation of the second aspect.

[0037] Based on the above technical solution, a mining conveyor belt tear detection system including a camera array, a gyroscope, a control module, an image processing module and a detection module was constructed. The camera array, gyroscope and other sensors were arranged at appropriate positions. The image processing module performed grayscale conversion, splicing and fusion, and edge enhancement on the captured images, and performed corresponding contour extraction and fusion. Then, the detection module calculated the area, angle with the running direction of the conveyor belt, and edge gradient mean based on the fused contour. When the calculation result meets the conditions, it is judged that the conveyor belt is torn. In this way, the specific tear position of the conveyor belt can be detected in real time and at a fixed point, meeting the real-time and accurate detection and early warning requirements, thereby indirectly improving the production efficiency of the mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 This is a flow chart of a method for visually detecting tearing of a mining conveyor belt provided in an embodiment of the present application;

[0040] Figure 2 Schematic diagram of a mining transmission device including a mining transmission belt provided in an embodiment of the present application;

[0041] Figure 3 This is a schematic diagram of the relative position relationship between the mining conveyor belt, rollers and camera provided in an embodiment of the present application;

[0042] Figure 4 Schematic diagram of the relative position relationship between the roller and the camera provided in an embodiment of the present application;

[0043] Figure 5 This is a schematic diagram of the camera installation structure provided in an embodiment of the present application;

[0044] Figure 6Schematic diagram of the relative position relationship between the camera and the light source provided in the embodiment of the present application;

[0045] Marking instructions: 1. Roller; 2. Belt; 3. Camera; 4. Roller frame; 5. Hinge; 6. Sliding base; 7. Camera slide rail; 8. Light source base; 9. Mobile light source. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0047] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0049] The embodiments of the present application propose a system and method for visual detection of tearing in mining conveyor belts, aiming to provide a solution that does not rely on large-scale training data, has strong adaptability and high real-time performance.

[0050] ‌Firstly‌, such as Figure 1 As shown, the mining conveyor belt tear visual detection system includes: a camera array arranged at the intervals between the mining belt conveyor rollers;

[0051] Gyroscope, used to dynamically monitor the real-time belt inclination of mining belt conveyors;

[0052] A control module, configured to control the camera array to adjust to a target pitch angle for shooting based on the real-time belt plane inclination angle and the camera array pitch angle adjustment strategy;

[0053] an image processing module, configured to convert an original image captured by the camera array into a plurality of grayscale images, perform stitching and fusing of the plurality of grayscale images to generate a panoramic image, perform edge enhancement processing on the panoramic image to obtain an enhanced image, extract connected domain closed contours from the enhanced image, and perform morphological closing operation fusion on adjacent closed contours whose distances meet a first preset condition; and

[0054] The detection module is used to calculate the area of ​​the fused contour, the angle between the main axis direction of the fused contour and the running direction of the conveyor belt, and the average edge gradient of the fused contour. When the area, angle and average edge gradient of the fused contour meet the second condition, it is determined that the conveyor belt is torn.

[0055] Specifically, industrial cameras are used to connect into a multi-camera splicing array to photograph the bottom surface of the conveyor belt of the mining belt conveyor.

[0056] The camera array can be set at the intervals between the rollers of the mining belt conveyor, such as Figure 2-5 shown.

[0057] Deploy a multi-camera array with adjustable angles at the intervals between the belt conveyor rollers, and dynamically adjust the camera pitch angle according to the belt inclination to ensure complete coverage of the belt bottom surface. Figure 6 As shown, the camera can be slidably mounted on the slide rail via a movable base. Figure 5 As shown, the slide rails can be hinged. The camera is movably assembled with the movable base via a rotating structure. These components can be equipped with a drive element for controlled movement.

[0058] This embodiment also provides a light source transmitter, which uses a circularly polarized light source and is installed adjacent to the camera.

[0059] Second, as Figure 1 As shown, the visual detection method for tearing of a mining conveyor belt is based on the above system, and the method includes:

[0060] Step S1: Obtain pictures of the belt conveyor during operation.

[0061] Specifically, based on the running speed of the belt, the image acquisition frequency of the industrial camera can be dynamically adjusted to capture multiple sections of the bottom surface of the belt.

[0062] Step S2: stitch the images acquired by the camera array.

[0063] Specifically, the image stitching method includes: extracting SIFT feature points from adjacent images and performing bidirectional matching, wherein the feature extraction is specifically to detect extreme points through a Gaussian difference pyramid to generate a 128-dimensional feature vector containing position / scale / direction information; the bidirectional matching is specifically to first find the nearest neighbor in image B based on the features of image A, and then reversely verify to ensure the uniqueness of the match; the RANSAC algorithm is used to eliminate incorrect matching points and solve the homography matrix H, specifically to randomly select 4 pairs of matching points to calculate the initial homography matrix H, calculate the reprojection error of all matching points after transformation by H, retain the inliers with an error less than a threshold (3 pixels), iterate 2500 times, and select the homography matrix H with the most inliers as the final required homography matrix; based on the iteratively selected final homography matrix, a weighted fusion algorithm is applied to eliminate stitching gaps, specifically to use linear gradient weights to smoothly transition from the edge area to the center, and to use multi-band fusion to fuse different frequency bands of the image pyramid separately to avoid misalignment of low-frequency information and generate a seamless panoramic image.

[0064] Step S3: Using geometric correction technology, the acquired curved surface image is converted into a straight surface.

[0065] Step S4: Convert the image into a grayscale image, calculate the second-order derivative of the grayscale image, and obtain the image contour details.

[0066] Specifically, ‌normalization and Gaussian smoothing‌: After mapping the image to the range [0,255], the grayscale image conversion is completed. The specific formula is: , where I is the pixel matrix of the original image, containing the grayscale values ​​of all pixels, and Grayscale is the grayscale conversion operation. is the converted image, and its value range is [0,255]. The specific operation of the function is , where Min(I) is the minimum grayscale value of the image pixel (i.e. the minimum value in the matrix), and max(I)‌ is the maximum grayscale value of the image pixel (i.e. the maximum value in the matrix). Gaussian smoothing is performed, and the Gaussian kernel used is , where σ is the smoothing intensity and x,y are the pixel positions in the digital image.

[0067] ‌Second-order derivative edge detection‌: grayscale image after Gaussian filtering Apply the following Laplace operator to get the second-order derivative contour details: , where i and j are the offsets of x and y, and K is the Laplace kernel.

[0068] Step S5: Perform grayscale transformation on the second-order derivative contour detail image and use median filtering to smooth the contour details.

[0069] Specifically, grayscale transformation enhancement: piecewise linear transformation is used to enhance edge contrast: , where k is the control slope, θ is the threshold, S is the second-order contour detail map, T(S) is the piecewise linear transformation function, and E is the grayscale image. The sigmoid function is used to enhance edge regions (preserve high values) and suppress non-edge regions (compress low values).

[0070] Before grayscale transformation and enhancement, corresponding normalization and Gaussian filtering can also be performed.

[0071] Normalize the second-order derivative contour details: , map the second-order derivative to [0, 255] to facilitate subsequent operations, min() is the minimum grayscale value of the image pixel, max() is the maximum grayscale value of the image pixel, L is the second-order contour detail map, and N() is the normalized result.

[0072] Gaussian kernel: .

[0073] Step S6: Binarize the image and find the contour.

[0074] Specifically, C=FindCountours(B) extracts the total number of closed contours in the binary image based on connected domain analysis. , B is the digital image after the binarization operation, FindContours() represents the contour search operation, and the specific operation is to use the Suzuki-Abe contour algorithm for topological contour analysis.

[0075] Step S7: Screening the contours that meet the tearing characteristics through contour analysis and region fusion.

[0076] Specifically, the contour fusion method includes: filtering the small contours using the following formula: , where Area( ) represents the total set of all identified contours, Represents the contour area threshold, Φ represents the threshold screening mechanism, removes noise contours with an area smaller than the threshold or an aspect ratio larger than the threshold, and selects all remaining contours. Based on the morphological closing operation, the merge distance is less than The remaining adjacent small contours have been framed to form a complete edge, and the merging algorithm is as follows: . Among them, the contour area is calculated and aspect ratio , remove or The noise profile of represents the distance threshold, Indicates the aspect ratio threshold.

[0077] Step S8: Check the constraints: 1. Using HSL color space analysis, the lightness value (L) of the cracked area should be 35% ± 5% lower than the baseline value (the baseline value is the average of the surrounding normal area); 2. Based on morphological feature detection, ensure that the contour continuity length is ≥ 300 mm (to filter out small scratches shorter than the roller spacing); 3. Color saturation (S) must be less than 15%, consistent with the low saturation characteristic caused by ash deposition; 4. The standard deviation of the main axis angle is less than 8° (to ensure linear extension characteristics); 5. The fractal dimension is less than 1.25 (to exclude stains that spread in a dendritic manner).

[0078] Step S9: Determine whether there is a matching contour, if so, execute step S10, otherwise execute step S1.

[0079] Specifically, the conditions for triggering the alarm are:

[0080] Condition 1: Contour area after fusion ;in is the contour area after fusion, It is the contour area threshold set in advance.

[0081] Condition 2: Angle between the main axis direction of the profile and the running direction of the belt ;in is the minimum threshold of the set angle, is the maximum threshold.

[0082] Condition 3: Contour edge gradient mean ;in is the actual contour edge gradient, is the gradient threshold set.

[0083] Step S10: Alarm and record the tearing position, and stop the belt conveyor.

[0084] Specifically, when recording the tearing position, the tearing position is calibrated jointly by the encoder and the image timestamp: ,in is the real-time belt speed, is the encoder reference time, The alarm trigger time.

[0085] In specific applications, the specific methods for dynamically adjusting the pitch angle of the camera include: using a gyroscope to monitor the inclination of the belt conveyor in real time, generating an angle compensation signal to drive the hinge motor, and adjusting the pitch angle of the camera array to the target angle. , satisfying the following constraints: .in, is the target coverage angle, is the inclination angle measured by the gyroscope, k is the proportional coefficient, ensuring that the viewing angle covers the full width of the belt, The current pitch angle of the camera.

[0086] The light source transmitter uses a circular polarized light source, which is installed close to the camera position and can be automatically moved to a position by a slide rail to meet the following requirements: in, is the position of the circularly polarized light source on the slide rail, is the belt width, and α is the divergence angle of the light source to eliminate the interference of reflections on the metal surface.

[0087] The advantages of the embodiments of the present application are mainly as follows:

[0088] 1. Environmental Robustness: The system uses a circularly polarized light source to suppress interference from metal surface reflections. Combined with a dynamic threshold algorithm, it automatically adapts to complex working conditions such as oil and dust on the belt surface, effectively eliminating image noise and improving the stability and accuracy of tear detection. Even under extreme conditions with a stain coverage rate of up to 30%, it can still maintain a detection rate of over 95%.

[0089] 2. Tilt Angle Versatility: The system uses an articulated camera array and gyroscope tilt feedback technology to adjust the camera pitch angle in real time (covering a tilt range of -30° to +45°). This allows it to adapt to the complex, tilted and undulating conveyor layouts underground without manual intervention, reducing equipment installation and commissioning time by over 80%.

[0090] 3. Real-time performance: Through a multi-stage image processing pipeline and FPGA hardware acceleration technology, the delay of the entire process of image acquisition, stitching, and analysis is compressed to less than 200ms, which is 5 times faster than traditional CPU solutions. This ensures that alarms can still be triggered in real time when the belt runs at high speed (5m / s), preventing the expansion of tears and causing production accidents.

[0091] 4. Precise positioning: Based on encoder pulse synchronization and image timestamp matching technology, combined with a belt speed integration algorithm, the tear position calibration error is less than ±5cm, which is 60% more accurate than traditional visual positioning methods, significantly shortening the troubleshooting time for maintenance personnel.

[0092] The present application also provides a method for detecting tearing of a mining conveyor belt, which is based on the above-mentioned system and includes:

[0093] Dynamically monitor the real-time belt surface inclination angle of a conveyor belt of a mining belt conveyor; based on the real-time belt surface inclination angle and the camera array pitch angle adjustment strategy, control the camera array to adjust to the target pitch angle for shooting;

[0094] converting an original image captured by the camera array into a plurality of grayscale images, performing splicing and fusing the plurality of grayscale images to generate a panoramic image, performing edge enhancement processing on the panoramic image to obtain an enhanced image, extracting connected domain closed contours from the enhanced image, and performing morphological closing operation fusion on adjacent closed contours whose distances meet a first preset condition; and

[0095] Calculate the area of ​​the fused contour, the angle between the main axis direction of the fused contour and the running direction of the conveyor belt, and the average edge gradient of the fused contour. When the area, angle and average edge gradient of the fused contour meet the second condition, it is determined that the conveyor belt is torn.

[0096] An embodiment of the present application also provides an electronic device, comprising: a processor, and a memory coupled to the processor, wherein the memory is used to store a computer program; and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method described in any one of the above embodiments.

[0097] The electronic device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The electronic device may include, but is not limited to, a processor and a memory.

[0098] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting various parts of the entire device using various interfaces and lines.

[0099] The memory may be used to store the computer program, and the processor implements various functions of the electronic device by running or executing the computer program stored in the memory and calling the data stored in the memory.

[0100] The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system, at least one application required for a function, and the like; the data storage area may store data generated based on the use of the mobile phone. Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0101] The embodiment of the present application also provides a storage medium, which is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. The computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0102] An embodiment of the present application further provides a computer program product, including: a computer program or instructions, which, when executed on a computer, causes the computer to execute any of the above-mentioned possible implementation methods.

[0103] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A mining conveyor belt tear detection system, characterized in that: The system comprises: A camera array is installed at the intervals between the rollers of a mining belt conveyor; Gyroscope, used to dynamically monitor the real-time belt inclination of mining belt conveyors; A control module, configured to control the camera array to adjust to a target pitch angle for shooting based on the real-time belt plane inclination angle and the camera array pitch angle adjustment strategy; An image processing module is configured to convert an original image captured by the camera array into a plurality of grayscale images; stitch and fuse the plurality of grayscale images to generate a panoramic image; perform edge enhancement processing on the panoramic image to obtain an enhanced image; extract connected domain closed contours from the enhanced image, and perform morphological closing operations on adjacent closed contours whose distances meet a first preset condition; The edge enhancement process is specifically as follows: Performing grayscale mapping on the panoramic image to obtain a grayscale image; Applying the Laplace operator to perform second-order derivative edge detection on the grayscale image to obtain the second-order derivative; Normalizing the second-order derivative to obtain a normalized image; Performing Gaussian smoothing on the normalized image to obtain a smoothed image; Performing grayscale transformation on the smoothed image to enhance edge areas and suppress non-edge areas, thereby obtaining an enhanced image; The extraction of the connected domain closed contour is specifically as follows: Binarizing the enhanced image to obtain a binarized image; and The closed contour in the binary image is extracted based on a connected domain analysis of the binary image; the connected domain analysis adopts the following check constraints: Based on morphological feature detection, the continuous length of the contour is guaranteed to be ≥300mm; the color saturation is less than 15%; the standard deviation of the main axis angle is less than 8°; and the fractal dimension is less than 1.

25. The detection module is used to calculate the area of ​​the fused contour, the angle between the main axis direction of the fused contour and the running direction of the conveyor belt, and the average edge gradient of the fused contour. When the area, angle and average edge gradient of the fused contour meet the second condition, it is determined that the conveyor belt is torn.

2. The system according to claim 1, wherein The system further comprises: a circularly polarized light source, wherein the installation position of the circularly polarized light source satisfies: ,in, is the belt width, and α is the divergence angle of the light source to eliminate the interference of reflections on the metal surface.

3. The system according to claim 1, wherein: The camera array pitch angle adjustment strategy is: ,in, is the target inclination angle, is the real-time belt surface inclination angle, k is the proportional coefficient, ensuring that the viewing angle covers the full width of the belt. is the current pitch angle of the camera array, is the target pitch angle.

4. The system according to claim 1, wherein The image processing module is specifically used for: Extract SIFT feature points of adjacent grayscale images and perform bidirectional matching, and use the RANSAC algorithm to eliminate mismatched points; Solve the matched homography matrix; as well as Based on the homography matrix, a weighted fusion algorithm is applied to eliminate stitching gaps to generate the panoramic image.

5. The system according to claim 1, wherein: The image processing module is further configured to: Calculating the closed contour area or the closed contour aspect ratio; and When the closed contour area or the closed contour aspect ratio meets a third preset condition, the noise contour is removed.

6. The system according to claim 1, wherein: The detection module is specifically used for: The tearing position of the conveyor belt is calibrated jointly by the encoder reference time, the real-time speed of the conveyor belt and the image time stamp.

7. A method for detecting tearing of a mining conveyor belt, characterized in that: The method is based on the system according to any one of claims 1 to 6, and the method comprises: Dynamically monitor the real-time belt surface inclination angle of a conveyor belt of a mining belt conveyor; based on the real-time belt surface inclination angle and the camera array pitch angle adjustment strategy, control the camera array to adjust to the target pitch angle for shooting; converting an original image captured by the camera array into a plurality of grayscale images, performing splicing and fusing the plurality of grayscale images to generate a panoramic image, performing edge enhancement processing on the panoramic image to obtain an enhanced image, extracting connected domain closed contours from the enhanced image, and performing morphological closing operation fusion on adjacent closed contours whose distances meet a first preset condition; and Calculate the area of ​​the fused contour, the angle between the main axis direction of the fused contour and the running direction of the conveyor belt, and the average edge gradient of the fused contour. When the area, angle and average edge gradient of the fused contour meet the second condition, it is determined that the conveyor belt is torn.

8. An electronic device, characterized in that: The electronic device includes: a processor, and a memory coupled to the processor, The memory is used to store computer programs; and The processor is configured to execute the computer program stored in the memory, so that the electronic device executes the method as claimed in claim 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a computer program or instructions, which, when executed on a computer, causes the computer to execute the method according to claim 7 .

Images