Intelligent inspection system and method for coal conveyor belt based on machine vision

Abstract

The present invention discloses an intelligent inspection system and method for a coal conveyor belt based on machine vision, and belongs to the field of non-destructive testing. The present invention obtains the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers by means of a position sensor installed on the side of each belt segment, imports the obtained complete image of the coal conveyor belt into a coal conveyor belt image abnormality analysis strategy to perform coal conveyor belt image abnormality analysis, imports the obtained swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers into an offset abnormality analysis strategy to perform offset abnormality analysis, calculates the coal conveyor belt danger value based on the obtained coal conveyor belt image abnormality analysis results and the offset abnormality analysis results, performs a coal conveyor belt danger warning based on the calculated coal conveyor belt danger value, comprehensively analyzes the operation data and image data of the coal conveyor belt through machine vision technology, and improves the accuracy and efficiency of abnormality analysis during the operation of the coal conveyor belt.

Description

Technical Field

[0001] The invention belongs to the field of nondestructive testing, and specifically relates to a coal conveyor belt intelligent inspection system and method based on machine vision. Background Art

[0002] The existing intelligent inspection system for coal conveyor belts is mainly used as a mobile monitoring platform. Its main function is to use mobile robots as carriers, integrate sensors such as cameras and infrared cameras, collect information such as on-site environmental videos and temperature, and rely on backstage personnel to continuously check monitoring videos and return data from the site to discover on-site problems. Affected by the subjective factors of backstage personnel, the system has low reliability and poor real-time performance, making it difficult to avoid and respond to safety accidents in a timely and effective manner.

[0003] The existing inspection system has a low level of integration. Various sensors only return information, but it is difficult to realize intelligent processing and judgment of various information on site. Due to the complex working conditions on site and changes in light, the stability of general traditional visual detection algorithms is poor, and there are a large number of false alarms and missed alarms. In addition, for equipment leakage, wear and tear during the use of belts and other defects, it is necessary to adopt artificial intelligence detection technology based on deep learning, which has high technical barriers and great difficulty, and is difficult to implement in an engineering manner. As a result, the existing technology cannot use machine vision technology to conduct a comprehensive analysis of the operation data and image data of the coal conveyor belt, resulting in low accuracy and efficiency of abnormal analysis during the operation of the coal conveyor belt.

[0004] In order to solve these problems, the present application designs an intelligent inspection system and method for coal conveyor belts based on machine vision. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention proposes an intelligent inspection system and method for a coal conveyor belt based on machine vision. The present invention divides the belt into several belt segments according to their lengths. The coal conveyor belt runs at a specified conveying speed. A camera installed above the coal conveyor belt is used to take regular photos of the surfaces of all belt segments to obtain a complete image of the coal conveyor belt. The swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are obtained by a position sensor installed on the side of each belt segment. The obtained complete image of the coal conveyor belt is imported into a coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis. The obtained swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are imported into an offset anomaly analysis strategy to perform offset anomaly analysis. The obtained coal conveyor belt image anomaly analysis results and offset anomaly analysis results are used to calculate the coal conveyor belt danger value. A coal conveyor belt danger warning is performed based on the calculated coal conveyor belt danger value. The operation data and image data of the coal conveyor belt are comprehensively analyzed by machine vision technology to improve the accuracy and efficiency of abnormal analysis during the operation of the coal conveyor belt.

[0006] To achieve the above object, the present invention provides the following technical solution: a coal conveyor belt intelligent inspection method based on machine vision, which includes the following specific steps:

[0007] The belt is divided into several belt segments according to its length. The coal conveyor belt runs at a specified conveying speed. The surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt.

[0008] The swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are obtained by means of a position sensor installed on the side of each belt segment;

[0009] Importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis;

[0010] The obtained swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are imported into the deviation anomaly analysis strategy to perform deviation anomaly analysis;

[0011] The obtained coal conveyor belt image anomaly analysis results and offset anomaly analysis results are used to calculate the coal conveyor belt danger value, and a coal conveyor belt danger warning is issued based on the calculated coal conveyor belt danger value.

[0012] It should be specifically explained that the belt is divided into a plurality of belt segments according to the length, the coal conveyor belt runs at a specified conveying speed, and the surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt, which includes the following specific steps:

[0013] S11, obtaining the number of pairs of conveying rollers on the transmission assembly, evenly dividing the belt into belt segments having the number of pairs of conveying rollers according to the length, and operating the coal conveying belt to run at a specified speed;

[0014] S12. Install a camera above the coal conveyor belt in advance. When the coal conveyor belt runs at a specified speed, the camera takes regular photos of the surface of all belt segments, and splices the images of the belt segments to obtain a complete image of the coal conveyor belt.

[0015] It should be specifically explained here that the importing of the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis includes the following specific contents:

[0016] S31, acquiring image data of each belt segment, and acquiring pixel data of each pixel point on the belt segment, crack length, number of cracks and maximum crack width data on the belt segment, and acquiring belt standard pixel value data, wherein the belt standard pixel value data is the average pixel value of the finished belt;

[0017] S32, obtaining pixel data of each pixel point on the belt segment and the belt standard pixel value data, substituting the pixel data of each pixel point on the belt segment and the belt standard pixel value data into the pixel abnormality coefficient calculation formula to calculate the pixel abnormality coefficient, wherein the pixel abnormality coefficient calculation formula of the i-th belt segment is: Where N is the number of pixels on the belt segment, xij is the pixel value of the jth pixel on the i-th belt segment, is the standard pixel value of the belt;

[0018] S33, obtaining the crack length, number of cracks and maximum crack width on the belt segment, and substituting the crack length, number of cracks and maximum crack width on the belt segment into the crack abnormality coefficient calculation formula to calculate the crack abnormality coefficient, wherein the crack abnormality coefficient calculation formula of the i-th belt segment is: Where T is the number of cracks on the i-th belt segment, d it is the length of the tth crack on the i-th belt segment, L it is the maximum width of the tth crack on the i-th belt segment, is the average length of the belt segment, and L is the average width of the belt segment;

[0019] S34, importing the calculated pixel anomaly coefficient and crack anomaly coefficient of the belt segment into the image anomaly value calculation formula of the belt segment to calculate the image anomaly value of the belt segment, wherein the image anomaly value calculation formula of the i-th belt segment is: Among them, a1 is the pixel abnormality coefficient ratio of the belt segment;

[0020] S35, obtaining a belt segment corresponding to the maximum image abnormality value and setting it as the central belt segment, obtaining the distance between the boundary line of each belt segment with the adjacent belt segment and far away from the central belt segment and the center line of the central belt segment, and obtaining the image abnormality value of each belt segment, substituting the image abnormality value of each belt segment and the distance between the boundary line of each belt segment with the adjacent belt segment and the center line of the central belt segment into the calculation formula of the coal conveyor belt image abnormality analysis value to calculate the coal conveyor belt image abnormality analysis value, wherein the calculation formula of the coal conveyor belt image abnormality analysis value is: Where m is the belt length, M is the number of belt segments, and C c is the image outlier value of the c-th belt segment, m c The distance between the boundary line of the cth belt segment and the adjacent belt segment and away from the central belt segment and the center line of the central belt segment;

[0021] It should be specifically explained here that the step of importing the acquired swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers into the deviation anomaly analysis strategy for deviation anomaly analysis includes the following specific steps:

[0022] S41, obtaining the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers;

[0023] S42, substituting the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers into the deviation abnormality analysis value calculation formula to calculate the deviation abnormality analysis value, wherein the deviation abnormality analysis value calculation formula is: Where Scd is the number of swings of the cth belt segment passing through the dth pair of conveyor rollers, J pcd is the amplitude of the pth swing of the cth belt segment passing through the dth pair of conveyor rollers, The closest to J within the safe swing range pcd The value of It is the maximum value of the safe swing amplitude range.

[0024] It should be specifically explained here that the calculation of the coal conveyor belt danger value using the obtained coal conveyor belt image abnormality analysis results and the offset abnormality analysis results, and the coal conveyor belt danger warning according to the calculated coal conveyor belt danger value include the following specific steps:

[0025] S51, obtaining the calculated coal conveyor belt image abnormality analysis value and offset abnormality analysis value, and substituting the obtained coal conveyor belt image abnormality analysis value and offset abnormality analysis value into the coal conveyor belt hazard value calculation formula to calculate the coal conveyor belt hazard value, wherein the coal conveyor belt hazard value calculation formula is: Among them, λ is the coefficient of the offset abnormal analysis value proportion;

[0026] S52. Compare the calculated coal conveyor belt danger value with the set coal conveyor belt danger threshold. If the obtained coal conveyor belt danger value is greater than or equal to the set coal conveyor belt danger threshold, a coal conveyor belt operation warning is issued to remind maintenance personnel to inspect and maintain the coal conveyor belt. If the obtained coal conveyor belt danger value is less than the set coal conveyor belt danger threshold, no coal conveyor belt operation warning is issued.

[0027] The intelligent inspection system for coal conveyor belt based on machine vision is realized based on the above-mentioned intelligent inspection method for coal conveyor belt based on machine vision, which specifically includes:

[0028] The image acquisition module is used to divide the belt into several belt segments according to the length. The coal conveyor belt runs at a specified conveying speed. The camera installed above the coal conveyor belt takes timed photos of the surface of all belt segments to obtain a complete image of the coal conveyor belt.

[0029] A position acquisition module, used to obtain the swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers through a position sensor installed on the side of each belt segment;

[0030] An image anomaly analysis module, used for importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis;

[0031] An offset anomaly analysis module is used to import the acquired swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers into an offset anomaly analysis strategy to perform offset anomaly analysis;

[0032] A danger warning module is used to calculate the danger value of the coal conveyor belt based on the obtained coal conveyor belt image abnormality analysis results and offset abnormality analysis results, and to issue a danger warning for the coal conveyor belt based on the calculated coal conveyor belt danger value;

[0033] The control module is used to control the operation of the image acquisition module, the position acquisition module, the image anomaly analysis module, the offset anomaly analysis module and the danger warning module.

[0034] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0035] The processor executes the above-mentioned machine vision-based intelligent inspection method for the coal conveyor belt by calling the computer program stored in the memory.

[0036] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned machine vision-based intelligent inspection method for coal conveyor belts.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention divides a belt into several belt segments according to its length, and the coal conveyor belt runs at a specified conveying speed. A camera installed above the coal conveyor belt is used to regularly shoot the surfaces of all belt segments to obtain a complete image of the coal conveyor belt. A position sensor installed on the side of each belt segment is used to obtain the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers. The obtained complete image of the coal conveyor belt is imported into a coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis. The obtained swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers are imported into an offset anomaly analysis strategy to perform offset anomaly analysis. The obtained coal conveyor belt image anomaly analysis results and offset anomaly analysis results are used to calculate the coal conveyor belt danger value. According to the calculated coal conveyor belt danger value, a coal conveyor belt danger warning is performed. The operation data and image data of the coal conveyor belt are comprehensively analyzed by machine vision technology, thereby improving the accuracy and efficiency of abnormality analysis during the operation of the coal conveyor belt. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0040] Figure 1 It is a schematic diagram of the overall process of the intelligent inspection method of the coal conveyor belt based on machine vision of the present invention;

[0041] Figure 2 It is a schematic diagram of the overall framework of the coal conveyor belt intelligent inspection system based on machine vision of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0044] Example 1

[0045] See also Figure 1 , an embodiment provided by the present invention: the technical problems solved by this embodiment are: the existing inspection system has a low degree of integration, and various sensors only realize the return of information, but it is difficult to realize the intelligent processing and judgment of various information on site; due to the complex on-site working conditions and changes in light, the general traditional visual detection algorithm has poor stability, and there are a large number of false alarms and missed alarms; and for defects such as equipment leakage, wear and tear during the use of belts, it is necessary to adopt artificial intelligence detection technology based on deep learning, which has high technical barriers and great difficulty, and is difficult to implement in an engineering manner; as a result, the existing technology cannot use machine vision technology to comprehensively analyze the operation data and image data of the coal conveyor belt, resulting in low accuracy and analysis efficiency of abnormal analysis during the operation of the coal conveyor belt;

[0046] The intelligent inspection method of coal conveyor belt based on machine vision includes the following specific steps:

[0047] The belt is divided into several belt segments according to its length. The coal conveyor belt runs at a specified conveying speed. The surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt.

[0048]

[0049]

[0050] This code is just a simple example. It just opens the camera, captures a frame of image, and displays the image. In fact, the time interval for capturing images needs to be calculated according to the length and speed of the belt, and the image needs to be processed and analyzed in order to identify abnormal conditions on the belt.

[0051] It should be specifically explained that the belt is divided into several belt segments according to its length, the coal conveyor belt runs at a specified conveying speed, and the surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt. Obtaining a complete image of the coal conveyor belt includes the following specific steps:

[0052] S11, obtaining the number of pairs of conveying rollers on the transmission assembly, evenly dividing the belt into belt segments having the number of pairs of conveying rollers according to the length, and operating the coal conveying belt to run at a specified speed;

[0053] S12, a camera is installed above the coal conveyor belt in advance, and when the coal conveyor belt runs at a specified speed, the camera takes timed shots of the surface of all belt segments, and the images of the belt segments are spliced ​​to obtain a complete image of the coal conveyor belt. It should be noted that the timed shooting here is calculated and set according to the running speed of the coal conveyor belt, the height at which the camera is installed above the coal conveyor belt, and the viewing angle of the camera, so that the coal conveyor belt runs just within the viewing angle of the camera within the interval time. The length of a belt segment is a conventional technical means in the art, and therefore will not be described in detail here;

[0054] The swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are obtained by means of a position sensor installed on the side of each belt segment;

[0055] Importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis;

[0056] In this embodiment, the acquired complete image of the coal conveyor belt is imported into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis, including the following specific contents:

[0057] S31, acquiring image data of each belt segment, and acquiring pixel data of each pixel point on the belt segment, crack length, number of cracks and maximum crack width data on the belt segment, and acquiring belt standard pixel value data, wherein the belt standard pixel value data is the average pixel value of the finished belt;

[0058] S32, obtaining pixel data of each pixel point on the belt segment and the belt standard pixel value data, substituting the pixel data of each pixel point on the belt segment and the belt standard pixel value data into the pixel abnormality coefficient calculation formula to calculate the pixel abnormality coefficient, wherein the pixel abnormality coefficient calculation formula of the i-th belt segment is: Where N is the number of pixels on the belt segment, xij is the pixel value of the jth pixel on the i-th belt segment, is the standard pixel value of the belt;

[0059] S33, obtaining the crack length, number of cracks and maximum crack width on the belt segment, and substituting the crack length, number of cracks and maximum crack width on the belt segment into the crack abnormality coefficient calculation formula to calculate the crack abnormality coefficient, wherein the crack abnormality coefficient calculation formula of the i-th belt segment is: Where T is the number of cracks on the i-th belt segment, d it is the length of the tth crack on the i-th belt segment, L it is the maximum width of the tth crack on the i-th belt segment, is the average length of the belt segment, and L is the average width of the belt segment;

[0060] S34, importing the calculated pixel anomaly coefficient and crack anomaly coefficient of the belt segment into the image anomaly value calculation formula of the belt segment to calculate the image anomaly value of the belt segment, wherein the image anomaly value calculation formula of the i-th belt segment is: Among them, a1 is the pixel abnormality coefficient ratio of the belt segment;

[0061] S35, obtaining a belt segment corresponding to the maximum image abnormality value and setting it as the central belt segment, obtaining the distance between the boundary line of each belt segment with the adjacent belt segment and far away from the central belt segment and the center line of the central belt segment, and obtaining the image abnormality value of each belt segment, substituting the image abnormality value of each belt segment and the distance between the boundary line of each belt segment with the adjacent belt segment and the center line of the central belt segment into the calculation formula of the coal conveyor belt image abnormality analysis value to calculate the coal conveyor belt image abnormality analysis value, wherein the calculation formula of the coal conveyor belt image abnormality analysis value is: Where m is the belt length, M is the number of belt segments, and C c is the image outlier value of the c-th belt segment, m c The distance between the boundary line of the cth belt segment and the adjacent belt segment and away from the central belt segment and the center line of the central belt segment;

[0062] The obtained swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are imported into the deviation anomaly analysis strategy to perform deviation anomaly analysis;

[0063] In this embodiment, the acquired swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are imported into the deviation anomaly analysis strategy to perform deviation anomaly analysis, which includes the following specific steps:

[0064] S41, obtaining the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers;

[0065] S42, substituting the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers into the deviation abnormality analysis value calculation formula to calculate the deviation abnormality analysis value, wherein the deviation abnormality analysis value calculation formula is: Where Scd is the number of swings of the cth belt segment passing through the dth pair of conveyor rollers, J pcd is the amplitude of the pth swing of the cth belt segment passing through the dth pair of conveyor rollers, The closest to J within the safe swing range pcd The value of It is the maximum value of the safe swing amplitude range;

[0066] The obtained coal conveyor belt image abnormality analysis results and offset abnormality analysis results are used to calculate the coal conveyor belt danger value, and a coal conveyor belt danger warning is issued according to the calculated coal conveyor belt danger value;

[0067] In this embodiment, it should be specifically explained that the obtained coal conveyor belt image abnormality analysis results and offset abnormality analysis results are used to calculate the coal conveyor belt danger value, and the coal conveyor belt danger warning is performed according to the calculated coal conveyor belt danger value, including the following specific steps:

[0068] S51, obtaining the calculated coal conveyor belt image abnormality analysis value and offset abnormality analysis value, and substituting the obtained coal conveyor belt image abnormality analysis value and offset abnormality analysis value into the coal conveyor belt hazard value calculation formula to calculate the coal conveyor belt hazard value, wherein the coal conveyor belt hazard value calculation formula is: Among them, λ is the coefficient of the offset abnormal analysis value proportion;

[0069] S52, comparing the calculated coal conveyor belt danger value with the set coal conveyor belt danger threshold value, if the obtained coal conveyor belt danger value is greater than or equal to the set coal conveyor belt danger threshold value, a coal conveyor belt operation warning is issued to remind maintenance personnel to inspect and maintain the coal conveyor belt, if the obtained coal conveyor belt danger value is less than the set coal conveyor belt danger threshold value, no coal conveyor belt operation warning is issued;

[0070] It should be noted in this embodiment that the pixel anomaly coefficient ratio of the belt segment, the offset anomaly analysis value ratio coefficient and the set coal conveyor belt danger threshold are determined in the following manner: at least five thousand sets of equipment operation data during the historical operation of the coal conveyor belt are obtained, and whether the coal conveyor belt fails is manually analyzed and determined, and the equipment operation data during the historical operation of the coal conveyor belt is substituted into the coal conveyor belt danger value calculation formula to calculate the coal conveyor belt danger value, and the calculated coal conveyor belt danger value and fault judgment result are imported into the fitting software, and the pixel anomaly coefficient ratio of the belt segment that meets the highest judgment accuracy, the offset anomaly analysis value ratio coefficient and the set coal conveyor belt danger threshold are output;

[0071] It should be noted here that the advantages of this embodiment over the prior art are as follows: the belt is divided into several belt segments according to its length, the coal conveyor belt runs at a specified conveying speed, and the surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt, and the swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are obtained by a position sensor installed on the side of each belt segment, and the obtained complete image of the coal conveyor belt is imported into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis, and the obtained swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are imported into the offset anomaly analysis strategy to perform offset anomaly analysis, and the obtained coal conveyor belt image anomaly analysis results and offset anomaly analysis results are used to calculate the coal conveyor belt danger value, and a coal conveyor belt danger warning is performed based on the calculated coal conveyor belt danger value, and the operation data and image data of the coal conveyor belt are comprehensively analyzed by machine vision technology to improve the accuracy and efficiency of abnormality analysis during the operation of the coal conveyor belt.

[0072] Example 2

[0073] like Figure 2 As shown, the intelligent inspection system for coal conveyor belt based on machine vision is realized based on the above-mentioned intelligent inspection method for coal conveyor belt based on machine vision, and specifically includes: an image acquisition module, which is used to divide the belt into a plurality of belt segments according to the length, and the coal conveyor belt runs at a specified conveying speed, and the surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt;

[0074] A position acquisition module, used to obtain the swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers through a position sensor installed on the side of each belt segment;

[0075] An image anomaly analysis module, used for importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis;

[0076] An offset anomaly analysis module is used to import the acquired swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers into an offset anomaly analysis strategy to perform offset anomaly analysis;

[0077] A danger warning module is used to calculate the danger value of the coal conveyor belt based on the obtained coal conveyor belt image abnormality analysis results and offset abnormality analysis results, and to issue a danger warning for the coal conveyor belt based on the calculated coal conveyor belt danger value;

[0078] The control module is used to control the operation of the image acquisition module, the position acquisition module, the image anomaly analysis module, the offset anomaly analysis module and the danger warning module.

[0079] Example 3

[0080] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0081] The processor executes the above-mentioned machine vision-based coal conveyor belt intelligent inspection method by calling the computer program stored in the memory.

[0082] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the machine vision-based coal conveyor belt intelligent inspection method provided in the above method embodiment.

[0083] Example 4

[0084] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0085] When the computer program runs on a computer device, the computer device executes the above-mentioned coal conveyor belt intelligent inspection method based on machine vision.

[0086] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

Claims

1. The intelligent inspection method of coal conveyor belt based on machine vision is characterized by: It includes the following specific steps: The belt is divided into several belt segments according to its length. The coal conveyor belt runs at a specified conveying speed. The surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt. The swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are obtained by means of a position sensor installed on the side of each belt segment; Importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis; The obtained swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers are imported into the deviation anomaly analysis strategy to perform deviation anomaly analysis; The obtained coal conveyor belt image abnormality analysis results and offset abnormality analysis results are used to calculate the coal conveyor belt danger value, and a coal conveyor belt danger warning is issued according to the calculated coal conveyor belt danger value; The method of importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis includes the following specific contents: S31, acquiring image data of each belt segment, and acquiring pixel data of each pixel point on the belt segment, crack length, number of cracks and maximum crack width data on the belt segment, and acquiring belt standard pixel value data, wherein the belt standard pixel value data is the average pixel value of the finished belt; S32, obtaining pixel data of each pixel point on the belt segment and the belt standard pixel value data, substituting the pixel data of each pixel point on the belt segment and the belt standard pixel value data into the pixel abnormality coefficient calculation formula to calculate the pixel abnormality coefficient, wherein the pixel abnormality coefficient calculation formula of the i-th belt segment is: Where N is the number of pixels on the belt segment, xij is the pixel value of the jth pixel on the i-th belt segment, is the standard pixel value of the belt; S33, obtaining the crack length, number of cracks and maximum crack width on the belt segment, and substituting the crack length, number of cracks and maximum crack width on the belt segment into the crack abnormality coefficient calculation formula to calculate the crack abnormality coefficient, wherein the crack abnormality coefficient calculation formula of the i-th belt segment is: Where T is the number of cracks on the i-th belt segment, d it is the length of the tth crack on the i-th belt segment, L it is the maximum width of the tth crack on the i-th belt segment, is the average length of the belt segment, is the average width of the belt segment.

2. The method for intelligent inspection of coal conveyor belt based on machine vision according to claim 1, characterized in that: The belt is divided into a plurality of belt segments according to the length, the coal conveyor belt runs at a specified conveying speed, and the surface of all belt segments is photographed at regular intervals by a camera installed above the coal conveyor belt to obtain a complete image of the coal conveyor belt, which includes the following specific steps: S11, obtaining the number of pairs of conveying rollers on the transmission assembly, evenly dividing the belt into belt segments having the number of pairs of conveying rollers according to the length, and operating the coal conveying belt to run at a specified speed; S12. Install a camera above the coal conveyor belt in advance. When the coal conveyor belt runs at a specified speed, the camera takes regular photos of the surface of all belt segments, and splices the images of the belt segments to obtain a complete image of the coal conveyor belt.

3. The method for intelligent inspection of coal conveyor belt based on machine vision according to claim 2, characterized in that: The method of importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis also includes the following specific contents: S34, importing the calculated pixel anomaly coefficient and crack anomaly coefficient of the belt segment into the image anomaly value calculation formula of the belt segment to calculate the image anomaly value of the belt segment, wherein the image anomaly value calculation formula of the i-th belt segment is: Among them, a1 is the pixel abnormality coefficient ratio of the belt segment; S35, obtaining a belt segment corresponding to the maximum image abnormality value and setting it as the central belt segment, obtaining the distance between the boundary line of each belt segment with the adjacent belt segment and far away from the central belt segment and the center line of the central belt segment, and obtaining the image abnormality value of each belt segment, substituting the image abnormality value of each belt segment and the distance between the boundary line of each belt segment with the adjacent belt segment and the center line of the central belt segment into the calculation formula of the coal conveyor belt image abnormality analysis value to calculate the coal conveyor belt image abnormality analysis value, wherein the calculation formula of the coal conveyor belt image abnormality analysis value is: Where m is the belt length, M is the number of belt segments, and C c is the image outlier value of the c-th belt segment, m c It is the distance between the boundary line of the cth belt segment and the adjacent belt segment and away from the central belt segment and the center line of the central belt segment.

4. The method for intelligent inspection of coal conveyor belt based on machine vision according to claim 3, characterized in that: The step of importing the acquired swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers into the deviation anomaly analysis strategy for deviation anomaly analysis comprises the following specific steps: S41, obtaining the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers; S42, substituting the swing amplitude and swing frequency data of each belt segment on each pair of conveying rollers into the deviation abnormality analysis value calculation formula to calculate the deviation abnormality analysis value, wherein the deviation abnormality analysis value calculation formula is: Among them, S cd is the number of swings of the cth belt segment passing through the dth pair of conveyor rollers, J pcd is the pth swing amplitude of the cth belt segment passing through the dth pair of conveyor rollers, The closest to J within the safe swing range pcd The value of It is the maximum value of the safe swing amplitude range.

5. The method for intelligent inspection of coal conveyor belt based on machine vision according to claim 4, characterized in that: The calculation of the coal conveyor belt danger value using the obtained coal conveyor belt image abnormality analysis results and the offset abnormality analysis results, and the coal conveyor belt danger warning according to the calculated coal conveyor belt danger value include the following specific steps: S51, obtaining the calculated coal conveyor belt image abnormality analysis value and offset abnormality analysis value, and substituting the obtained coal conveyor belt image abnormality analysis value and offset abnormality analysis value into the coal conveyor belt hazard value calculation formula to calculate the coal conveyor belt hazard value, wherein the coal conveyor belt hazard value calculation formula is: Among them, λ is the coefficient of the offset abnormal analysis value proportion; S52. Compare the calculated coal conveyor belt danger value with the set coal conveyor belt danger threshold. If the obtained coal conveyor belt danger value is greater than or equal to the set coal conveyor belt danger threshold, a coal conveyor belt operation warning is issued to remind maintenance personnel to inspect and maintain the coal conveyor belt. If the obtained coal conveyor belt danger value is less than the set coal conveyor belt danger threshold, no coal conveyor belt operation warning is issued.

6. A machine vision-based intelligent inspection system for coal conveyor belts, which is implemented based on the machine vision-based intelligent inspection method for coal conveyor belts as claimed in any one of claims 1 to 5, characterized in that: Specifically include: The image acquisition module is used to divide the belt into several belt segments according to the length. The coal conveyor belt runs at a specified conveying speed. The camera installed above the coal conveyor belt takes timed photos of the surface of all belt segments to obtain a complete image of the coal conveyor belt. A position acquisition module, used to obtain the swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers through a position sensor installed on the side of each belt segment; An image anomaly analysis module, used for importing the acquired complete image of the coal conveyor belt into the coal conveyor belt image anomaly analysis strategy to perform coal conveyor belt image anomaly analysis; An offset anomaly analysis module is used to import the acquired swing amplitude and swing frequency data of each belt segment on each pair of conveyor rollers into an offset anomaly analysis strategy to perform offset anomaly analysis; A danger warning module is used to calculate the danger value of the coal conveyor belt based on the obtained coal conveyor belt image abnormality analysis results and offset abnormality analysis results, and to issue a danger warning for the coal conveyor belt based on the calculated coal conveyor belt danger value; The control module is used to control the operation of the image acquisition module, the position acquisition module, the image anomaly analysis module, the offset anomaly analysis module and the danger warning module.

7. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the machine vision-based intelligent inspection method for coal conveyor belts as described in any one of claims 1 to 5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the intelligent inspection method for coal conveyor belts based on machine vision as described in any one of claims 1 to 5.

Images