Method, device, system, equipment and medium for detecting tear of conveyor belt

Abstract

This application discloses a method, apparatus, system, electronic device, and readable storage medium for detecting tears in conveyor belts, applicable to the field of material handling technology. The method includes acquiring a binary laser image of the laser beam projection area on the conveyor belt to be inspected; determining the highest position value of the laser beam in the binary laser image based on the horizontal projection data of the binary laser image; cropping the binary laser image based on the highest position value and a laser width threshold to obtain a target laser image by removing image blocks corresponding to the torn area of ​​the conveyor belt in the binary laser image. The tear condition of the conveyor belt is determined based on the target value distribution in the vertical projection data of the target laser image. This application overcomes the cumbersome drawbacks of related tear fault detection methods, achieving a simple and efficient detection of whether a conveyor belt has torn.

Description

Technical Field

[0001] This application relates to the field of material transport technology, and in particular to a method, apparatus, system, electronic device and readable storage medium for detecting tear in conveyor belts. Background Technology

[0002] Belt conveyors are used by companies in various industries such as ports, metallurgy, mining, chemicals, petroleum, power plants, and building materials to transport materials, especially long-distance, high-power, high-capacity, and high-speed belt conveyors. A belt conveyor is a widely used type of belt conveyor, consisting of a frame, conveyor belt, belt rollers, tensioning device, and transmission device. The conveyor belt connects the drive unit and the transported materials. Its main material is rubber, but to increase its load-bearing capacity, different core ropes of different materials, such as synthetic fiber core belts, ordinary canvas core belts, or steel cord core belts, are often threaded through it during production. In actual production, conveyor belts can be punctured by sharp objects or deviate from their designated path. If these abnormalities are not detected in time, large-scale tearing of the conveyor belt can cause cargo to spill, paralyzing the entire belt conveyor. In severe cases, it can even cause injuries or fatalities to inspection personnel, resulting in significant economic losses. Therefore, tear detection of conveyor belts is necessary to ensure the safe and stable operation of belt conveyors.

[0003] Current technologies for conveyor belt tear detection involve capturing images of the laser stripe area with a camera, extracting parameters such as laser intensity and curvature, and then using image processing methods combined with machine learning algorithms to train a tear fault detection model. This model is then used to identify conveyor belt tears. However, the detection accuracy of the model trained using machine learning algorithms depends on the size of the training samples; higher accuracy requires a larger training sample size. Large-scale training samples, however, require significant manpower and time for annotation. Overall, this is not a simple or efficient method for conveyor belt tear detection.

[0004] Therefore, a simple and efficient way to detect whether a conveyor belt has torn is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] This application provides a method, apparatus, system, electronic device, and readable storage medium for detecting tears in conveyor belts, which can simply and efficiently detect whether a conveyor belt has torn.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] This application provides a method for detecting tearing in conveyor belts, including:

[0008] Obtain a binary image of the laser beam projection area on the belt to be inspected;

[0009] Based on the horizontal projection data of the laser binary image, determine the highest position value of the laser ray in the laser binary image;

[0010] The laser binary image is cropped based on the highest position value and the laser width threshold to obtain the target laser image, so as to remove the image block in the laser binary image corresponding to the torn area of ​​the belt to be detected;

[0011] The tear condition of the belt to be detected is determined based on the distribution of target values ​​in the vertical projection data of the target laser image; the target value is determined by the pixel value of the pixel point that is not the laser ray in the binary laser image.

[0012] Optionally, acquiring the binary image of the laser beam projection area on the belt to be detected includes:

[0013] The original image of the belt to be detected is obtained, and the ROI region is extracted from the original belt image to obtain the target belt image;

[0014] Based on the color characteristics of the laser beam, the laser image of the laser beam projection area is extracted from the target belt image;

[0015] The laser image is binarized based on the laser color distribution area to obtain a laser binary image.

[0016] Optionally, after acquiring the binary image of the laser beam projection area on the belt to be detected, the method further includes:

[0017] If the angle between the laser line in the binary laser image and the target coordinate axis satisfies the preset tilt condition, then the binary laser image is fitted, and the tilt angle value of the laser line is determined based on the fitting result.

[0018] The laser binary image is tilted based on the tilt angle value, and the corrected image is used as the laser binary image.

[0019] Optionally, cropping the binary laser image based on the highest position value and the laser width threshold to obtain the target laser image includes:

[0020] The laser width threshold is determined based on the width of the laser beam, and the target height range is determined based on the highest position value and the laser width threshold.

[0021] Remove pixels in the binary laser image whose ordinate values ​​are not within the target height range to obtain the target laser image.

[0022] Optionally, determining the highest position value of the laser ray in the laser binary image based on the horizontal projection data of the laser binary image includes:

[0023] The binary laser image is then subjected to horizontal projection processing to obtain horizontal projection data;

[0024] The maximum value in the horizontal projection data is taken as the highest position value of the laser ray in the binary laser image.

[0025] Optionally, after determining the tear condition of the belt to be detected based on the target value distribution in the vertical projection data of the target laser image, the method further includes:

[0026] If a target value exists in the vertical projection data of the target laser image, the tear area of ​​the belt to be detected is determined according to the pixel points corresponding to each target value in the vertical projection data.

[0027] The pixel corresponding to the first target value in the vertical projection data is taken as the tear position, and the total number of consecutively appearing target values ​​is counted.

[0028] The tear width of a single frame image is calculated based on the actual distance represented by each pixel and the total number of pixels.

[0029] Another aspect of this application provides a tear detection device for a conveyor belt, comprising:

[0030] The image data acquisition module is used to acquire a binary image of the laser beam projection area on the belt to be inspected;

[0031] The horizontal projection processing module is used to determine the highest position value of the laser ray in the laser binary image based on the horizontal projection data of the laser binary image;

[0032] The tear region removal module is used to crop the laser binary image based on the highest position value and the laser width threshold to obtain the target laser image, so as to remove the image block in the laser binary image corresponding to the tear region of the belt to be detected;

[0033] The belt tear detection module is used to determine the tear condition of the belt to be detected based on the target value distribution in the vertical projection data of the target laser image; the target value is determined by the pixel value of the pixel point that is not the laser ray in the laser binary image.

[0034] This application also provides an electronic device including a processor for executing a computer program stored in a memory to implement the steps of the conveyor belt tear detection method as described in any of the preceding claims.

[0035] This application also provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the conveyor belt tear detection method as described in any of the preceding claims.

[0036] Finally, this application also provides a tear detection system for conveyor belts, including a laser, an image acquisition component, and an image processing server;

[0037] The laser and the image acquisition component are installed between the carrying belt and the return belt, facing the back of the conveyor belt;

[0038] The laser is used to project laser beams onto the return conveyor belt;

[0039] The image acquisition component is used to acquire images of the return conveyor belt and transmit the images of the return conveyor belt to the image processing server;

[0040] The image processing server is used to implement the steps of the conveyor belt tear detection method as described in any of the preceding claims by executing a computer program.

[0041] The advantage of the technical solution provided in this application is that by utilizing the discontinuity of the belt surface after a belt tear, and by combining the laser color space distribution with horizontal and vertical projection processing of the laser image, image data reflecting whether the laser line is continuous can be obtained. Based on the continuity of the laser line, it is possible to effectively identify whether the conveyor belt has torn. The entire detection process is simple, and it can ensure online and efficient detection of conveyor belt tearing faults, making it more practical.

[0042] Furthermore, this application also provides a corresponding implementation device, system, electronic device, and readable storage medium for the tear detection method of conveyor belts, which further makes the method more practical. The device, system, electronic device, and readable storage medium have corresponding advantages.

[0043] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1A flowchart illustrating a method for detecting tearing of a conveyor belt provided in this application;

[0046] Figure 2 This application provides a schematic diagram of a laser binary image in an exemplary embodiment;

[0047] Figure 3 Provide the corrected version for this application Figure 2 A schematic diagram of the horizontal projection of a binary laser image;

[0048] Figure 4 Provided for this application the corrected Figure 2 A schematic diagram of cropping a binary laser image;

[0049] Figure 5 Provided for this application Figure 2 A schematic diagram of horizontal correction for a binary laser image;

[0050] Figure 6 A structural diagram of one specific embodiment of the conveyor belt tear detection device provided in this application;

[0051] Figure 7 A structural diagram of one specific embodiment of the electronic device provided in this application;

[0052] Figure 8 A structural diagram of one specific embodiment of the conveyor belt tear detection system provided in this application;

[0053] Figure 9 A schematic diagram of monocular vision triangulation provided in this application;

[0054] Figure 10 This is a structural diagram of another specific embodiment of the conveyor belt tear detection system provided in this application. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0056] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may include steps or units not listed. Various non-limiting embodiments of this application are described in detail below.

[0057] First see Figure 1 , Figure 1 A flowchart illustrating a method for detecting tearing of a conveyor belt provided in this application. This application may include the following:

[0058] S101: Obtain the binary image of the laser beam projection area on the belt to be inspected.

[0059] In this step, the conveyor belt to be inspected is the one that needs to be tested for tearing. A laser emits laser beams towards the conveyor belt, and an image acquisition device captures an image of the belt. Since this application is based on the phenomenon that the conveyor belt surface becomes discontinuous after a tear, the tearing fault can be detected by detecting whether the laser beam is continuous. Accordingly, the image processed in the entire tear detection process is the image of the laser beam projection area on the belt to be inspected. The laser binary image is obtained by binarizing the image of the belt to be inspected captured by the image acquisition device, which contains the laser beam. Figure 2 As shown. This step does not impose any limitations on how to select the image containing the laser beam or on the binarization process of the image. Those skilled in the art can choose flexibly according to the actual situation, which will not affect the implementation of this application.

[0060] S102: Determine the highest position value of the laser beam in the laser binary image based on the horizontal projection data of the laser binary image.

[0061] In this step, the binary laser image obtained in the previous step can be horizontally projected. The pixels of each row in the horizontal direction are accumulated to obtain the horizontal projection data, which is a column vector. i represents the i-th row of the binary laser image, j is the j-th pixel in the i-th row, and w represents the total number of pixels in the i-th row of the binary laser image. The length of this column vector is equal to the height h of the image. Visualizing the horizontal projection values ​​means that a horizontal projection image can be drawn based on the horizontal projection data, such as... Figure 3 As shown, as a simple method, the maximum value in the horizontal projection data can be directly used as the highest position value of the laser beam in the binary laser image.

[0062] S103: The binary laser image is cropped based on the highest position value and the laser width threshold to obtain the target laser image, so as to remove the image block in the binary laser image corresponding to the torn area of ​​the belt to be detected.

[0063] To accurately extract laser beam image blocks from a binary laser image, the image can be cropped. After determining the highest position of the laser beam in the binary laser image in the previous step, the maximum possible width of the laser beam is determined based on empirical values ​​or the slope of the horizontal projection of the binary laser image—this is the laser width threshold in this step. The binary laser image is then cropped based on the highest position value and the laser width threshold. For ease of description, the cropped image can be defined as the target laser image. The target laser image retains only the laser beam image blocks as much as possible; ideally, background and torn areas will be removed. The cropped target laser image is... Figure 4 The image within the frame is also about to... Figure 4 The target laser image is obtained by cropping the image of the bounding box. Figure 2 For example, the white strip area in the image is the laser beam image block. The black partition on the strip area indicates that the laser beam position on the belt plane has changed due to gaps or cracks at the laser beam projection location. The white rectangle below the black partition is the image block corresponding to the torn area of ​​the conveyor belt. In this way, the continuity of the laser beam in the target laser image can be analyzed simply and efficiently.

[0064] S104: Determine the tear condition of the belt to be inspected based on the target value distribution in the vertical projection data of the target laser image.

[0065] The image processing object targeted in the aforementioned steps is a binary laser image. Since it is a binary image, the pixel values ​​of the laser image pixels fall into only two categories: the pixel values ​​corresponding to the laser beam and the pixel values ​​corresponding to non-laser beam pixels. If all pixel values ​​in a column of the target laser image are non-laser beam pixels, then that column corresponds to a tear in the conveyor belt. Therefore, this embodiment can identify the tear location based on the distribution of the target values. The target value is determined by the pixel values ​​corresponding to non-laser beam pixels. For example, the target value can be the sum of multiple non-laser beam pixel values; the specific number can be determined based on the actual situation, as long as the target value reflects that the column consists entirely of non-laser beam pixels. To facilitate calculation, the pixel values ​​corresponding to non-laser beam pixels are generally set to 0, while the pixel values ​​corresponding to laser beam pixels are not 0. Correspondingly, the target value can be 0. This step performs vertical projection processing on the target laser image, that is, summing up the pixel values ​​of each column of the target laser image to obtain vertical projection data, i.e., obtaining a row vector. i represents the i-th pixel in the j-th column of the binary laser image, j is the j-th column of the binary laser image, and h thresh This represents the laser width threshold. Since the aforementioned steps remove pixel values ​​from the belt tear area through horizontal projection, if the target value appears in the vertical projection data after vertical projection, the pixel corresponding to that target value is... Figure 2 The black-blocked pixels in the image represent the locations where the laser beam changes when it encounters a crack or tear in the conveyor belt. Therefore, the presence of a target value in the vertical projection data of the target laser image can be used to detect whether the conveyor belt has a tearing fault. If a tearing fault occurs, the tearing area and size of the conveyor belt can be determined further based on the distribution of the target value in the vertical projection data of the target laser image.

[0066] The technical solution provided in this application utilizes the discontinuity of the conveyor belt surface after tearing. Based on the laser color space distribution and combined with horizontal and vertical projection processing of the laser image, image data reflecting the continuity of the laser line can be obtained. The continuity of the laser line can effectively identify whether a tear has occurred in the conveyor belt. The entire detection process is simple, ensuring online and efficient detection of conveyor belt tearing faults, making it more practical. The entire detection process has low dependence on computing hardware, effectively reducing the excessive use of computing resources.

[0067] It should be noted that there is no strict order of execution for the steps in this application. As long as they conform to a logical order, these steps can be executed simultaneously or in a certain preset order. Figure 1 This is just an illustrative example and does not mean that this is the only possible execution order.

[0068] In the above embodiments, there is no limitation on how to obtain the binary laser image. This embodiment also provides an optional method for obtaining the binary laser image, which may include the following:

[0069] The original image of the belt to be detected is obtained, and the ROI region is extracted from the original belt image to obtain the target belt image; based on the color characteristics of the laser light, the laser image of the laser light projection area is extracted from the target belt image; the laser image is binarized according to the laser color distribution area to obtain the laser binary image.

[0070] In this embodiment, an image acquisition device, such as a visible light camera, installed on the belt conveyor acquires an original belt image. Based on prior knowledge, a preliminary ROI (region of interest) extraction is performed on the original belt image. In this embodiment, the ROI is the conveyor belt area containing the laser beam projection area. The resulting image is a color image, including three color channels: RGB (red, green, blue). The image size is h×w, where h represents the height of the image and w represents the width. Then, the laser region is extracted based on the laser color characteristics of the laser beam emitted by the laser installed on the belt conveyor. For example, the laser color distribution area [B] can be obtained first based on prior knowledge. low G low ,R low ]、[B high G high ,R high ], B low G represents the maximum pixel value of the blue pixel. low R is the minimum pixel value of the green pixel. low B is the minimum pixel value of the red pixel. high G represents the maximum pixel value of the blue pixel. high R is the maximum pixel value of the green pixel. high This represents the maximum pixel value of the red pixels. Based on the actual application scenario, a pixel value of 1 is set for the laser beam pixels, and another pixel value of 0 is set for pixels that are not laser beams. Correspondingly, the laser image can be binarized according to the following relationship: pixels in the laser binary image that do not conform to the laser color distribution range are set to 0, and pixels that conform to the laser color distribution range are set to 1:

[0071] if p ij =1

[0072] else,p ij =0

[0073] In the formula, p ijLet be the pixel value of the pixel in the i-th row and j-th column of the binary laser image. After processing, the resulting binary laser image has the same size as the target belt image. For example, if the laser emits blue laser light, according to the BGR color space, the laser line color distribution range is (125:255, 230:255, 91:255). Similarly, converting the image to other color spaces such as HSV (hue, saturation, brightness) sets the pixel value of the laser image with a value in (125:255, 230:255, 91:255) to 1, and sets the pixel value of the laser image with a value not in (125:255, 230:255, 91:255) to 0.

[0074] As can be seen from the above, this embodiment obtains a laser binary image with better image quality and fewer interfering pixels by processing the original belt image multiple times, which is beneficial to improving the detection efficiency of subsequent tearing faults.

[0075] The above embodiments do not limit how to crop the binary laser image. In order to further reduce the background data and torn area data contained in the target laser image, based on the above embodiments, this application also provides a method for cropping a binary laser image, which may include the following:

[0076] The laser width threshold is determined based on the width of the laser beam, and the target height range is determined based on the highest position value and the laser width threshold. Pixels whose vertical coordinate values ​​in the binary laser image are not within the target height range are removed to obtain the target laser image.

[0077] To reduce data processing complexity, the laser width threshold h in this application... thresh The value can be determined based on the width parameter of the laser beam emitted by the laser and empirical knowledge. Since the laser beam in the binary laser image is concentrated in a certain area in the horizontal direction, the highest position value is the maximum value h in the horizontal projection data. max When cropping a binary laser image, only images with heights matching [h] are retained. max -h thresh ,h max +h thresh The image patch can be used to remove torn areas and background areas. The height of the cropped target laser image is 2×h. thresh , with a width of w.

[0078] Furthermore, to improve practicality and applicability to more application scenarios, based on the above embodiments, this application may also include the following:

[0079] If a target value exists in the vertical projection data of the target laser image, the tear area of ​​the belt to be detected is determined according to the pixel points corresponding to each target value in the vertical projection data; the pixel point corresponding to the first target value appearing in the vertical projection data is taken as the tear position, and the total number of consecutively appearing target values ​​is counted; the tear width of a single frame image is calculated based on the actual distance represented by each pixel and the total number.

[0080] Understandably, the target value is determined by the pixel values ​​of pixels in the binary laser image that are not laser rays. Typically, during binarization, the pixel values ​​of these pixels are set to 0. Correspondingly, the appearance of a target value of 0 in the vertical projection data indicates the presence of a tear. If a tear exists, the tear area of ​​the belt to be detected can be determined based on the pixel position corresponding to each target value. The coordinates of the first target value (e.g., 0) can be marked as the tear location, and the number of consecutive target values ​​(e.g., 0) is recorded as the tear width. With the image acquisition device installed in a fixed position, the actual distance represented by each pixel can be obtained using any existing camera calibration method. By counting the number of pixels representing the tear width, the actual tear width can be obtained.

[0081] It is understandable that if the image acquisition device has poor focusing performance, or the focal length during image acquisition is not optimal, or the laser performance is poor, the laser line in the acquired laser image will have a certain tilt, and the straightness of the laser line affects the overall detection accuracy of tear faults. To further improve the tear detection accuracy of conveyor belts, the following may be included between steps S101 and S102:

[0082] The process involves several steps: First, determining whether the angle between the laser line in the binary laser image and the target coordinate axis meets a preset tilt condition. If the angle meets the preset tilt condition, the binary laser image is fitted, and the tilt angle of the laser line is determined based on the fitting result. The binary laser image is then tilt-corrected based on this tilt angle value, and the corrected image is used as the binary laser image. If the angle between the laser line in the binary laser image and the target coordinate axis does not meet the preset tilt condition, step S102 is executed directly. In other words, if the conveyor belt tear detection system can ensure that the laser beam is horizontally imaged in the binary laser image, the correction step is unnecessary.

[0083] In this embodiment, the preset tilt condition is a standard used to determine whether the laser beam is tilted, and those skilled in the art can flexibly determine it according to the actual situation. The target coordinate axis can be a pre-specified coordinate axis in the image plane, which is related to the preset tilt condition. For example, when the angle between the laser line in the binary laser image and the x-axis exceeds 15°, the laser beam is determined to be tilted. Correspondingly, the preset tilt condition is that the angle between the laser line in the binary laser image and the x-axis is greater than 15°. For example, when the angle between the laser line in the binary laser image and the y-axis is less than 85°, the laser beam is determined to be tilted. Correspondingly, the preset tilt condition is that the angle between the laser line in the binary laser image and the y-axis is less than 85°. When the laser beam is tilted in the image, any fitting method such as the Hough line fitting algorithm can be used to fit the binary laser image to obtain the tilt angle of the laser line. The tilt angle is used to correct the tilt of the binary laser image, and the corrected binary laser image is used as the binary laser image in the subsequent S102 step. The corrected binary laser image has the same image size as the original binary laser image. For example, Figure 2 The laser beam in the binary laser image is tilted. After correction, the following is obtained: Figure 5 .

[0084] This application also provides a corresponding apparatus for the conveyor belt tear detection method, further enhancing the practicality of the method. The apparatus can be described from both a functional module perspective and a hardware perspective. The conveyor belt tear detection apparatus provided in this application is described below. This apparatus is used to implement the conveyor belt tear detection method provided in this application. In this embodiment, the conveyor belt tear detection apparatus may include or be divided into one or more program modules. These one or more program modules are stored in a storage medium and executed by one or more processors to complete the conveyor belt tear detection method disclosed in Embodiment 1. The program module referred to in this application is a series of computer program instruction segments capable of performing a specific function, which is more suitable than the program itself for describing the execution process of the conveyor belt tear detection apparatus in the storage medium. The following description will specifically introduce the functions of each program module in this embodiment. The conveyor belt tear detection apparatus described below and the conveyor belt tear detection method described above can be referred to in correspondence.

[0085] From the perspective of functional modules, see Figure 6 , Figure 6 A structural diagram of a conveyor belt tear detection device provided in this application, in one specific embodiment, shows that the device may include:

[0086] The image data acquisition module 601 is used to acquire a binary image of the laser beam projection area on the belt to be inspected.

[0087] The horizontal projection processing module 602 is used to determine the highest position value of the laser beam in the laser binary image based on the horizontal projection data of the laser binary image.

[0088] The tear region removal module 603 is used to crop the laser binary image based on the highest position value and the laser width threshold to obtain the target laser image, so as to remove the image block in the laser binary image corresponding to the tear region of the belt to be detected.

[0089] The belt tear detection module 604 is used to determine the tear condition of the belt to be detected based on the target value distribution in the vertical projection data of the target laser image; the target value is determined by the pixel value of the non-laser light pixel in the laser binary image.

[0090] Optionally, in some embodiments of this example, the image data acquisition module 601 may also be used to: acquire the original belt image of the belt to be detected, and extract the ROI region from the original belt image to obtain the target belt image; extract the laser image of the laser beam projection area from the target belt image based on the color features of the laser beam; and perform binarization processing on the laser image according to the laser color distribution area to obtain a laser binary image.

[0091] Optionally, in some other embodiments of this example, the above-mentioned device may further include a correction module, which is used to perform fitting processing on the laser binary image if the angle between the laser line in the laser binary image and the target coordinate axis satisfies a preset tilt condition, and determine the tilt angle value of the laser line according to the fitting result; perform tilt correction on the laser binary image based on the tilt angle value, and use the corrected image as the laser binary image.

[0092] Indicatively, in some other embodiments of this example, the tear region removal module 603 described above can also be used to: determine a laser width threshold based on the width of the laser beam, and determine a target height range based on the highest position value and the laser width threshold; remove pixels in the laser binary image whose vertical coordinate values ​​are not within the target height range to obtain a target laser image.

[0093] Indicatively, in some other embodiments of this example, the horizontal projection processing module 602 can also be used to: perform horizontal projection processing on the laser binary image to obtain horizontal projection data; and take the maximum value in the horizontal projection data as the highest position value of the laser ray in the laser binary image.

[0094] Optionally, in other embodiments of this example, the above-mentioned device may further include a tear width calculation module, which is used to determine the tear area of ​​the belt to be detected based on the pixels corresponding to each target value in the vertical projection data if there is a target value in the vertical projection data of the target laser image; take the pixel corresponding to the first target value in the vertical projection data as the tear position, and count the total number of consecutively appearing target values; and calculate the tear width of a single frame image based on the actual distance represented by each pixel and the total number.

[0095] The functions of each module of the conveyor belt tear detection device of this application can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can be referred to the relevant descriptions in the above method embodiments, which will not be repeated here.

[0096] As can be seen from the above, this embodiment can achieve simple and efficient detection of whether the conveyor belt has torn.

[0097] The conveyor belt tear detection device mentioned above is described from the perspective of functional modules. Furthermore, this application also provides an electronic device, which is described from the perspective of hardware. Figure 7 This is a schematic diagram of the structure of the electronic device provided in one embodiment of this application. For example... Figure 7 As shown, the electronic device includes a memory 70 for storing a computer program; and a processor 71 for executing the computer program to implement the steps of the conveyor belt tear detection method as described in any of the above embodiments.

[0098] The processor 71 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 71 may also be a controller, microcontroller, microprocessor, or other data processing chip. The processor 71 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 71 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 71 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 71 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0099] The memory 70 may include one or more computer-readable storage media, which may be non-transitory. The memory 70 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the memory 70 may be an internal storage unit of an electronic device, such as a server hard drive. In other embodiments, the memory 70 may be an external storage device of an electronic device, such as a plug-in hard drive on a server, a Smart Media Card (SMC), a Secure Digital (SD) card, or a Flash Card. Furthermore, the memory 70 may include both internal and external storage units of the electronic device. The memory 70 can be used not only to store application software and various types of data installed in the electronic device, such as code in the process of executing the conveyor belt tear detection method, but also to temporarily store data that has been output or will be output. In this embodiment, the memory 70 is used to store at least the following computer program 701, which, after being loaded and executed by the processor 71, is capable of implementing the relevant steps of the conveyor belt tear detection method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 70 may also include an operating system 702 and data 703, and the storage method may be temporary storage or permanent storage. The operating system 702 may include Windows, Unix, Linux, etc. The data 703 may include, but is not limited to, data corresponding to the tear detection results of the conveyor belt.

[0100] In some embodiments, the aforementioned electronic device may further include a display screen 72, an input / output interface 73, a communication interface 74 (or network interface), a power supply 75, and a communication bus 76. The display screen 72 and input / output interface 73, such as a keyboard, are user interfaces; optional user interfaces may also include standard wired interfaces, wireless interfaces, etc. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a display screen or display unit, used to display information processed in the electronic device and to display a visual user interface. The communication interface 74 may optionally include a wired interface and / or a wireless interface, such as a Wi-Fi interface, a Bluetooth interface, etc., typically used to establish communication connections between the electronic device and other electronic devices. The communication bus 76 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0101] Those skilled in the art will understand that Figure 7 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, such as sensors 77 that perform various functions.

[0102] The functions of each functional module of the electronic device of this application can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can be referred to the relevant descriptions in the above method embodiments, which will not be repeated here.

[0103] As can be seen from the above, this embodiment can achieve simple and efficient detection of whether the conveyor belt has torn.

[0104] It is understood that if the conveyor belt tear detection method in the above embodiments is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the related technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes: USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, removable disk, CD-ROM, magnetic disk or optical disk, and other media capable of storing program code.

[0105] Based on this, this application also provides a readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the conveyor belt tear detection method as described in any of the above embodiments.

[0106] Finally, this application also provides a tear detection system for conveyor belts; please refer to [link to relevant documentation]. Figure 8 It may include the following:

[0107] A conveyor belt tear detection system is applied to belt conveyors and may include a laser 801, an image acquisition component 802, and an image processing server 803. Inevitably, for normal operation, the laser 801, image acquisition component 802, and image processing server 803 need to be connected to a power distribution box 800. For example... Figure 9 As shown, the laser beam emitted from laser 801 strikes the surface of the conveyor belt, perpendicular to both sides of the belt. The image acquisition device 8021 in the image acquisition assembly 802, such as a camera, forms an angle with laser 801. This angle can be any angle between 15° and 90°. Utilizing the principle of monocular vision triangulation, the position of the image in the camera changes as the object's height changes. Similarly, when the conveyor belt tears, the resulting gap causes the laser beam's position on the conveyor belt plane to change. Therefore, the continuity of the laser beam can be used to identify conveyor belt tears.

[0108] In this embodiment, both the laser 801 and the image acquisition component 802 are installed between the carrying belt and the return belt of the conveyor belt, facing the back of the conveyor belt. The laser 801 is used to project laser light onto the return belt. The laser 801 can be any type of laser emitter, such as a line laser. The image acquisition component 802 is used to acquire images of the return belt and transmit these images to the image processing server 803. The image acquisition component 802 includes at least one image acquisition device 8021, such as a camera or webcam. To improve the image acquisition effect, it can also be equipped with components that can improve the image imaging effect or the image acquisition effect. The image processing server 803 is used to implement the steps of the conveyor belt tear detection method as described in any of the above embodiments by executing a computer program. The processor of the image processing server 803 has a built-in computer program that implements the steps of the conveyor belt tear detection method as described in any of the above embodiments. Alternatively, a chip or readable storage medium storing the computer program that implements the steps of the conveyor belt tear detection method as described in any of the above embodiments can be directly integrated into the image processing server 803. Neither of these methods affects the implementation of this application.

[0109] In this embodiment, the entire conveyor belt tear detection system can be installed in the middle of the belt conveyor. The image acquisition device 8021 in the laser 801 and image acquisition assembly 802 is mounted from top to bottom, such as a camera. Figure 10 As shown. Considering that the downward shooting of the image acquisition component 802 can reduce the amount of material falling onto the surface of the image acquisition component 802 and the laser 801 during belt operation, it will not affect the operation of the entire system and can also avoid increasing the maintenance workload of the entire system. In addition, considering the imaging of the laser beam, and that the accuracy of the entire tear detection method is related to the straightness of the laser line, since the return belt is not allowed to be loaded with material and is in a flat state, the image acquisition component 802 acquires the image of the surface of the return belt.

[0110] Furthermore, to improve the quality of the acquired images, the image acquisition component 802 may also include a light-reflecting plate 8022, which similarly faces downwards, i.e., towards the back of the conveyor belt. Figure 10 As shown. Without the addition of the illumination plate 8022, the camera-captured images are mostly black, with only the laser line area showing highlights. Adding the illumination plate allows the camera-captured images to clearly show the laser line and the surface texture of the belt, facilitating the operator's review of the saved fault images after system detection and alarm, and enabling direct observation of the tear area. Furthermore, to improve the stability of image acquisition quality and reduce image processing complexity, the image acquisition component 802 can be equipped with a light shield 8023, housing the illumination plate 8022, image acquisition device 8021, and laser 801 inside the light shield 8023. The light shield 8023 reduces interference from external light sources.

[0111] The functions of each module of the conveyor belt tear detection system in this embodiment of the invention can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can be referred to the relevant descriptions in the above method embodiments, which will not be repeated here.

[0112] As can be seen from the above, this embodiment can achieve simple and efficient detection of whether the conveyor belt has torn.

[0113] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the hardware disclosed in the embodiments, including devices and electronic equipment, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0114] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0115] The foregoing has provided a detailed description of a method, apparatus, system, electronic device, and readable storage medium for detecting tearing of conveyor belts. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for detecting tearing in a conveyor belt, characterized in that, include: The original image of the belt to be detected is acquired, and the ROI region is extracted from the original belt image to obtain the target belt image; based on the color characteristics of the laser light, the laser image of the laser light projection area is extracted from the target belt image; the laser image is binarized according to the laser color distribution area to obtain the laser binary image; The laser binary image is horizontally projected to obtain horizontal projection data. The horizontal projection data is obtained by accumulating the pixels of each row in the horizontal direction of the laser binary image to form a column vector. The maximum value in the horizontal projection data is taken as the highest position value of the laser ray in the laser binary image. The laser width threshold is determined based on the width of the laser beam, and the target height range is determined based on the highest position value and the laser width threshold. Pixels in the laser binary image whose vertical coordinate values ​​are not within the target height range are removed to obtain the target laser image, thereby removing the image block in the laser binary image corresponding to the torn area of ​​the belt to be detected; the target height range is [highest position value - laser width threshold, highest position value + laser width threshold]; The target laser image is vertically projected to obtain vertical projection data. The vertical projection data is obtained by accumulating the pixels of each column in the vertical direction of the target laser image to form a row vector. The tearing condition of the belt to be detected is determined according to the distribution of target values ​​in the vertical projection data of the target laser image. If the target value exists in the vertical projection data, it is determined that the belt to be detected is torn. The target value is determined by the pixel value of the pixel point that is not the laser beam in the binary laser image.

2. The method for detecting tearing of conveyor belts according to claim 1, characterized in that, After acquiring the binary image of the laser beam projection area on the belt to be detected, the process further includes: If the angle between the laser line in the binary laser image and the target coordinate axis satisfies the preset tilt condition, then the binary laser image is fitted, and the tilt angle value of the laser line is determined based on the fitting result. The laser binary image is tilted based on the tilt angle value, and the corrected image is used as the laser binary image.

3. The method for detecting tearing of conveyor belts according to claim 1 or 2, characterized in that, After determining the tear condition of the belt to be detected based on the target value distribution in the vertical projection data of the target laser image, the method further includes: If a target value exists in the vertical projection data of the target laser image, the tear area of ​​the belt to be detected is determined according to the pixel points corresponding to each target value in the vertical projection data. The pixel corresponding to the first target value in the vertical projection data is taken as the tear position, and the total number of consecutively appearing target values ​​is counted. The tear width of a single frame image is calculated based on the actual distance represented by each pixel and the total number of pixels.

4. A tear detection device for a conveyor belt, characterized in that, include: The image data acquisition module is used to acquire the original belt image of the belt to be detected, and to extract the ROI region from the original belt image to obtain the target belt image; based on the color characteristics of the laser light, to extract the laser image of the laser light projection area from the target belt image; and to perform binarization processing on the laser image according to the laser color distribution area to obtain a laser binary image. The horizontal projection processing module is used to perform horizontal projection processing on the laser binary image to obtain horizontal projection data. The horizontal projection data is obtained by accumulating the pixels of each row in the horizontal direction of the laser binary image to form a column vector. The maximum value in the horizontal projection data is taken as the highest position value of the laser ray in the laser binary image. The tear region removal module is used to determine a laser width threshold based on the width of the laser beam, and to determine a target height range based on the highest position value and the laser width threshold. It then removes pixels in the binary laser image whose ordinate values ​​are not within the target height range to obtain a target laser image, thereby removing the image block in the binary laser image corresponding to the tear region of the belt to be detected. The target height range is [highest position value - laser width threshold, highest position value + laser width threshold]. The belt tear detection module is used to perform vertical projection processing on the target laser image to obtain vertical projection data. The vertical projection data is obtained by accumulating each column of pixels in the vertical direction of the target laser image to form a row vector. Based on the distribution of target values ​​in the vertical projection data of the target laser image, the tear condition of the belt to be detected is determined. If the target value exists in the vertical projection data, it is determined that the belt to be detected has torn. The target value is determined by the pixel value of the pixel point that is not the laser ray in the binary laser image.

5. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the steps of the conveyor belt tear detection method as described in any one of claims 1 to 3.

6. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the conveyor belt tear detection method as described in any one of claims 1 to 3.

7. A tear detection system for conveyor belts, characterized in that, Includes lasers, image acquisition components, and image processing servers; The laser and the image acquisition component are installed between the carrying belt and the return belt, facing the back of the conveyor belt; The laser is used to project laser beams onto the return conveyor belt; The image acquisition component is used to acquire images of the return conveyor belt and transmit the images of the return conveyor belt to the image processing server; The image processing server is used to implement the steps of the conveyor belt tear detection method as described in any one of claims 1 to 3 by executing a computer program.

Images