Conveyor belt sweeper wear detection method, system and equipment and medium

Abstract

The invention discloses a conveyor belt sweeper wear detection method and system, equipment and a medium, and relates to the technical field of sweeper wear detection, and the method comprises the steps: obtaining an initial image and a video stream of a belt region between a sweeper and a feed opening; performing frame extraction processing on the video stream to obtain a belt area image; collecting belt area images as an image set, and calculating similarity values of all the belt area images and the initial image in sequence to obtain a calculation result; based on the calculation result, dividing the image set into a foreign matter image set and a foreign matter-free image set, and forming a data set; constructing a visual model, and training the visual model by using the data set; based on the trained visual model, processing a real-time image of a belt area between the sweeper and the discharging port to obtain a processing result; and based on the processing result, whether the sweeper is abraded or not is judged. According to the invention, the abrasion of the conveyor belt sweeper can be timely detected at low cost.

Description

Technical Field

[0001] The present invention relates to the technical field of cleaner wear detection, and in particular to a conveyor belt cleaner wear detection method, system, equipment and medium. Background Art

[0002] Sweepers, primarily made of polyurethane, are used to clean residual material from belt conveyors. Currently, the cutter heads of polyurethane sweepers are consumables and require regular inspection by maintenance personnel to monitor wear. Failure to promptly replace worn cutter heads reduces cleaning efficiency, impacting the lifespan of the conveyor belt and rollers and potentially causing system downtime. Using a sweeper equipped with additional sensors, or retrofitting an existing sweeper with a set of sensors and network transmission sensors, incurs significant costs. Summary of the Invention

[0003] In view of this, the present application provides a conveyor belt cleaner wear detection method, system, equipment and medium to achieve timely detection of conveyor belt cleaner wear at low cost.

[0004] A first aspect of the present application provides a method for detecting wear of a conveyor belt cleaner, comprising:

[0005] Obtain the initial image and video stream of the belt area between the tail roller and the discharge port of the sweeper;

[0006] Setting a time interval, performing frame extraction processing on the video stream to obtain a belt area image;

[0007] Collecting belt area images within a preset time period as an image set, and calculating similarity values between all belt area images in the image set and the initial image in sequence to obtain a calculation result;

[0008] Based on the calculation result, the image set is divided into a set of images with foreign matter and a set of images without foreign matter, wherein the set of images with foreign matter and the set of images without foreign matter constitute a data set;

[0009] Building a visual model, and training the visual model using the data set;

[0010] Based on the trained visual model, the real-time image of the belt area between the tail roller and the discharge port of the sweeper is processed to obtain the processing results;

[0011] Based on the processing result, it is determined whether the cleaner is worn.

[0012] In a possible implementation of the first aspect, an initial image and video stream of the belt area between the tail roller and the discharge port of the sweeper are obtained by a camera.

[0013] In a possible implementation of the first aspect, calculating the similarity between all belt area images in the image set and the initial image in sequence includes:

[0014]

[0015] SSIM(I1, I2) is the similarity value between the belt area image and the initial image, is the initial image mean, is the mean value of the belt area image, is the covariance between the initial image and the belt area image, is the initial image variance, is the belt area image variance.

[0016] In a possible implementation of the first aspect, dividing the image set into a set of images with foreign matter and a set of images without foreign matter based on the calculation result includes:

[0017] Setting a first threshold, and when the similarity value between the belt area image and the initial image is greater than the first threshold, classifying the corresponding belt area image into the foreign body-free image set;

[0018] When the similarity value between the belt area image and the initial image is less than or equal to the first threshold, the corresponding belt area image is classified into the foreign matter image set.

[0019] In a possible implementation of the first aspect, processing the real-time image based on the trained visual model to obtain a processing result includes:

[0020] The real-time image is input into the trained visual model for processing, and the real-time image is divided into the image set with foreign matter or the image set without foreign matter.

[0021] In a possible implementation of the first aspect, determining whether the cleaner is worn based on the processing result includes:

[0022] If the real-time image is classified into the set of images with foreign matter, it is determined that the cleaner is worn;

[0023] If the real-time image is classified into the foreign matter-free image set, it is determined that the cleaner is not worn.

[0024] A second aspect of the present application provides a conveyor belt cleaner wear detection system, comprising:

[0025] An acquisition unit, used to acquire an initial image and video stream of the belt area between the tail roller of the sweeper and the discharge port;

[0026] A video stream processing unit is used to set a time interval and perform frame extraction processing on the video stream to obtain a belt area image;

[0027] a similarity value calculation unit, configured to collect belt area images within a preset time period as an image set, and calculate similarity values between all belt area images in the image set and the initial image in sequence to obtain a calculation result;

[0028] a data set unit, configured to divide the image set into a set of images with foreign matter and a set of images without foreign matter based on the calculation result, wherein the set of images with foreign matter and the set of images without foreign matter constitute a data set;

[0029] A visual model unit, configured to construct a visual model and train the visual model using the data set;

[0030] A processing unit is used to process a real-time image of the belt area between the tail roller of the sweeper and the discharge port based on the trained visual model to obtain a processing result;

[0031] A judging unit is used to judge whether the sweeper is worn based on the processing result.

[0032] The third aspect of the present application provides an electronic device, comprising: a processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; and the memory is used to store a program, and the program is used to implement a conveyor belt cleaner wear detection method as provided in the first aspect of the present application.

[0033] A fourth aspect of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. The computer-executable instructions are used to execute a conveyor belt cleaner wear detection method as provided in the first aspect of the present application.

[0034] Compared with the prior art, the present application provides a conveyor belt cleaner wear detection method, system, equipment and medium, including: obtaining an initial image and video stream of the belt area between the tail roller and the discharge port of the cleaner, the belt area being the area after the cleaner has cleaned the belt; then obtaining a belt area image by performing frame extraction processing on the video stream of this part of the area; performing similarity calculation on the belt area image and the initial image in sequence to obtain a calculation result, wherein the initial image is an image of the cleaned belt; according to the calculation result, the belt area images in the image set are divided into a set of images with foreign matter and a set of images without foreign matter and form a data set, the set of images with foreign matter indicating that the cleaner has not cleaned cleanly, and the set of images without foreign matter indicating that the cleaner has cleaned cleanly; then constructing a visual model and using the data set for training, and then obtaining the belt image of the area in real time and inputting it into the trained visual model, outputting the processing result, and judging whether the cleaner is worn based on the processing result, that is, judging whether the belt image belongs to the set of images with foreign matter, if so, it means that the cleaner is worn, and if not, it means that the cleaner is not worn.

[0035] Its beneficial effect lies in: Based on image analysis and visual models, the determination of whether the cleaner is worn is converted to the determination of whether there are foreign objects in the cleaned belt area. If the visual model determines that there is foreign objects in the belt area after the cleaner has been cleaned, it indicates that the cleaner is worn; otherwise, it indicates that there is no wear. No modification is required to the cleaner body, and cameras are installed at the front and rear of the conveyor belt. Only the angle of the camera near the discharge port needs to be adjusted, which greatly reduces the cost of inspection while ensuring the efficiency and accuracy of inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0037] Figure 1 This is a flow chart of a method for detecting wear of a conveyor belt cleaner provided in an embodiment of the present application;

[0038] Figure 2 This is a schematic diagram of the composition of a conveyor belt cleaner wear detection system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0040] In this application, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0041] Example 1

[0042] As can be seen from the above background technology, during the use of polyurethane material cleaners, the cutter head, as a consumable part, requires regular inspection and wear by maintenance personnel. Failure to replace the worn cutter head in a timely manner will lead to reduced cleaning efficiency and the following problems: 1) The uncleaned material may contain hard particles. These particles will continuously rub against the conveyor belt surface during operation. For example, in a conveyor belt system that transports ore, hard particles such as quartz sand in the ore remain on the conveyor belt, acting like sandpaper, polishing the conveyor belt surface when the conveyor belt contacts components such as rollers and idlers. This will cause the rubber layer on the conveyor belt surface to gradually become thinner, and may even cause scratches and cracks, significantly shortening the service life of the conveyor belt. 2) The residual material on the conveyor belt surface will cause uneven weight distribution on both sides of the conveyor belt. For example, if the material on one side is not cleaned cleanly, while the other side is relatively clean, the conveyor belt will shift toward the side with more material during operation. This deviation phenomenon will further cause friction between the conveyor belt and components such as the frame and sidewalls, which will not only damage the edge of the conveyor belt, but may also cause the conveyor belt to fall off the roller, causing the conveyor belt system to shut down; 3) For the roller, residual materials will enter the gap between the roller and the conveyor belt. These materials will be crushed during the rotation of the roller, generating heat. At the same time, the accumulation of materials will cause uneven force on the roller. For example, at the driving roller of the conveyor belt, if the material is not cleaned properly, the material will accumulate on the surface of the roller. On the one hand, it will reduce the friction between the roller and the conveyor belt, causing the conveyor belt to slip; on the other hand, the material will be repeatedly crushed when the roller rotates, which can easily damage the rubber coating on the surface of the roller, thereby affecting the service life of the roller. In addition, the heat generated by the material may also cause the lubricating grease of the roller bearing to deteriorate, causing bearing damage.

[0043] In the existing technology, the monitoring of sweepers mainly relies on manual inspections or additional sensors installed on the sweepers. However, the manual inspection method relies on manual experience and operation and maintenance rules and regulations and lacks quantitative standards. Although the method of additionally installing sensors on the sweeper avoids manual inspections, the installation of sensors increases costs. In addition, an additional set of network usage sensors needs to be installed to access the network to analyze sensor signals, which further increases costs.

[0044] Therefore, the present application provides a method for detecting wear of a conveyor belt cleaner, such as Figure 1 Shown, including:

[0045] Obtain the initial image and video stream of the belt area between the tail roller and the discharge port of the sweeper;

[0046] Setting a time interval, performing frame extraction processing on the video stream to obtain a belt area image;

[0047] Collecting belt area images within a preset time period as an image set, and calculating similarity values between all belt area images in the image set and the initial image in sequence to obtain a calculation result;

[0048] Based on the calculation result, the image set is divided into a set of images with foreign matter and a set of images without foreign matter, wherein the set of images with foreign matter and the set of images without foreign matter constitute a data set;

[0049] Building a visual model, and training the visual model using the data set;

[0050] Based on the trained visual model, the real-time image of the belt area between the tail roller and the discharge port of the sweeper is processed to obtain the processing results;

[0051] Based on the processing result, it is determined whether the cleaner is worn.

[0052] Among them, the initial image and video stream of the belt area between the tail roller of the sweeper and the discharge port are obtained through the camera. The camera does not need to be installed separately. The existing conveyor belt system has cameras installed upstream and downstream. It is only necessary to adjust the camera at the discharge port to aim at the belt area between the sweeper and the discharge port. The purpose of obtaining the initial image is to use the initial image as a standard image of a clean belt.

[0053] Among them, the time interval is set to extract frames from the video stream, such as 1 minute / time. The specific time interval can be adjusted according to actual conditions, and then the video stream is converted into multiple belt area images.

[0054] Among them, the belt area images within a period of time are collected as an image set, and the similarity values of all belt area images in the image set and the initial image are calculated by the formula The similarity value range is [-1, 1]. When the similarity value is closer to 1, the belt area image is more similar to the initial image.

[0055] Among them, based on the calculation results, the image set is divided into a set of images with foreign objects and a set of images without foreign objects. The set of images with foreign objects and the set of images without foreign objects constitute a data set. Specifically, by setting a first threshold, such as 0.9, when the similarity value between the belt area image and the initial image exceeds 0.9, the belt area image is judged to be an image without foreign objects, otherwise, the belt area image is judged to be an image with foreign objects.

[0056] Among them, a visual model is constructed and the data set is used to train the visual model. The training methods include but are not limited to YOLO, Transformer and convolutional neural network training.

[0057] Among them, a real-time image of the belt area between the tail roller of the sweeper and the discharge port is obtained and input into the trained visual model. If it is judged that the real-time image belongs to the image set with foreign matter, it is judged that the sweeper is worn. If it is judged that the real-time image belongs to the image set without foreign matter, it is judged that the sweeper is not worn.

[0058] In some embodiments, an initial image and video stream of the belt area between the tail drum of the sweeper and the discharge port are obtained by a camera.

[0059] In some embodiments, calculating the similarity between all belt region images in the image set and the initial image in sequence includes:

[0060]

[0061] SSIM(I1, I2) is the similarity value between the belt area image and the initial image, is the initial image mean, is the mean value of the belt area image, is the covariance between the initial image and the belt area image, is the initial image variance, is the belt area image variance.

[0062] In some embodiments, based on the calculation result, dividing the image set into a set of images with foreign matter and a set of images without foreign matter comprises:

[0063] Setting a first threshold, and when the similarity value between the belt area image and the initial image is greater than the first threshold, classifying the corresponding belt area image into the foreign body-free image set;

[0064] When the similarity value between the belt area image and the initial image is less than or equal to the first threshold, the corresponding belt area image is classified into the foreign matter image set.

[0065] In some embodiments, the real-time image is processed based on the trained visual model to obtain a processing result including:

[0066] The real-time image is input into the trained visual model for processing, and the real-time image is divided into the image set with foreign matter or the image set without foreign matter.

[0067] In some embodiments, based on the processing result, determining whether the cleaner is worn includes:

[0068] If the real-time image is classified into the set of images with foreign matter, it is determined that the cleaner is worn;

[0069] If the real-time image is classified into the foreign matter-free image set, it is determined that the cleaner is not worn.

[0070] Example 2

[0071] Based on the conveyor belt cleaner wear detection method provided in the first embodiment of the present application, the second embodiment of the present application also provides a conveyor belt cleaner wear detection system, such as Figure 2 Shown, including:

[0072] An acquisition unit, used to acquire an initial image and video stream of the belt area between the tail roller of the sweeper and the discharge port;

[0073] A video stream processing unit is used to set a time interval and perform frame extraction processing on the video stream to obtain a belt area image;

[0074] a similarity value calculation unit, configured to collect belt area images within a preset time period as an image set, and calculate similarity values between all belt area images in the image set and the initial image in sequence to obtain a calculation result;

[0075] a data set unit, configured to divide the image set into a set of images with foreign matter and a set of images without foreign matter based on the calculation result, wherein the set of images with foreign matter and the set of images without foreign matter constitute a data set;

[0076] A visual model unit, configured to construct a visual model and train the visual model using the data set;

[0077] A processing unit is used to process a real-time image of the belt area between the tail roller of the sweeper and the discharge port based on the trained visual model to obtain a processing result;

[0078] A judging unit is used to judge whether the sweeper is worn based on the processing result.

[0079] The specific principles and execution processes of each unit in the conveyor belt cleaner wear detection system disclosed in the above-mentioned embodiment 2 of the present application are the same as those of the conveyor belt cleaner wear detection method disclosed in the above-mentioned embodiment 1 of the present application. Please refer to the corresponding parts of the conveyor belt cleaner wear detection method disclosed in the above-mentioned embodiment 1 of the present application, and no further details will be given here.

[0080] Example 3

[0081] Embodiment 3 of the present application provides an electronic device, comprising: a processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; and the memory is used to store a program, wherein the program is used to implement a conveyor belt cleaner wear detection method as provided in Embodiment 1 of the present application.

[0082] Example 4

[0083] Embodiment 4 of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. The computer-executable instructions are used to execute a conveyor belt cleaner wear detection method as provided in Embodiment 1 of the present application.

[0084] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computing software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may 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.

[0085] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0086] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for detecting wear of a conveyor belt cleaner, characterized in that: include: Obtain the initial image and video stream of the belt area between the tail roller and the discharge port of the sweeper; Setting a time interval, performing frame extraction processing on the video stream to obtain a belt area image; Collecting belt area images within a preset time period as an image set, and calculating similarity values between all belt area images in the image set and the initial image in sequence to obtain a calculation result; Based on the calculation result, the image set is divided into a set of images with foreign matter and a set of images without foreign matter, wherein the set of images with foreign matter and the set of images without foreign matter constitute a data set; Building a visual model, and training the visual model using the data set; Based on the trained visual model, the real-time image of the belt area between the tail roller and the discharge port of the sweeper is processed to obtain the processing results; Based on the processing result, it is determined whether the cleaner is worn.

2. A conveyor belt cleaner wear detection method according to claim 1, characterized in that: The camera is used to obtain the initial image and video stream of the belt area between the tail roller of the sweeper and the discharge port.

3. A conveyor belt cleaner wear detection method according to claim 1, characterized in that: Calculating the similarity between all belt area images in the image set and the initial image in sequence includes: SSIM(I1, I2) is the similarity value between the belt area image and the initial image, is the initial image mean, is the mean value of the belt area image, is the covariance between the initial image and the belt area image, is the initial image variance, is the belt area image variance.

4. A conveyor belt cleaner wear detection method according to claim 1, characterized in that: Based on the calculation result, dividing the image set into a foreign body image set and a foreign body free image set includes: Setting a first threshold, and when the similarity value between the belt area image and the initial image is greater than the first threshold, classifying the corresponding belt area image into the foreign body-free image set; When the similarity value between the belt area image and the initial image is less than or equal to the first threshold, the corresponding belt area image is classified into the foreign matter image set.

5. A conveyor belt cleaner wear detection method according to claim 1, characterized in that: The real-time image is processed based on the trained visual model to obtain processing results including: The real-time image is input into the trained visual model for processing, and the real-time image is divided into the image set with foreign matter or the image set without foreign matter.

6. A conveyor belt cleaner wear detection method according to claim 5, characterized in that: Based on the processing result, determining whether the sweeper is worn includes: If the real-time image is classified into the set of images with foreign matter, it is determined that the cleaner is worn; If the real-time image is classified into the foreign matter-free image set, it is determined that the cleaner is not worn.

7. A conveyor belt cleaner wear detection system, characterized in that: include: An acquisition unit, used to acquire an initial image and video stream of the belt area between the tail roller of the sweeper and the discharge port; A video stream processing unit is used to set a time interval and perform frame extraction processing on the video stream to obtain a belt area image; a similarity value calculation unit, configured to collect belt area images within a preset time period as an image set, and calculate similarity values between all belt area images in the image set and the initial image in sequence to obtain a calculation result; a data set unit, configured to divide the image set into a set of images with foreign matter and a set of images without foreign matter based on the calculation result, wherein the set of images with foreign matter and the set of images without foreign matter constitute a data set; A visual model unit, configured to construct a visual model and train the visual model using the data set; A processing unit is used to process a real-time image of the belt area between the tail roller of the sweeper and the discharge port based on the trained visual model to obtain a processing result; A judging unit is used to judge whether the sweeper is worn based on the processing result.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is configured to call and execute a program stored in the memory; The memory is used to store a program, and the program is used to implement a conveyor belt cleaner wear detection method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute a conveyor belt cleaner wear detection method according to any one of claims 1 to 6.

Images