Method for detecting belt conveyor carrier roller faults through inspection robot
Through the inspection robot image preprocessing and noise data clustering method of belt rollers, combined with structural similarity and noise comparison, the problem of difficult internal faults in image analysis in the prior art is solved, and the failure of rollers is realized Comprehensive and accurate detection.
Patent Information
- Application Number
- CN202411260434.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-12-03
AI Technical Summary
In the prior art, inspection robots are difficult to identify internal faults of the belt roller through image analysis only, and they are not comprehensive enough to effectively detect all fault conditions when relying on operation noise.
Multiple sets of images of the rollers were photographed by patrol robots for preprocessing and structural similarity comparison analysis. Combined with the K-value clustering method of noise data, the structural similarity threshold and noise comparison were set to comprehensively judge the fault condition of the rollers.
Through the comprehensive judgment of structural similarity index and noise analysis, the comprehensiveness and accuracy of fault detection are improved, ensuring effective identification of roller deformation and internal faults.
Smart Images

Figure CN119067959A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of fault detection, and in particular relates to a method for detecting belt conveyor roller faults by a patrol robot. Background Art
[0002] After long-term operation, belt conveyor rollers may wear out and deform. Therefore, it is necessary to regularly detect the degree of fault during use to ensure the normal operation of the equipment and avoid major safety accidents and production accidents. In the prior art, inspection robots are usually used to capture images of belt conveyor rollers using high-definition cameras on the inspection robots, and the images are analyzed to calculate the deformation amount to determine whether there is a fault. However, this method of judging faults based solely on images is not completely accurate. For example, belt conveyor rollers sometimes have internal fractures, which cannot be identified from images alone. At this time, it is necessary to use operating noise for identification. For this reason, a method for detecting belt conveyor roller faults using inspection robots is proposed. Summary of the invention
[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method for detecting belt conveyor roller failures by an inspection robot, thereby solving the problems in the prior art.
[0004] The purpose of the present invention can be achieved by the following technical solutions:
[0005] A method for detecting belt conveyor roller failure by an inspection robot comprises the following steps:
[0006] Use the camera on the inspection robot to take multiple sets of images of the roller and pre-process the images;
[0007] The structural similarity of the preprocessed images was compared with the original images of the conveyor belt roller, and the mean value of the structural similarity index was calculated.
[0008] The signal collector on the inspection robot is used to collect the roller noise, and the collected noise is normalized, and the normalized noise data is clustered using the K value clustering method;
[0009] The structural similarity threshold is set, and whether the roller structure has deformation failure is determined according to the mean value of the structural similarity index; and the clustering result of the noise data is compared with the critical noise of the roller to determine whether a failure occurs.
[0010] Furthermore, the image preprocessing step includes:
[0011] S11, eliminating images that do not capture the complete roller, and selecting images that can fully display the roller;
[0012] S12, using a Gaussian filter to construct a noise reduction function to perform noise reduction on the filtered image;
[0013] Furthermore, the noise reduction function is:
[0014] D(I,σ)=GaussianBlur(I,σ)
[0015] Where I represents the filtered image, σ is the standard deviation of the Gaussian filter, and GaussianBlur represents the Gaussian filter function.
[0016] Furthermore, the structural similarity comparison analysis process is:
[0017] S21, comparing the structural similarity of the preprocessed multiple groups of images with the original images respectively, and calculating multiple groups of structural similarity indexes SSIM;
[0018] S22, averaging multiple structural similarity indices.
[0019] Furthermore, the calculation expression of the structural similarity index SSIM is:
[0020]
[0021] Where x and y are the preprocessed image and the original image respectively; u x and u y are the mean values of the pixels in images x and y respectively; x and σ y are the variances of the pixel values of images x and y, respectively, xy The covariance between the pixel values of image x and y. c1 and c2 are constants used to stabilize the calculation and are usually small positive numbers.
[0022] Furthermore, the formula for noise normalization is:
[0023]
[0024] In the formula, v * is the normalized noise, v is the collected roller noise data; v max and v min are the maximum and minimum values of the corresponding data in the total sample data.
[0025] Furthermore, the structural similarity threshold is 0.8, and when the mean absolute value of the structural similarity index is less than 0.8, it is determined that the roller has a deformation fault.
[0026] A detection system for belt conveyor roller faults by an inspection robot, comprising:
[0027] Image preprocessing module: Use the camera on the inspection robot to take multiple groups of images of the roller and preprocess the images;
[0028] Image comparison module: perform structural similarity comparison analysis on the preprocessed multiple groups of images and the original images of the belt conveyor roller, and calculate the mean value of the structural similarity index;
[0029] Noise processing module: The signal collector on the inspection robot is used to collect roller noise, and the collected noise is normalized, and the normalized noise data is clustered using the K value clustering method;
[0030] And, the fault judgment module: sets the structural similarity threshold, and judges whether the roller structure has a deformation fault according to the mean value of the structural similarity index; and compares the clustering result of the noise data with the critical noise of the roller to judge whether a fault has occurred.
[0031] A computer storage medium stores a readable program, and when the program is running, it can execute the above-mentioned method for detecting belt conveyor roller faults by a patrol robot.
[0032] An electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;
[0033] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned method for detecting belt conveyor roller faults by an inspection robot.
[0034] Beneficial effects of the present invention:
[0035] 1. By comparing the captured image of the belt conveyor roller with the original image, the structural similarity index is used to characterize the difference to determine the deformation degree of the belt conveyor roller; and the noise level analysis during the operation of the belt conveyor roller is combined to comprehensively determine the fault and improve the comprehensiveness of fault detection.
[0036] 2. The stability and credibility of the representation index are improved by averaging the structural similarity index of multiple groups of captured images and the original images.
[0037] 3. Use Gaussian filter to reduce noise on the image before image comparison to improve image clarity and improve the accuracy of image comparison structure.
[0038] 4. By removing the images that do not fully show the roller from the captured image set, the size of the image data set can be reduced and the computing processing speed can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of the present invention 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0040] Figure 1 It is a flow chart of the detection method of the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0042] like Figure 1 As shown, a method for detecting belt conveyor roller failure by an inspection robot includes the following steps:
[0043] S1, using the camera on the inspection robot to take multiple groups of images of the roller and pre-processing the images;
[0044] The preprocessing of the image set consists of the following steps:
[0045] S11, eliminating images that do not capture the complete roller, and selecting images that can fully display the roller, so as to reduce the number of images in the data set, thereby reducing the amount of calculation and improving the calculation speed;
[0046] S12, performing noise reduction processing on the screened image to improve the clarity of the roller in the image;
[0047] A Gaussian filter is used to construct a denoising function, and the denoising process is performed on the filtered image I. The denoising function is:
[0048] D(I,σ)=GaussianBlur(I,σ)
[0049] Where I represents the filtered image, σ is the standard deviation of the Gaussian filter, and GaussianBlur represents the Gaussian filter function, which takes the standard deviation σ of the Gaussian filter and the filtered image I as input, outputs the denoised image, and improves the clarity of the image to facilitate the subsequent similarity comparison analysis;
[0050] Moreover, the convolution kernel size is an important parameter in the Gaussian filter, which determines the smoothness of the filter on the image. Generally, the larger the convolution kernel size, the more obvious the smoothing effect, but it may also cause the loss of image details. The selection of an appropriate convolution kernel size needs to be determined according to the specific image characteristics and noise reduction requirements. In this embodiment, the convolution kernel of the Gaussian filter is 5×5.
[0051] S2, performing structural similarity comparison analysis on the preprocessed multiple groups of images and the original images of the belt conveyor roller, and obtaining the mean value of the structural similarity index;
[0052] S21, comparing the structural similarity of the preprocessed multiple groups of images with the original images respectively, and calculating multiple groups of structural similarity indexes SSIM;
[0053] The structural similarity index (SSIM) is an indicator used to measure the similarity between two images, which takes into account the differences in image structure; the calculation expression of SSIM is as follows:
[0054]
[0055] Where x and y are the preprocessed image and the original image respectively; u x and u y are the mean values of the pixels in images x and y respectively; x and σ y are the variances of the pixel values of images x and y, respectively, xy The covariance between the pixel values of image x and y. c1 and c2 are constants used to stabilize the calculation and are usually small positive numbers.
[0056] The value range of SSIM is [-1,1]. When two images are exactly the same, the value of SSIM is 1; when there is no similarity between the two images, the value of SSIM is 0.
[0057] S22, averaging multiple structural similarity indices;
[0058] For n structural similarity indices S{S1, S2...S n}, find the mean:
[0059]
[0060] S3, using the signal collector on the inspection robot to collect the roller noise, normalizing the collected noise, and clustering the normalized noise data using the K value clustering method;
[0061] The normalization formulas include:
[0062]
[0063] In the formula, v * is the normalized noise, v is the collected roller noise data; v max and v min are the maximum and minimum values of the corresponding data in the total sample data.
[0064] S4, set the structural similarity threshold, and judge whether the roller structure has deformation failure according to the mean value of the structural similarity index obtained in S2; and compare the clustering result obtained in S3 with the critical noise of the roller to judge whether a failure has occurred; when the mean value of the structural similarity index exceeds the threshold or the critical noise is exceeded in the noise, it is judged that the belt conveyor roller is faulty.
[0065] In the deformation fault judgment, the structural similarity threshold is 0.8. When the absolute value of the mean value of the structural similarity index is less than 0.8, it is judged that the roller has a deformation fault.
[0066] The method of the present invention may be implemented in hardware, firmware, or as software or computer code that may be stored in a recording medium (such as a CDROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded over a network and will be stored in a local recording medium, so that the method described herein may be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, processor, or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown herein.
[0067] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.
Claims
1. A method for detecting belt conveyor roller failure using an inspection robot, characterized in that: The following steps are involved: Use the camera on the inspection robot to take multiple sets of images of the roller and pre-process the images; The structural similarity of the preprocessed images was compared with the original images of the conveyor belt roller, and the mean value of the structural similarity index was calculated. The signal collector on the inspection robot is used to collect the roller noise, and the collected noise is normalized, and the normalized noise data is clustered using the K value clustering method; The structural similarity threshold is set, and whether the roller structure has deformation failure is determined according to the mean value of the structural similarity index; and the clustering result of the noise data is compared with the critical noise of the roller to determine whether a failure occurs.
2. The method for detecting belt conveyor roller failure by an inspection robot according to claim 1, characterized in that: The steps of image preprocessing include: S11, eliminating images that do not capture the complete roller, and selecting images that can fully display the roller; S12, using a Gaussian filter to construct a noise reduction function to perform noise reduction on the filtered image.
3. The method for detecting belt conveyor roller failure by an inspection robot according to claim 2, characterized in that: The noise reduction function is: D(I,σ)=GaussianBlur(I,σ) Where I represents the filtered image, σ is the standard deviation of the Gaussian filter, and GaussianBlur represents the Gaussian filter function.
4. The method for detecting belt conveyor roller failure by an inspection robot according to claim 1, characterized in that: The structural similarity comparison analysis process is: S21, comparing the structural similarity of the preprocessed multiple groups of images with the original images respectively, and calculating multiple groups of structural similarity indexes SSIM; S22, averaging multiple structural similarity indices.
5. The method for detecting belt conveyor roller failure by an inspection robot according to claim 4, characterized in that: The calculation expression of the structural similarity index SSIM is: Where x and y are the preprocessed image and the original image respectively; u x and u y are the mean values of the pixels in images x and y respectively; x and σ y are the variances of the pixel values of images x and y, respectively, xy The covariance between the pixel values of image x and y. c1 and c2 are constants used to stabilize the calculation and are usually small positive numbers.
6. The method for detecting belt conveyor roller failure by an inspection robot according to claim 1, characterized in that: The formula for noise normalization is: In the formula, v * is the normalized noise, v is the collected roller noise data; v max and v min are the maximum and minimum values of the corresponding data in the total sample data.
7. The method for detecting belt conveyor roller failure by an inspection robot according to claim 1, characterized in that: The structural similarity threshold is 0.
8. When the mean absolute value of the structural similarity index is less than 0.8, it is determined that the roller is deformed.
8. A detection system for belt conveyor roller failure by an inspection robot, characterized in that: include: Image preprocessing module: Use the camera on the inspection robot to take multiple groups of images of the roller and preprocess the images; Image comparison module: perform structural similarity comparison analysis on the preprocessed multiple groups of images and the original images of the belt conveyor roller, and calculate the mean value of the structural similarity index; Noise processing module: The signal collector on the inspection robot is used to collect roller noise, and the collected noise is normalized, and the normalized noise data is clustered using the K value clustering method; And, the fault judgment module: sets the structural similarity threshold, and judges whether the roller structure has a deformation fault according to the mean value of the structural similarity index; and compares the clustering result of the noise data with the critical noise of the roller to judge whether a fault has occurred.
9. A computer storage medium storing a readable program, characterized in that: When the program is running, it can execute the method for detecting belt conveyor roller faults by an inspection robot as described in any one of claims 1 to 7.
10. An electronic device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to a method for detecting belt conveyor roller faults by an inspection robot according to any one of claims 1-7.
