Hydraulic support oil cylinder barrel inner hole defect detection method and system based on image processing

Abstract

The invention provides a hydraulic support oil cylinder barrel inner hole defect detection method and system based on image processing. The method comprises the steps that an image frame containing an oil cylinder barrel inner hole is intercepted from a real-time monitoring video stream under the working environment of a hydraulic support; adjusting the contrast and brightness of the image frame by applying a high dynamic range imaging technology to obtain a second image frame; identifying and positioning the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame by using an edge detection algorithm and a threshold segmentation technology; geometric deviations between the boundary of the oil cylinder barrel inner hole in the second image frame and the standard oil cylinder barrel inner hole model and between the internal structure change of the oil cylinder barrel inner hole and the standard oil cylinder barrel inner hole model are calculated, and a geometric deviation result is obtained; according to the geometric deviation result, the defect position of the inner hole of the oil cylinder barrel is marked in the second image frame, and a detection report is generated; according to the invention, efficient and accurate detection of the inner hole of the cylinder barrel of the hydraulic support oil cylinder is realized, the detection precision and efficiency are improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of industrial image processing, and in particular, to a method and system for detecting defects in the inner hole of a hydraulic support cylinder barrel based on image processing. Background Art

[0002] In modern mine exploitation and engineering operations, as a key support equipment, the performance of hydraulic supports directly affects the safety and efficiency of work. Especially the cylinder components in hydraulic supports, which are under high pressure and harsh working environments for a long time, are prone to defects such as wear and cracks. If these problems are not discovered and handled in time, they will seriously affect the normal operation of hydraulic supports and even lead to safety accidents.

[0003] Currently, for the defect detection of the inner hole of a hydraulic support cylinder barrel, it mainly relies on manual visual inspection or traditional contact measurement methods. Manual visual inspection is affected by the complex working environment and poor lighting conditions. In addition, there are subjective judgment errors in manual inspection, making it difficult to ensure the consistency and reliability of detection results. Traditional contact measurement methods are cumbersome to operate, time-consuming, and may cause secondary damage to the inner hole of the cylinder barrel. Summary of the Invention

[0004] The embodiments of the present invention provide a method and system for detecting defects in the inner hole of a hydraulic support cylinder barrel based on image processing to solve the problems of unreliable detection results, cumbersome operation, and long time consumption in the prior art.

[0005] In a first aspect, the embodiments of the present invention provide a method for detecting defects in the inner hole of a hydraulic support cylinder barrel based on image processing, including: Intercepting an image frame containing the inner hole of the cylinder barrel from the real-time monitoring video stream in the working environment of the hydraulic support; Applying high dynamic range imaging technology to adjust the contrast and brightness of the image frame to obtain a second image frame; Using edge detection algorithms and threshold segmentation techniques to identify and locate the boundary of the inner hole of the cylinder barrel and the internal structure changes in the inner hole of the cylinder barrel in the second image frame; Calculating the geometric deviation between the boundary of the inner hole of the cylinder barrel and the internal structure changes in the inner hole of the cylinder barrel in the second image frame and a standard inner hole model of the cylinder barrel to obtain a geometric deviation result, where the geometric deviation result includes defect position information of the inner hole of the cylinder barrel; Marking the defect position of the inner hole of the cylinder barrel in the second image frame according to the geometric deviation result and generating a detection report.

[0006] Optionally, the intercepting an image frame containing the inner hole of the cylinder barrel from the real-time monitoring video stream in the working environment of the hydraulic support includes: The working environment video stream inside the cylinder barrel of the oil cylinder is captured in real time through a high-resolution camera installed on the hydraulic support; The image jitter in the working environment video stream is eliminated through image stabilization technology to obtain a target working environment video stream; The dynamic changes in the inner hole area of the oil cylinder barrel in the target working environment video stream are detected using a motion estimation algorithm to identify the appearance moment of the inner hole of the oil cylinder barrel; Based on the appearance moment, sample image frames containing multiple inner holes of the oil cylinder barrel are synchronously intercepted in the target working environment video stream; The image frames containing the inner holes of the oil cylinder barrel are selected from the sample image frames of the multiple inner holes of the oil cylinder barrel using a target recognition algorithm.

[0007] Optionally, the application of high dynamic range imaging technology to adjust the contrast and brightness of the image frame to obtain a second image frame includes: Through a high dynamic range synthesis algorithm, the image frame is synthesized with image frames taken at different exposure levels to generate a high dynamic range image; The local contrast of the high dynamic range image is adjusted using local tone mapping technology to obtain a target high dynamic range image; The overall brightness of the target high dynamic range image is adjusted using a global brightness correction algorithm to obtain a second image frame.

[0008] Optionally, the use of edge detection algorithms and threshold segmentation techniques to identify and locate the boundaries of the inner holes of the oil cylinder barrel and the internal structure changes of the inner holes of the oil cylinder barrel in the second image frame includes: The second image frame is processed using an edge detection algorithm to obtain the edge information of the inner hole of the oil cylinder barrel, and the edge information includes the boundary of the inner hole of the oil cylinder barrel; Based on the edge information, the inner hole area of the oil cylinder barrel in the second image frame is separated using threshold segmentation technology to obtain a segmentation result; Based on the segmentation result, a feature point detection algorithm is applied to identify the key feature points in the second image frame to obtain key feature point information, and the key feature point information includes the feature points inside the inner hole of the oil cylinder barrel; Based on the key feature point information, template matching technology is used to identify and locate the boundaries of the inner holes of the oil cylinder barrel and the internal structure changes of the inner holes of the oil cylinder barrel in the second image frame.

[0009] Optionally, calculating the geometric deviation between the boundaries of the inner holes of the oil cylinder barrel and the internal structure changes in the second image frame and a standard inner hole model of the oil cylinder barrel to obtain a geometric deviation result, and the geometric deviation result includes the defect position information of the inner hole of the oil cylinder barrel includes: Based on the boundary of the inner hole of the oil cylinder barrel and the changes in the internal structure of the inner hole of the oil cylinder barrel in the second image frame, change information is obtained; Determine the standard information of the preset standard inner hole model of the oil cylinder barrel, align the standard information with the change information, and obtain the actual structural change information after alignment. The standard information includes dimensions, shape, and position information; Input the actual structural change information into the preset standard inner hole model of the oil cylinder barrel to obtain a geometric deviation value. The geometric deviation includes differences in dimensions, shape, and position; Among them, the calculation formula for the geometric deviation value is as follows: ; ; Among them, represents the actual structural change information and the standard inner hole model of the oil cylinder barrel the geometric deviation value between them; represents the volume of the inner hole of the oil cylinder barrel; represents the three-dimensional function of the actual structural change information; is the three-dimensional function of the standard inner hole model of the oil cylinder barrel; represents the weight coefficient, which is used to balance different types of deviations; represents the partial derivative of the actual structural change information in the direction ; represents the partial derivative of the standard model in the direction ; represents the number of normal directions of the inner hole surface of the oil cylinder barrel; is an index variable, representing different directions; represents the th unit vector in the direction; represents the influence parameter of the geometric deviation value; According to the geometric deviation value, apply the preset defect evaluation criteria to determine whether there are defects in the inner hole of the oil cylinder barrel, and obtain the geometric deviation result.

[0010] Optionally, according to the geometric deviation result, mark the defect position of the inner hole of the oil cylinder barrel in the second image frame, and the generated detection report includes: Based on the geometric deviation result, mark the defect position of the inner hole of the oil cylinder barrel in the second image frame to obtain the defect position information; Based on the preset defect classification criteria, evaluate the severity of the defect at the defect position to obtain the defect severity information. The defect classification criteria specify the defect categories corresponding to different geometric deviations; Based on the defect location information and the defect severity information, obtain a comprehensive analysis result; Based on the comprehensive analysis result, generate a detection report including the comprehensive analysis result, where the detection report includes the defect location, defect description, defect level, and recommended repair measures.

[0011] Optionally, based on a preset defect classification standard, evaluate the defect severity of the defect location to obtain defect severity information, where the defect classification standard stipulates that the defect categories corresponding to different geometric deviations include: Define the defect severity; Among them, the calculation formula for the defect severity is as follows: ; Among them, represents the defect severity; represents the weight vector; is the feature vector; bias term; is the geometric feature weight vector; is the geometric feature vector; is the geometric feature bias term; is the texture feature weight vector; is the texture feature vector; is the texture feature bias term; is the edge feature weight vector; is the edge feature vector; is the edge feature bias term; represents the location information of the detected defect area; Define the geometric feature vector in the defect severity, and introduce geometric feature expressions, where the geometric feature expressions include: the area expression of the defect area, the circularity expression, the depth expression, and the direction expression; Among them, the calculation formula for the geometric feature expressions is as follows: ; ; ; ; Among them, represents the area of the defect area; represents the pixels in the defect area; represents the pixel occupied area; represents the circularity of the defect area; is the pi; represents the area of the defect area; Represents the perimeter of the defect area; Represents the defect depth; Represents the number of points for measuring depth within the defect area; Represents the th measurement point; Represents the th depth value of the measurement point; Represents the cosine similarity between the defect direction and the standard direction, where is the direction angle of the defect, is the standard direction angle; Represents the position information of the detected defect area; Defines the edge feature vector in the defect severity, introduces the edge feature expression, and the edge feature expression includes: the gradient intensity expression of the defect area, the curvature expression of the defect edge, the length expression of the defect edge, and the discontinuous defect edge expression; Among them, the calculation formula of the edge feature expression is as follows: ; ; ; ; Among them, Represents the gradient intensity of the defect area; Represents the gradient of the image in the horizontal direction; Represents the gradient of the image in the vertical direction; Represents the curvature of the defect edge; and Represents the first derivative of the edge position with respect to the arc length ; and Represents the second derivative of the edge position with respect to the arc length ; The arc length is defined by the parametric curve ; Represents the length of the defect edge; and respectively represent the positions of two adjacent points on the edge curve; Represents the number of edge points; Represents the adjacent two points and The Euclidean distance between them; Represents the discontinuous defect edge, and respectively represent the positions of two adjacent points on the edge curve; Represents the gray value at the position ; Indicates the location information of the detected defect area.

[0012] In a second aspect, an embodiment of the present application provides a hydraulic support cylinder inner hole defect detection system based on image processing, including: An acquisition module, configured to intercept an image frame including the inner hole of the cylinder barrel from a real-time monitoring video stream in the working environment of the hydraulic support; An adjustment module, configured to adjust the contrast and brightness of the image frame by applying high dynamic range imaging technology to obtain a second image frame; An identification module, configured to identify and locate the boundary of the inner hole of the cylinder barrel and the internal structure change of the inner hole of the cylinder barrel in the second image frame by using an edge detection algorithm and a threshold segmentation technique; A calculation module, configured to calculate the geometric deviation between the boundary of the inner hole of the cylinder barrel and the internal structure change of the inner hole of the cylinder barrel in the second image frame and a standard cylinder barrel inner hole model to obtain a geometric deviation result, where the geometric deviation result includes the defect position information of the inner hole of the cylinder barrel; A generation module, configured to mark the defect position of the inner hole of the cylinder barrel in the second image frame according to the geometric deviation result and generate a detection report.

[0013] In a third aspect, an embodiment of the present invention provides a computing device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the hydraulic support cylinder inner hole defect detection method based on image processing according to any one of the first aspects.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the hydraulic support cylinder inner hole defect detection method based on image processing according to any one of the first aspects is implemented.

[0015] In an embodiment of the present invention, an image frame containing the inner hole of the cylinder barrel of the hydraulic support is intercepted from the real-time monitoring video stream in the working environment of the hydraulic support; the high dynamic range imaging technology is applied to adjust the contrast and brightness of the image frame to obtain a second image frame; the edge detection algorithm and the threshold segmentation technology are used to identify and locate the boundary of the inner hole of the cylinder barrel and the internal structure change of the inner hole of the cylinder barrel in the second image frame; the geometric deviation between the boundary of the inner hole of the cylinder barrel and the internal structure change of the inner hole of the cylinder barrel in the second image frame and the standard inner hole model of the cylinder barrel is calculated to obtain a geometric deviation result, and the geometric deviation result includes the defect position information of the inner hole of the cylinder barrel; according to the geometric deviation result, the defect position of the inner hole of the cylinder barrel is marked in the second image frame, and a detection report is generated. The technical solution provided by the present invention enables efficient, accurate, and automated detection of the inner hole of the cylinder barrel of the hydraulic support, improves the detection accuracy and efficiency, reduces the maintenance cost, and improves the stability of safe operation.

[0016] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a method for detecting defects in the inner hole of the cylinder barrel of a hydraulic support based on image processing provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a system for detecting defects in the inner hole of the cylinder barrel of a hydraulic support based on image processing provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0020] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0021] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] As a key component in mining and engineering machinery, the integrity of the inner hole of the hydraulic support cylinder directly affects the reliability and safety of the equipment. Traditional manual detection methods have problems such as low efficiency and insufficient accuracy, which are difficult to meet the needs of modern industrial production. Based on this, the present invention provides a method for detecting inner hole defects of hydraulic support cylinders based on image processing. Figure 1 ,include: Step 101: intercepting an image frame including the inner hole of the cylinder barrel from a real-time monitoring video stream in a hydraulic support working environment; In this step, the real-time monitoring video stream refers to a continuous video stream obtained from a camera installed in the working environment of the hydraulic support; the image frame refers to a single static image captured from the video stream.

[0023] This step captures image frames containing the inner hole of the cylinder barrel from the real-time monitoring video stream obtained by the cameras installed in the working environment of the hydraulic support; these cameras are installed in key locations that can fully cover the hydraulic support to ensure that the video stream contains enough information; through video processing software, the portion containing the inner hole of the cylinder barrel is selected from the continuous video stream and converted into a single static image for subsequent processing.

[0024] Step 102: applying high dynamic range imaging technology to adjust the contrast and brightness of the image frame to obtain a second image frame; In this step, high dynamic range imaging technology (HDR): an image processing technology used to improve the contrast and brightness in an image so that both dark and bright details in the image can be clearly seen; This step applies high-dynamic-range imaging technology to process the image frames intercepted in step 101, adjusting the contrast and brightness of the images to improve the image quality; through high-dynamic-range imaging technology, the details in the images can be better presented, especially in a working environment with complex or variable lighting conditions; the adjusted image is called the second image frame, which is more suitable for subsequent image processing and analysis.

[0025] Step 103: Use edge detection algorithms and threshold segmentation techniques to identify and locate the boundaries of the inner hole of the oil cylinder barrel and the internal structure changes of the inner hole of the oil cylinder barrel in the second image frame; In this step, the edge detection algorithm refers to an image processing algorithm used to identify the edges in an image, that is, the object contours or the boundaries between different regions; the threshold segmentation technique refers to an image segmentation technique that divides the image into different regions by setting a threshold, thereby identifying the regions of interest. This step uses edge detection algorithms and threshold segmentation techniques to identify and locate the inner hole of the oil cylinder barrel in the second image frame; the edge detection algorithm can find the boundaries of the inner hole of the oil cylinder barrel, and the threshold segmentation technique can separate the inner hole region of the oil cylinder barrel from the background, further clarifying the internal structure changes of the inner hole; the combination of the two techniques can more accurately identify and locate the defect positions.

[0026] Step 104: Calculate the geometric deviation between the boundaries of the inner hole of the oil cylinder barrel and the internal structure changes of the inner hole of the oil cylinder barrel in the second image frame and the standard inner hole model of the oil cylinder barrel to obtain a geometric deviation result, and the geometric deviation result includes the defect position information of the inner hole of the oil cylinder barrel; In this step, the geometric deviation refers to the difference between the actual object and the standard model, usually including differences in size, shape, and position; the standard inner hole model of the oil cylinder barrel refers to the ideal model of the inner hole of the oil cylinder barrel in a defect-free state.

[0027] This step calculates the geometric deviation between the boundaries of the inner hole of the oil cylinder barrel and the internal structure changes of the inner hole identified and located in step 103 and the standard inner hole model of the oil cylinder barrel; by comparing the actually detected boundaries of the inner hole and the internal structure changes of the inner hole with the standard inner hole model of the oil cylinder barrel, specific geometric deviation results can be obtained, and the geometric deviation results include the defect position information of the inner hole of the oil cylinder barrel, thereby determining the locations where defects and serious defects exist.

[0028] Step 105: Mark the defect positions of the inner hole of the oil cylinder barrel in the second image frame according to the geometric deviation result and generate a detection report; In this step, based on the geometric deviation results obtained in step 104, the defect positions of the inner hole of the oil cylinder barrel are marked in the second image frame. The marking can be in the form of graphic annotation, color identification, etc., so as to visually display the specific positions of the defects; a detailed inspection report is generated, which contains information such as the positions, types of the defects, and recommended treatment measures, so as to facilitate the maintenance personnel to carry out subsequent maintenance work.

[0029] The embodiments of the present invention can achieve the following beneficial effects through the above steps: Through the high-dynamic-range imaging technology and image processing algorithms, the image quality and the accuracy of detection are improved; The whole process from intercepting image frames from the video stream to generating the inspection report is automated, reducing manual intervention and improving the detection efficiency; It can monitor the state of the inner hole of the oil cylinder barrel in real time in a complex working environment, discover and mark the defect positions in time, and provide guarantee for the safe operation of the equipment.

[0030] The generated inspection report contains the specific positions and types of the defects, providing detailed basis for subsequent maintenance and repair.

[0031] In the fields of modern mine exploitation and construction machinery, the stable operation of the hydraulic support is crucial for safe production. The state of the inner hole of the oil cylinder barrel directly affects the performance and service life of the hydraulic support. However, the working environment of the hydraulic support is complex, and it is difficult for traditional detection methods to monitor the state of the inner hole of the oil cylinder barrel in real time and accurately. Based on this, the present invention provides a specific embodiment. In step 101, an image frame containing the inner hole of the oil cylinder barrel is intercepted from the real-time monitoring video stream in the working environment of the hydraulic support, which specifically includes the following steps: Step 110: Through a high-resolution camera installed on the hydraulic support, the working environment video stream inside the oil cylinder barrel of the hydraulic support is captured in real time; In this step, the high-resolution camera refers to a camera with a relatively high resolution, such as 1080p or higher, which can capture more details; the working environment video stream refers to the video data stream captured by the camera in real time.

[0032] In this step, a high-resolution camera is installed on the hydraulic support to ensure that the camera can cover the position where the inner hole of the oil cylinder barrel is located. The working environment video stream inside the oil cylinder barrel is captured in real time through the camera to ensure that all dynamic information of the inner hole of the oil cylinder barrel is included in the video stream.

[0033] Step 111: Eliminate the image jitter in the working environment video stream through the image stabilization technology to obtain the target working environment video stream; In this step, the image stabilization technology refers to a technology used to reduce or eliminate image jitter, usually implemented through software algorithms.

[0034] Since the hydraulic support may vibrate during operation, the images in the video stream will jitter. For example, the optical image stabilization (OIS) technology is used to process the captured video stream to eliminate image jitter and obtain a more stable video stream, that is, the target working environment video stream.

[0035] Step 112: Use the motion estimation algorithm to detect the dynamic changes in the inner hole area of the cylinder barrel in the target working environment video stream to identify the appearance moment of the inner hole of the cylinder barrel; In this step, the motion estimation algorithm refers to an image processing algorithm used to detect the motion of objects in a video sequence.

[0036] This step uses the motion estimation algorithm to detect the dynamic changes in the inner hole area of the cylinder barrel in the target working environment video stream. By detecting the motion of the inner hole area of the cylinder barrel, the appearance moment of the inner hole of the cylinder barrel in the video stream can be identified to determine when to intercept the effective image frames containing the inner hole of the cylinder barrel.

[0037] Step 113: Based on the appearance moment, synchronously intercept sample image frames containing multiple inner holes of the cylinder barrel in the target working environment video stream; After the appearance moment of the inner hole of the cylinder barrel is identified in step 102, according to these moments, sample image frames containing multiple inner holes of the cylinder barrel are synchronously intercepted in the target working environment video stream, and these sample image frames will be used for the next target recognition.

[0038] Step 114: Use the target recognition algorithm to screen out the image frames containing the inner hole of the cylinder barrel from the sample image frames of the multiple inner holes of the cylinder barrel; In this step, the target recognition algorithm refers to an algorithm used to identify specific targets from images.

[0039] This step uses the target recognition algorithm to screen the sample image frames intercepted in step 113 and select the image frames containing the inner hole of the cylinder barrel. The target recognition algorithm can identify it according to the characteristics of the inner hole of the cylinder barrel, such as shape, texture, etc., to ensure that the finally intercepted image frames contain the inner hole of the cylinder barrel.

[0040] The embodiments of the present invention can achieve the following beneficial effects through the above steps: Through the high-resolution camera and image stabilization technology, the quality of the video stream is improved, image jitter is eliminated, and the accuracy of subsequent processing is ensured; Using the motion estimation algorithm and the target recognition algorithm, the appearance moment of the inner hole of the cylinder barrel is intelligently identified, and the effective image frames containing the inner hole of the cylinder barrel are screened out from them, improving the detection accuracy and efficiency; The whole process is automated, reducing the need for manual intervention and improving the efficiency and reliability of detection; By real-time monitoring the video stream and promptly identifying the appearance moment of the inner hole of the oil cylinder barrel, the real-time monitoring of the state of the inner hole of the oil cylinder barrel is realized, which helps the operator to promptly discover potential defects.

[0041] In the working environment of the hydraulic support, due to the complex and variable lighting conditions, the image frames directly intercepted from the real-time monitoring video stream have problems of insufficient contrast and brightness, which directly affects the accuracy of subsequent defect detection. To overcome this problem and improve the image quality to ensure the reliability of defect detection, based on this, the present invention provides a specific embodiment. In step 102, the high dynamic range imaging technology is applied to adjust the contrast and brightness of the image frame to obtain a second image frame, which specifically includes the following steps: Step 201: Through the high dynamic range synthesis algorithm, synthesize the image frame with the image frames taken at different exposure levels to generate a high dynamic range image; In this step, the high dynamic range synthesis algorithm refers to an image processing technology used to synthesize the image frames taken at different exposure levels into a single high dynamic range image; the high dynamic range image (HDR image) refers to an image format that has a higher dynamic range than ordinary images and can better retain the details of the dark and bright parts in the image.

[0042] This step uses the high dynamic range synthesis algorithm to synthesize the image frames intercepted in step 101 into a single high dynamic range image, and selects the most appropriate pixel values in each image to retain the richest detail information, generating a high dynamic range image with more details.

[0043] Step 202: Adopt the local tone mapping technology to adjust the local contrast of the high dynamic range image to obtain the target high dynamic range image; In this step, the local tone mapping technology refers to an image processing technology used to adjust the local contrast of the image, enabling the image to enhance the discernibility of details while maintaining the high dynamic range.

[0044] In the generated high dynamic range image, although it contains a large amount of detail information, due to the high dynamic range, overexposure or underexposure may still occur when directly viewed. Therefore, this step adopts the local tone mapping technology to adjust the local contrast of the high dynamic range image. This technology can enhance the contrast of different regions in the image while maintaining the overall dynamic range of the image, making the details of the dark and bright parts more obvious, thereby obtaining the target high dynamic range image.

[0045] Step 203: Adopt the global brightness correction algorithm to adjust the overall brightness of the target high dynamic range image to obtain the second image frame; In this step, the global brightness correction algorithm refers to an image processing technique used to adjust the overall brightness of an image, enabling the image to present a better visual effect on the display.

[0046] This step adjusts the overall brightness of the target high-dynamic range image through the global brightness correction algorithm. The global brightness correction algorithm can adjust the overall brightness level of the image, making the image present a better visual effect on the display. By adjusting the brightness, it can ensure that the details in the image are clearly visible on various display devices, thereby obtaining the final second image frame.

[0047] The embodiments of the present invention can achieve the following beneficial effects through the above steps: By using the high-dynamic range synthesis algorithm to synthesize image frames with different exposure levels into a single high-dynamic range image, it can better retain the details of the dark and bright parts in the image; Utilize local tone mapping technology to adjust the local contrast of the high-dynamic range image, making the details in the image more obvious and enhancing the recognizability of the image; Adjust the overall brightness of the image through the global brightness correction algorithm to ensure that the image is clearly visible on various display devices and improve the visual effect of the image; The processed second image frame has a higher dynamic range and better contrast, which is helpful for subsequent processing steps such as edge detection and threshold segmentation, improving the accuracy and reliability of the detection.

[0048] In order to accurately detect the defects in the inner hole of the hydraulic support cylinder barrel, it is necessary to further extract useful key feature information from the image frames processed by the high-dynamic range imaging technology. Based on this, the present invention provides a specific embodiment. In step 103, an edge detection algorithm and threshold segmentation technology are used to identify and locate the boundary of the inner hole of the cylinder barrel of the hydraulic support and the internal structure changes of the inner hole of the cylinder barrel, which specifically include the following steps: Step 301: Apply an edge detection algorithm to process the second image frame to obtain the edge information of the inner hole of the cylinder barrel, and the edge information includes the boundary of the inner hole of the cylinder barrel; In this step, the edge detection algorithm refers to an image processing technique used to identify the boundaries of objects in an image. Common edge detection algorithms include Canny edge detection, Sobel operator, etc.

[0049] In this step, the Canny edge detection algorithm is used to process the second image frame. The Canny edge detection algorithm detects edges by calculating the gradient of the image and applying a double-threshold technique, and finally obtains the edge information of the inner hole of the cylinder barrel, and these edge information contain the boundary positions of the inner hole of the cylinder barrel.

[0050] Step 302: Based on the edge information, use threshold segmentation technology to separate the inner hole area of the oil cylinder barrel in the second image frame, and obtain a segmentation result; In this step, the threshold segmentation technology refers to an image segmentation technology that distinguishes different regions in an image by setting one or more thresholds.

[0051] After obtaining the edge information, use threshold segmentation technology to separate the inner hole area of the oil cylinder barrel in the second image frame from the background. For example, the OTSU threshold segmentation algorithm can automatically select the optimal threshold to obtain a clear segmentation result. This step uses the OTSU threshold segmentation algorithm to accurately separate the inner hole area of the oil cylinder barrel from the background.

[0052] Step 303: Based on the segmentation result, apply a feature point detection algorithm to identify the key feature points in the second image frame, and obtain key feature point information, where the key feature point information includes the feature points inside the inner hole of the oil cylinder barrel; In this step, the feature point detection algorithm refers to an image processing technology used to identify feature points in an image. Common algorithms include Scale-Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), etc.

[0053] For example, use the Speeded-Up Robust Features algorithm to identify the key feature points in the third image frame. These feature points are usually located inside the inner hole of the oil cylinder barrel and can help identify the structural changes of the inner hole. Through the feature point detection algorithm, key feature point information is obtained, which plays a key role in subsequent defect localization.

[0054] Step 304: Based on the key feature point information, adopt template matching technology to identify and locate the boundary of the inner hole of the oil cylinder barrel and the internal structural changes in the second image frame; In this step, the template matching technology refers to an image processing technology used to identify regions in an image that are similar to a given template.

[0055] In this step, after obtaining the key feature point information, use template matching technology to identify and locate the boundary of the inner hole of the oil cylinder barrel and the internal structural changes in the second image frame. The template matching technology can identify regions similar to the standard template, accurately locate the boundary of the inner hole of the oil cylinder barrel and the internal structural changes, and the finally obtained second image frame contains complete boundary and structural change information.

[0056] The embodiments of the present invention can achieve the following beneficial effects through the above steps: Through the edge detection algorithm and threshold segmentation technology, the boundary of the inner hole of the oil cylinder barrel can be more accurately identified, improving the accuracy of subsequent processing; By using feature point detection algorithms and template matching techniques, the internal structural changes in the inner hole of the oil cylinder barrel can be identified more accurately, improving the accuracy and reliability of detection. The entire process is automated, reducing the need for manual intervention and improving the efficiency and accuracy of detection.

[0057] After identifying and locating the boundaries of the inner hole of the oil cylinder barrel and the internal structural changes in the inner hole, it is necessary to further evaluate the specific situation of the defects. Based on this, the present invention provides a specific embodiment. In step 104, calculate the geometric deviation between the boundaries of the inner hole of the oil cylinder barrel and the internal structural changes in the inner hole of the second image frame and the standard inner hole model of the oil cylinder barrel to obtain a geometric deviation result. The geometric deviation result includes the defect position information of the inner hole of the oil cylinder barrel, and specifically includes the following steps: Step 401: Based on the boundaries of the inner hole of the oil cylinder barrel and the internal structural changes in the inner hole of the second image frame, obtain change information. In this step, the information on the boundaries of the inner hole of the oil cylinder barrel and the internal structural changes in the inner hole is extracted from the second image frame. This information includes the boundary position information obtained by edge detection and threshold segmentation and the internal structural change information obtained by feature point detection. Summarize this information to form change information describing the actual inner hole state.

[0058] Step 402: Determine the standard information of the preset standard inner hole model of the oil cylinder barrel, align the standard information with the change information to obtain the aligned actual structural change information. The standard information includes size, shape, and position information. For example, the standard inner hole model of the oil cylinder barrel is a perfect cylinder with a diameter of 100 mm and a length of 500 mm, and its surface is smooth without defects; align the change information obtained in step 401 with the standard information to ensure that the differences between the two are compared in the same coordinate system. Through this alignment, the aligned actual structural change information is obtained for subsequent calculation of geometric deviation.

[0059] Step 403: Input the actual structural change information into the preset standard inner hole model of the oil cylinder barrel to obtain a geometric deviation value. The geometric deviation includes differences in size, shape, and position. Among them, the calculation formula for the geometric deviation value is as follows: ; ; Among them, represents the actual structural change information and the standard inner hole model of the oil cylinder barrel the geometric deviation value between them; represents the volume of the inner hole of the oil cylinder barrel; A three-dimensional function representing actual structural change information; is a three-dimensional function of the inner hole model of a standard cylinder barrel; Represents a weight coefficient used to balance different types of deviations; Represents the actual structural change information in the direction partial derivative; Represents the partial derivative of the standard model in the direction partial derivative; Represents the number of normal directions of the inner hole surface of the cylinder barrel; Is an index variable representing different directions; Represents the unit vector of the th direction; Represents the influence parameter of the geometric deviation value; After obtaining the aligned actual structural change information, input this information into a preset standard inner hole model of the cylinder barrel, and obtain the geometric deviation value through a calculation formula. This calculation formula not only considers the average deviation within the volume, but also adds the difference in partial derivatives in the normal direction of the surface to quantify the change in the surface shape. This can more comprehensively evaluate the defect situation, and by introducing a weight coefficient, the sensitivity to different types of deviations can be adjusted according to the actual situation; this geometric deviation value reflects the differences in the size, shape, and position of the actual inner hole.

[0060] Step 404: According to the geometric deviation value, apply a preset defect evaluation standard to determine whether there is a defect in the inner hole of the cylinder barrel, and obtain a geometric deviation result; For example, the defect evaluation standard stipulates that if the geometric deviation value exceeds 5 mm, it is considered that there is a defect; according to the above standard, judge the calculated geometric deviation value. If it exceeds 5 mm, mark it as having a defect to obtain the geometric deviation result; this geometric deviation result contains defect position information, such as the defect appears at a specific position in the inner hole of the cylinder barrel.

[0061] The embodiments of the present invention can achieve the following beneficial effects through the above steps: By calculating the geometric deviation between the actual structural change and the standard model, more accurately identify the defect position and severity of the inner hole of the cylinder barrel; Using the geometric deviation value calculation formula, quantify the differences in the size, shape, and position of the inner hole of the cylinder barrel, and provide an objective evaluation basis; The whole process realizes automated processing, reduces the need for manual intervention, and improves the efficiency and accuracy of detection; According to the defect evaluation standard formulated according to industry specifications and manufacturer requirements, ensure the scientificity and practicality of the detection results, and contribute to the safe operation of the equipment.

[0062] For the convenience of subsequent maintenance and repair work, the following steps will be further processed based on these deviation results. Based on this, the present invention provides a specific embodiment. In step 105, according to the geometric deviation results, mark the defect positions of the inner hole of the oil cylinder barrel in the second image frame and generate a detection report, which specifically includes the following steps: Step 501: Based on the geometric deviation results, mark the defect positions of the inner hole of the oil cylinder barrel in the second image frame to obtain defect position information; For example, in the second image frame, use color markings such as red rectangular frames and arrows to mark the positions where the geometric deviation values exceed a predetermined threshold, and these positions are the defect positions. After marking, an image frame containing defect position information is obtained. For example, if the geometric deviation value exceeds 5 millimeters, a mark is added near this position and the specific position coordinates are recorded.

[0063] Step 502: Based on a preset defect classification standard, evaluate the severity of the defects at the defect positions to obtain defect severity information, and the defect classification standard stipulates the defect categories corresponding to different geometric deviations; For example, preset a defect classification standard, which stipulates the defect categories corresponding to different geometric deviations. For example, a geometric deviation between 1 - 3 millimeters belongs to a minor defect, 3 - 5 millimeters belongs to a medium defect, and greater than 5 millimeters belongs to a serious defect. For each marked defect position, evaluate its defect severity according to the preset defect classification standard. For example, if the geometric deviation at a certain position is 7 millimeters, it is evaluated as a serious defect. After evaluation, the defect severity information of each defect position is obtained.

[0064] Step 503: Based on the defect position information and the defect severity information, obtain a comprehensive analysis result; In this step, the specific coordinate information of each defect position is combined with the corresponding defect severity information to form a comprehensive analysis result. For example, the comprehensive analysis result can be a table listing the coordinates of each defect position, defect descriptions such as a dimensional deviation of 7 millimeters, and defect levels such as "serious defect", etc.

[0065] Step 504: Based on the comprehensive analysis result, generate a detection report containing the comprehensive analysis result, and the detection report includes defect positions, defect descriptions, defect levels, and recommended repair measures; This step generates an inspection report based on the comprehensive analysis results. The report should include the following content: defect location, coordinate information of the specific defect location; defect description, describing the specific situation of each defect, such as "dimension deviation of 7 mm, shape deviation of 5 mm"; defect level, the severity of the defect evaluated according to the defect classification standard, such as "severe defect"; recommended repair measures, providing corresponding repair suggestions according to the defect level, for example, "It is recommended to immediately stop the machine for inspection and replace the severely worn parts."

[0066] The embodiments of the present invention can achieve the beneficial effects through the above steps as follows: By marking the defect location in the second image frame, the defect location is made more intuitive, facilitating rapid identification by maintenance personnel; Based on the preset defect classification standard, evaluate the severity of the defect at the defect location to ensure the scientificity and accuracy of the evaluation results; Based on the defect location information and defect severity information, form a comprehensive analysis result to facilitate a comprehensive understanding of the state of the inner hole of the oil cylinder barrel; Generate an inspection report containing the defect location, defect description, defect level, and recommended repair measures, providing a detailed basis for maintenance and repair.

[0067] In order to more accurately evaluate the defect situation of the inner hole of the oil cylinder barrel and provide a scientific classification basis for it, it is necessary to conduct a detailed analysis according to the preset defect classification standard. Based on this, the present invention provides a specific embodiment. In step 502, based on the preset defect classification standard, evaluate the severity of the defect at the defect location to obtain defect severity information. The defect classification standard stipulates the defect categories corresponding to different geometric deviations, and specifically includes the following steps: Step 511: Define the severity of the defect; Among them, the calculation formula of the severity of the defect is as follows: ; Among them, represents the severity of the defect; represents the weight vector; is the feature vector; bias term; is the geometric feature weight vector; is the geometric feature vector; is the geometric feature bias term; is the texture feature weight vector; is the texture feature vector; is the texture feature bias term; is the edge feature weight vector; is the edge feature vector; is the edge feature bias term; Indicates the location information of the detected defect area; By introducing a linear regression model in machine learning, the severity of defects can be evaluated more flexibly according to different features. This method can automatically adjust the weights based on historical data, thus more accurately reflecting the actual situation.

[0068] Step 512: Define the geometric feature vector in the defect severity, and introduce geometric feature expressions, where the geometric feature expressions include: the area expression of the defect area, the circularity expression, the depth expression, and the direction expression; Among them, the calculation formulas of the geometric feature expressions are as follows: ; ; ; ; Among them, represents the area of the defect area; represents the pixels in the defect area; represents the pixel occupied area; represents the circularity of the defect area; is the pi; represents the area of the defect area; represents the perimeter of the defect area; represents the defect depth; represents the number of points for measuring the depth within the defect area; represents the th measurement point; represents the th measurement point depth value; represents the cosine similarity between the defect direction and the standard direction, where is the direction angle of the defect, is the standard direction angle; Indicates the location information of the detected defect area; By introducing these specific geometric features and assigning them their respective weight vectors and bias terms, the location and nature of the defects can be evaluated more meticulously, and the importance of each feature can also be adjusted according to the requirements of different application scenarios.

[0069] Step 513: Define the edge feature vector in the defect severity, and introduce edge feature expressions, where the edge feature expressions include: the gradient intensity expression of the defect area, the curvature expression of the defect edge, the length expression of the defect edge, and the discontinuous defect edge expression; Among them, the calculation formulas of the edge feature expressions are as follows: ; ; ; ; Among them, represents the gradient intensity of the defect area; represents the gradient of the image in the horizontal direction; represents the gradient of the image in the vertical direction; represents the curvature of the defect edge; and represent the first derivative of the edge position with respect to the arc length ; and represent the second derivative of the edge position with respect to the arc length ; The arc length is defined by the parametric curve ; represents the length of the defect edge; and represent the positions of two adjacent points on the edge curve respectively; represents the number of edge points; represents the adjacent two points and the Euclidean distance between them; represents the discontinuous defect edge, and represent the positions of two adjacent points on the edge curve respectively; represents the gray value at the position ; represents the position information of the detected defect area; By introducing edge features and assigning them their respective weight vectors and bias terms, the edge information of the defect can be evaluated more carefully.

[0070] The embodiments of the present invention can achieve the beneficial effects through the above steps as follows: By comprehensively considering geometric features, texture features, and edge features, the evaluation of the defect severity is more comprehensive and accurate; Introducing specific feature expressions and calculation formulas makes the defect evaluation scientific and operable.

[0071] Figure 2 FIG. is a schematic structural diagram of a hydraulic support cylinder inner hole defect detection system based on image processing provided by an embodiment of the present application, as Figure 2 shown, the system includes: The acquisition module 21 is used to intercept image frames containing the inner hole of the cylinder barrel from the real-time monitoring video stream in the working environment of the hydraulic support; The adjustment module 22 is used to adjust the contrast and brightness of the image frame by applying high dynamic range imaging technology to obtain a second image frame; The recognition module 23 is used to recognize and locate the boundary of the inner hole of the cylinder barrel and the internal structure change of the inner hole of the cylinder barrel in the second image frame by using edge detection algorithms and threshold segmentation techniques; The calculation module 24 is used to calculate the geometric deviation between the boundary of the inner hole of the cylinder barrel and the internal structure change of the inner hole of the cylinder barrel in the second image frame and the standard inner hole model of the cylinder barrel to obtain a geometric deviation result, and the geometric deviation result includes the defect position information of the inner hole of the cylinder barrel; The generation module 25 is used to mark the defect position of the inner hole of the cylinder barrel in the second image frame according to the geometric deviation result and generate a detection report.

[0072] Figure 2 The described defect detection system for the inner hole of the cylinder barrel of the hydraulic support based on image processing can execute Figure 1 The described defect detection method for the inner hole of the cylinder barrel of the hydraulic support based on image processing in the illustrated embodiment, its implementation principle and technical effects will not be elaborated. For the defect detection system for the inner hole of the cylinder barrel of the hydraulic support based on image processing in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here. Figure 2 The defect detection system for the inner hole of the cylinder barrel of the hydraulic support based on image processing in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0073] The processing component 32 is configured to: intercept an image frame containing the inner hole of the cylinder barrel from the real-time monitoring video stream in the working environment of the hydraulic support; apply high-dynamic-range imaging technology to adjust the contrast and brightness of the image frame to obtain a second image frame; use edge detection algorithms and threshold segmentation techniques to identify and locate the boundary of the inner hole of the cylinder barrel and the internal structure changes of the inner hole of the cylinder barrel in the second image frame; calculate the geometric deviation between the boundary of the inner hole of the cylinder barrel and the internal structure changes of the inner hole of the cylinder barrel in the second image frame and the standard inner hole model of the cylinder barrel to obtain a geometric deviation result, where the geometric deviation result includes the defect position information of the inner hole of the cylinder barrel; mark the defect position of the inner hole of the cylinder barrel in the second image frame according to the geometric deviation result, and generate a detection report.

[0074] Among them, the processing component 32 includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (AICs), digital signal processors (DPs), digital signal processing devices (DPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0075] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (RAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0076] The computing device further includes other components, such as an input / output interface, a display component, and a communication component.

[0077] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module can be an output device or an input device.

[0078] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0079] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device can refer to a cloud server, and the above processing component, storage component, etc. can be basic server resources leased or purchased from a cloud computing platform.

[0080] An embodiment of the present invention also provides a computer storage medium storing a computer program, which when executed by a computer can implement the above-mentioned Figure 1 defect detection method for the inner hole of the hydraulic support cylinder based on image processing shown in the embodiment.

[0081] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0082] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for detecting inner hole defects of hydraulic support cylinder barrel based on image processing, characterized in that: include: Intercepting an image frame containing the inner hole of the cylinder barrel from a real-time monitoring video stream in the working environment of the hydraulic support; Applying high dynamic range imaging technology to adjust the contrast and brightness of the image frame to obtain a second image frame; Using edge detection algorithm and threshold segmentation technology to identify and locate the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame; Calculating the geometric deviation between the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame and the standard inner hole model of the oil cylinder barrel to obtain a geometric deviation result, wherein the geometric deviation result includes defect position information of the inner hole of the oil cylinder barrel; According to the geometric deviation result, the defect position of the inner hole of the cylinder barrel is marked in the second image frame, and a detection report is generated.

2. The method according to claim 1, characterized in that The method of intercepting an image frame containing the inner hole of the oil cylinder barrel from the real-time monitoring video stream under the working environment of the hydraulic support comprises: The high-resolution camera installed on the hydraulic support can capture the working environment video stream inside the cylinder barrel in real time; Eliminating image jitter in the working environment video stream by using image stabilization technology to obtain a target working environment video stream; Using a motion estimation algorithm to detect dynamic changes in the inner hole area of ​​the oil cylinder barrel in the target working environment video stream to identify the appearance time of the inner hole of the oil cylinder barrel; Based on the occurrence time, synchronously intercepting a sample image frame containing multiple cylinder bores in the target working environment video stream; The target recognition algorithm is used to filter out the image frames containing the inner holes of the oil cylinder barrel from the sample image frames of the multiple inner holes of the oil cylinder barrel.

3. The method according to claim 1, characterized in that The step of applying high dynamic range imaging technology to adjust the contrast and brightness of the image frame to obtain a second image frame includes: The image frame is synthesized with image frames shot at different exposure levels by a high dynamic range synthesis algorithm to generate a high dynamic range image; Using a local tone mapping technique to adjust the local contrast of the high dynamic range image to obtain a target high dynamic range image; A global brightness correction algorithm is used to adjust the overall brightness of the target high dynamic range image to obtain a second image frame.

4. The method according to claim 3, characterized in that The method of using edge detection algorithm and threshold segmentation technology to identify and locate the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame includes: Applying an edge detection algorithm to process the second image frame to obtain edge information of the inner hole of the cylinder barrel, wherein the edge information includes a boundary of the inner hole of the cylinder barrel; Based on the edge information, a threshold segmentation technique is used to separate the inner hole area of ​​the oil cylinder barrel in the second image frame to obtain a segmentation result; Based on the segmentation result, a feature point detection algorithm is applied to identify key feature points in the second image frame to obtain key feature point information, wherein the key feature point information includes feature points inside the inner hole of the cylinder barrel; Based on the key feature point information, template matching technology is used to identify and locate the boundary of the inner hole of the cylinder barrel and the internal structure changes of the inner hole of the cylinder barrel in the second image frame.

5. The method according to claim 4, characterized in that The step of calculating the geometric deviation between the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame and the standard inner hole model of the oil cylinder barrel to obtain a geometric deviation result, wherein the geometric deviation result includes the defect position information of the inner hole of the oil cylinder barrel, including: Based on the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame, obtaining change information; Determine standard information of a preset standard oil cylinder bore model, align the standard information with the change information, and obtain the aligned actual structural change information, wherein the standard information includes size, shape, and position information; Inputting the actual structural change information into the preset standard cylinder bore model to obtain a geometric deviation value, wherein the geometric deviation includes differences in size, shape and position; The geometric deviation value calculation formula is as follows: ； ； in, Indicates actual structural change information Standard cylinder bore model The geometric deviation value between Indicates the volume of the inner hole of the cylinder barrel; Three-dimensional functions that represent information about actual structural changes; It is a three-dimensional function of the inner bore model of the standard oil cylinder; Represents the weight coefficient, which is used to balance different types of deviations; Indicates the actual structural change information in the direction The partial derivatives on ; Indicates that the standard model is in the direction The partial derivatives on ; Indicates the number of normal directions on the inner bore surface of the cylinder barrel; is an index variable, indicating different directions; Indicates Unit vectors in directions; Influencing parameters representing geometric deviation values; According to the geometric deviation value, a preset defect assessment standard is applied to determine whether there is a defect in the inner hole of the cylinder barrel, and a geometric deviation result is obtained.

6. The method according to claim 5, characterized in that The step of marking the defect position of the inner hole of the oil cylinder barrel in the second image frame according to the geometric deviation result and generating a detection report includes: Based on the geometric deviation result, marking the defect position of the inner hole of the cylinder barrel in the second image frame to obtain defect position information; Based on a preset defect classification standard, evaluating the defect severity of the defect position to obtain defect severity information, wherein the defect classification standard specifies defect categories corresponding to different geometric deviations; Obtaining a comprehensive analysis result based on the defect location information and the defect degree information; Based on the comprehensive analysis result, a test report including the comprehensive analysis result is generated, wherein the test report includes defect location, defect description, defect level and recommended repair measures.

7. The method according to claim 6, characterized in that Based on the preset defect classification standard, the defect severity of the defect position is evaluated to obtain defect severity information. The defect classification standard stipulates that the defect categories corresponding to different geometric deviations include: Define the severity of the defect; The calculation formula for the severity of the defect is as follows: ； in, Indicates the severity of the defect; represents the weight vector; is the eigenvector; bias term; is the geometric feature weight vector; is the geometric eigenvector; is the geometric feature bias term; is the texture feature weight vector; is the texture feature vector; is the texture feature bias term; is the edge feature weight vector; is the marginal eigenvector; is the edge feature bias term; Indicates the location information of the detected defect area; Defining a geometric feature vector in the defect severity, introducing a geometric feature expression, the geometric feature expression including: an area expression, a circularity expression, a depth expression and a direction expression of the defect area; The calculation formula of the geometric characteristic expression is as follows: ； ； ； ； in, Indicates the area of ​​the defect region; represents pixels in the defect area; Represents pixels Area occupied; Indicates the circularity of the defect area; is pi; Indicates the area of ​​the defect region; Indicates the perimeter of the defect area; Indicates the depth of the defect; Indicates the number of points at which depth is measured within the defect area; Indicates measurement points; Indicates Depth value of each measuring point; represents the cosine similarity between the defect direction and the standard direction, where is the orientation angle of the defect, is the standard direction angle; Indicates the location information of the detected defect area; Defining the edge feature vector in the defect severity, introducing the edge feature expression, the edge feature expression includes: the gradient intensity expression of the defect area, the curvature expression of the defect edge, the length expression of the defect edge and the discontinuity defect edge expression; The calculation formula of the edge feature expression is as follows: ； ； ； ； in, Indicates the gradient strength of the defect area; Represents the gradient of the image in the horizontal direction; Represents the gradient of the image in the vertical direction; Indicates the curvature of the defect edge; and Indicates the edge position with respect to the arc length The first derivative of ; and Indicates the edge position with respect to the arc length The second derivative of; arc length By parameterized curve definition; Indicates the length of the defect edge; and Respectively represent the positions of two adjacent points on the edge curve; Indicates the number of edge points; Represents two adjacent points and The Euclidean distance between represents the edge of the discontinuity defect, and Respectively represent the positions of two adjacent points on the edge curve; Indicates location The gray value at ; Indicates the location information of the detected defect area.

8. A hydraulic support cylinder bore defect detection system based on image processing, characterized in that: include: The acquisition module is used to intercept the image frame containing the inner hole of the cylinder barrel from the real-time monitoring video stream under the working environment of the hydraulic support; An adjustment module, used for adjusting the contrast and brightness of the image frame by applying a high dynamic range imaging technology to obtain a second image frame; An identification module, used to identify and locate the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame by using an edge detection algorithm and a threshold segmentation technology; a calculation module, used to calculate the geometric deviation between the boundary of the inner hole of the oil cylinder barrel and the internal structure change of the inner hole of the oil cylinder barrel in the second image frame and the standard inner hole model of the oil cylinder barrel, and obtain a geometric deviation result, wherein the geometric deviation result includes defect position information of the inner hole of the oil cylinder barrel; A generation module is used to mark the defect position of the inner hole of the cylinder barrel in the second image frame according to the geometric deviation result, and generate a detection report.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for detecting inner bore defects of a hydraulic support cylinder barrel based on image processing as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a method for detecting inner hole defects of a hydraulic support cylinder barrel based on image processing is implemented as described in any one of claims 1 to 7.

Images