Hydraulic support oil cylinder body welding deformation detection method and system based on image processing

Abstract

The invention provides a hydraulic support oil cylinder body welding deformation detection method and system based on image processing, and the method comprises the steps: obtaining image data, captured by a sensor, of a welding region of a hydraulic support oil cylinder body, and the image data comprises a first image before welding and a second image after welding is completed; key position information of the welding area is identified by applying a key point positioning technology; key position information of the first image and key position information of the second image are determined according to the key position information, so that the deformation degree of the hydraulic support oil cylinder body in the welding process is quantified, and a deformation quantification result is obtained; and according to the deformation quantification result, the deformation state of the welding area is monitored and recorded. According to the technical scheme, the precision and efficiency of deformation detection of the hydraulic support oil cylinder body in the welding process are improved, the labor cost is reduced, and the production safety is improved.

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 welding deformation of a hydraulic support cylinder body based on image processing. Background Art

[0002] The hydraulic support is one of the indispensable important devices in coal mining, and the welding quality of its cylinder body is directly related to the safety and service life of the hydraulic support. In the manufacturing process of the hydraulic support cylinder body, welding is a key process, and the quality of welding directly affects the performance and safety of the entire support.

[0003] Currently, the detection of welding deformation of the hydraulic support cylinder body mainly relies on manual visual inspection or traditional mechanical measuring tools, such as vernier calipers, micrometers, etc. These methods still have certain limitations in practical applications. The method of manual visual inspection is easily affected by the experience and subjective judgment of the operator, resulting in inconsistent detection results; traditional mechanical measuring tools are more cumbersome to operate and difficult to achieve full - range detection of complex welding structures. Summary of the Invention

[0004] The embodiments of the present invention provide a method and system for detecting welding deformation of a hydraulic support cylinder body based on image processing, so as to solve the problems of inconsistent detection results, cumbersome operation, and difficulty in achieving full - range detection of complex welding structures in the prior art.

[0005] In a first aspect, the embodiments of the present invention provide a method for detecting welding deformation of a hydraulic support cylinder body based on image processing, including: Obtaining sample image data of the welding area of the hydraulic support cylinder body captured by a sensor, where the image data includes a first image before welding and a second image after welding is completed; Applying key - point positioning technology to identify the key position information of the welding area in the sample image data; Determining the key position information of the first image and the key position information of the second image according to the key position information, so as to quantify the deformation degree of the hydraulic support cylinder body during the welding process and obtain a deformation quantification result; Monitoring and recording the deformation state of the welding area according to the deformation quantification result.

[0006] Optionally, the obtaining sample image data of the welding area of the hydraulic support cylinder body captured by a sensor, where the image data includes a first image before welding and a second image after welding is completed includes: Controlling the rotation angle of the sensor to ensure that the key welding parts of the hydraulic support cylinder body are all within the visible range of the sensor; Set the acquisition time interval or trigger condition of the sensor, acquire the image data within the welding area, and record the capture time and position information of the image data; Apply image stabilization technology and image stitching algorithm to process the image data to obtain sample image data.

[0007] Optionally, the application of key point location technology to identify the key position information of the welding area in the sample image data includes: Preprocess the sample image data to obtain target image data, where the target image data includes: the starting point of the weld, the midpoint of the weld, the weld center line, and the position of welding defects; Filter the key points in the target image data according to preset conditions; Use feature matching technology to match the key points with the key points in the feature library, determine the position information of the key points and the correlation between the key points and the position change, and obtain a matching result; Based on the matching result, construct a key position information model for the welding area; Optimize the key position information model through a machine learning algorithm, and output the position coordinates and descriptors of each key point in the welding area to obtain key position information, where the key position information includes the position information of the starting point of the weld, the position information of the end point of the weld, and the position information of the edge points of the welding area.

[0008] Optionally, the use of feature matching technology to match the key points with the key points in the feature library, determine the position information of the key points and the correlation between the key points and the position change, and obtain a matching result includes: Extract the descriptors of the key points, and based on the descriptors of the key points, construct a feature library, where the descriptor represents the local feature encoding for the key points in the first image and the second image, and the feature library includes the position information of preset key points and the descriptors of the position information of the preset key points; Use a feature matching algorithm to find the preset key points that match the key point descriptors in the feature library; Evaluate the reliability of the matching result to determine that the matched key points have a confidence level higher than a preset threshold; Determine the position change of the matched key points during the welding process and the correlation between the matched key points and the position change, and generate a matching result; Among them, the calculation formula for the correlation is as follows: ; Among them, represents the key point correlation coefficient; represents the variable of the welding process; Indicates the position change of key points .

[0009] Optionally, the method further includes: Defining variables for the welding process, where the variables include: welding temperature, welding speed, welding time, and current intensity; Among them, the calculation formula for the variables is as follows: ; Among them, represents a set of welding process states, and the set of welding process states contains multiple variables that describe the states at moments during the welding process; represents the temperature value at moment during the welding process; is the initial temperature at the start of welding; and are coefficients related to the characteristics of the welding equipment and materials; represents the speed at which the welding head moves during the welding process; represents the initial welding speed; and are coefficients related to the welding process; represents the time elapsed from the start of welding to moment; represents the current time; represents the time point when welding starts; represents the current magnitude of the current during the welding process at moment; is the initial current intensity, and are coefficients related to the characteristics of the welding equipment and materials.

[0010] Optionally, determining the key position information of the first image and the key position information of the second image according to the key position information to quantify the deformation degree of the hydraulic support cylinder barrel during the welding process, and the obtained deformation quantification result includes: Determining the key position information of the first image and the key position information of the second image according to the key position information; Comparing the key position information of the first image and the key position information of the second image to obtain a coordinate difference; Comparing the coordinate difference and calculating the displacement vector of each key point to quantify the deformation degree of the hydraulic support cylinder barrel during the welding process; Based on the coordinate difference, establishing a deformation quantification model to obtain a deformation quantification result.

[0011] Optionally, the deformation quantification result is used to monitor and record the deformation state of the welding area, and a deformation monitoring report is generated, including: Recording the deformation quantification result to form a record of the deformation state of the welding area changing with time; Based on the deformation state record, analyzing the deformation trend of the hydraulic support cylinder barrel during the welding process to obtain a deformation trend analysis result; Generating a deformation monitoring report, summarizing the deformation trend analysis result, and providing a summary description of the deformation quantification of the welding area.

[0012] In a second aspect, an embodiment of the present application provides a hydraulic support cylinder barrel welding deformation detection system based on image processing, including: An acquisition module for acquiring sample image data of the welding area of the hydraulic support cylinder barrel captured by a sensor, where the image data includes a first image before welding and a second image after welding is completed; An identification module for applying key point positioning technology to identify the key position information of the welding area in the sample image data; A quantification module for determining the key position information of the first image and the key position information of the second image according to the key position information to quantify the deformation degree of the hydraulic support cylinder barrel during the welding process and obtain a deformation quantification result; A monitoring module for monitoring and recording the deformation state of the welding area according to the deformation quantification result.

[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 a method for detecting the welding deformation of a hydraulic support cylinder barrel 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, a method for detecting the welding deformation of a hydraulic support cylinder barrel based on image processing according to any one of the first aspects is implemented.

[0015] In an embodiment of the present invention, image data of the welded area of the hydraulic support cylinder block captured by a sensor is obtained. The image data includes a first image before welding and a second image after welding is completed. The key point positioning technology is applied to identify the key position information of the welded area. The key position information of the first image and the key position information of the second image are determined according to the key position information, so as to quantify the deformation degree of the hydraulic support cylinder block during the welding process and obtain a deformation quantification result. According to the deformation quantification result, the deformation state of the welded area is monitored and recorded. The technical solution provided by the present invention improves the accuracy and efficiency of the deformation detection of the hydraulic support cylinder block during the welding process, reduces the labor cost, and improves the production safety.

[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 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 according to these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a method for detecting the welding deformation of a hydraulic support cylinder block 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 the welding deformation of a hydraulic support cylinder block 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 processes described in the specification, claims and above-mentioned drawings of the present invention, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be 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 such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than 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 belong to the scope of protection of the present invention.

[0022] The hydraulic support is an important support device in coal mining, and the welding quality of its cylinder body directly affects the safety and service life of the support. Existing welding deformation detection methods mostly rely on manual inspection or traditional mechanical measurement means, and these methods have problems such as low efficiency, low accuracy, and inability to achieve automation. Based on this, the present invention provides a method for detecting welding deformation of the cylinder body of a hydraulic support based on image processing, as Figure 1 , including: Step 101: Obtain image data of the welding area of the cylinder body of the hydraulic support captured by a sensor, where the image data includes a first image before welding and a second image after welding is completed; In this step, the sensor refers to a device for capturing images; the welding area refers to the part of the cylinder body of the hydraulic support that needs to be welded; the image data refers to the image information captured by the sensor, including an image file in digital form; the first image refers to the image data before welding; the second image refers to the image data after welding is completed.

[0023] In this step, before welding, a high-precision vision sensor is used to photograph the welding area of the cylinder body of the hydraulic support to obtain the first image data; after welding is completed, the same area is photographed again to obtain the second image data; ensure that the shooting conditions of the two images, such as light, angle, etc., are as consistent as possible for subsequent comparison.

[0024] Step 102: Apply key point positioning technology to identify the key position information of the welding area; In this step, the key point location technology refers to a technology used to identify specific points in an image, which is commonly used in fields such as image registration and feature matching; the key position information refers to the position point information in the welding area that is of great significance for detecting deformation.

[0025] In this step, a feature detection algorithm is used to detect significant feature points within the welding area from the first image and extract the descriptors of these feature points; similarly, the same feature point detection and descriptor extraction operations are performed on the second image; a feature matching algorithm is used to match the feature points of the first image with the feature points of the second image to determine the key position information of the key points.

[0026] Step 103: Determine the key position information of the first image and the second image according to the key position information to quantify the deformation degree of the cylinder body of the hydraulic support during the welding process and obtain a deformation quantification result; In this step, the deformation quantification result refers to the deformation degree of the cylinder body of the hydraulic support calculated by comparing the position differences of the key points before and after welding.

[0027] In this step, according to the key position information, determine the key position information of the first image and the second image, preliminarily estimate the deformation situation of the welding area, calculate the deformation quantification result, and combine the variables during the welding process to obtain the final deformation quantification result.

[0028] Step 104: Monitor and record the deformation state of the welding area according to the deformation quantification result; In this step, the deformation state refers to the shape change situation of the welding area before and after welding.

[0029] In this step, record the deformation quantification result and store it in the database for subsequent data analysis and quality monitoring; analyze the deformation quantification result, evaluate the influence of the welding process on the cylinder body of the hydraulic support, and provide a basis for improving the welding process; if the deformation quantification result exceeds the predetermined range, issue an alarm to prompt the operator to take measures.

[0030] The embodiments of the present invention can achieve the following beneficial effects through the above steps: Through image processing technology and key point location technology, the deformation situation of the welding area can be detected more accurately, with higher accuracy compared to traditional manual detection methods; Automatically obtain image data and, through analysis, reduce the need for manual intervention and improve the detection efficiency; Realize real-time monitoring of the deformation state of the welding area, timely discover and solve potential quality problems, and ensure the quality stability of the product; By recording and analyzing the deformation quantification results during each welding process, it provides rich data support for long-term quality management and process improvement, and helps to further improve the level of welding technology.

[0031] In modern manufacturing, ensuring welding quality is crucial for improving product performance and safety. The welding of the hydraulic support cylinder block is particularly important, and any welding defect may lead to serious safety hazards. Based on this, the present invention provides a specific embodiment. In step 101, sample image data of the welding area of the hydraulic support cylinder block captured by a sensor is obtained. The image data includes a first image before welding and a second image after welding is completed, and specifically includes the following steps: Step 111: Control the rotation angle of the sensor to ensure that the key welding parts of the hydraulic support cylinder block are all within the visible range of the sensor; In this step, the rotation angle refers to adjusting the angle or position of the sensor so that it can cover the target area to be observed; in this embodiment, it refers to adjusting the angle of the camera to ensure that the key welding parts are within the visible range of the sensor.

[0032] In this step, the sensor is installed around the hydraulic support cylinder block to ensure that the sensor can cover the entire welding area; by controlling the rotation mechanism of the sensor, its viewing angle is adjusted to ensure that the key welding parts of the hydraulic support cylinder block are all within the visible range of the sensor. This step can be achieved by presetting the rotation angle or manually adjusting through a software interface; a preliminary test is carried out to ensure that all key parts can clearly appear in the sensor's field of view, and necessary calibration is carried out to ensure the image quality.

[0033] Step 112: Set the acquisition time interval or trigger condition of the sensor, acquire the image data within the welding area, and record the capture time and position information of the image data; In this step, the acquisition time interval refers to the frequency at which the sensor repeatedly acquires images within a certain period of time; the trigger condition refers to the act of starting image acquisition based on the occurrence of certain specific events.

[0034] For example, according to the characteristics of the welding process, the acquisition time interval of the sensor for acquiring images is preset in advance, such as setting to acquire once per second or once every 5 seconds, to ensure that the key moments before and after welding can be captured; while acquiring images, the capture time and position information of each image are recorded so that the image can be accurately associated with its corresponding welding state during subsequent analysis.

[0035] Step 113: Apply image stabilization technology and image stitching algorithms to process the image data to obtain sample image data; In this step, image stabilization technology refers to the technology used to reduce image blurring and jitter, improve image quality. Common image stabilization technologies include feature point-based image stabilization algorithms; image stitching algorithms refer to the technology used to merge multiple partially overlapping images into a complete image. Common image stitching algorithms include feature matching-based image stitching technology.

[0036] For example, using a feature point-based image stabilization algorithm to reduce image blurring caused by sensor movement or external vibration, ensuring the clarity of each frame of the image; applying a feature matching-based image stitching technology to stitch multiple frames of images into a complete image, ensuring the integrity of the entire welding area; after the above processing, sample image data is obtained, including the first image before welding and the second image after welding is completed. These image data will be used for subsequent key point positioning and deformation quantification analysis.

[0037] The embodiments of the present invention can achieve the following beneficial effects through the above steps: By adjusting the rotation angle of the sensor, ensure that all key welding parts are within the visible range, avoiding the omission of important information due to angle limitations; Set the acquisition time interval or trigger condition of the sensor, and record the capture time and position information, ensuring the time synchronization of the image data, which is convenient for subsequent analysis; Apply image stabilization technology and image stitching algorithms to improve the quality of the image data, ensure the clarity and integrity of the image, and provide a reliable data basis for subsequent analysis.

[0038] After obtaining the sample image data, it is necessary to process it to extract effective information. Based on this, the present invention provides a specific embodiment. In step 102, the key point positioning technology is applied to identify the key position information of the welding area in the sample image data, which specifically includes the following steps: Step 201: Preprocess the sample image data to obtain target image data, where the target image data includes: the starting point of the weld, the midpoint of the weld, the weld center line, and the position of welding defects; In this step, various preprocessing methods improve the quality of the sample image data. For example, applying the Gaussian filtering algorithm to remove noise in the image, enhancing the image contrast through histogram equalization technology to make the feature points more prominent; converting the color image to a grayscale image to simplify subsequent processing steps; using the Harris corner detection algorithm to identify the starting point of the weld, the midpoint of the weld, the weld center line, and the position of welding defects, and mark them; integrating the above feature point information together to form the target image data.

[0039] Step 202: Screen the key points in the target image data according to preset conditions; In this step, key points refer to points with obvious features, which can be used for image matching and positioning. In this embodiment, the key points refer to specific position points in the welding area, such as the starting point of the weld seam, the ending point of the weld seam, etc.

[0040] In this step, it is preset which feature points are key points, such as the starting point of the weld seam, the ending point of the weld seam, specific points on the center line, etc.; according to the preset conditions, the key points that meet the conditions are screened out from the target image data.

[0041] Step 203: Use feature matching technology to match the key points with the key points in the feature library, determine the position information of the key points and the correlation between the key points and the position change, and obtain a matching result; In this step, feature matching technology refers to a technology for finding corresponding points between two images. Common methods include Scale-Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), etc.

[0042] For example, extract descriptors for each key point in the target image data for feature matching; use the Speeded-Up Robust Features technology to find points in the feature library whose similarity to the key point descriptor is higher than the preset threshold; record the position information of the key points in the matching result; analyze the position changes of the matched key points in different images to determine their correlation.

[0043] Step 204: Based on the matching result, construct a key position information model for the welding area; For example, according to the matching result, construct a model to describe the state of the welded joint, and this model can distinguish normal weld seams and weld seams with defects.

[0044] Step 205: Optimize the key position information model through a machine learning algorithm, and output the position coordinates and descriptors of each key point in the welding area to obtain key position information, where the key position information includes the position information of the starting point of the weld seam, the position information of the ending point of the weld seam, and the position information of the edge points of the welding area; In this step, the machine learning algorithm refers to a technology for predicting unknown data by training a model; in this embodiment, it is used to optimize the key position information model to make it more accurately reflect the actual state of the welding area; the descriptor refers to a vector used to describe the features of a certain point in an image for feature matching; in this embodiment, the descriptor is used to represent the features of the key points in the welding area.

[0045] For example, use a deep neural network to optimize the key position information model to make it more accurately reflect the actual state of the welding area; output the position coordinates and their descriptors of each key point in the welding area, including the position information of the starting point of the weld seam, the position information of the ending point of the weld seam, and the position information of the edge points of the welding area.

[0046] The embodiments of the present invention can achieve the beneficial effects through the above steps as follows: Through preprocessing and feature matching techniques, the quality of image data is improved, making the extraction of key position information more accurate; By using feature matching techniques and machine learning algorithms, the automatic extraction and optimization of key position information are realized, reducing the need for manual intervention and improving the detection efficiency; The output key position information provides detailed data support for subsequent deformation quantification; By optimizing the key position information model through machine learning algorithms, the accuracy and robustness of the model are improved, enhancing the adaptability of the system.

[0047] To further analyze the key points to accurately capture the minute position change information during the welding process. Based on this, the present invention provides a specific embodiment. In step 203, the feature matching technique is used to match the key points with the key points in the feature library, determine the position information of the key points and the correlation between the key points and the position change, and obtain the matching result, which specifically includes the following steps: Step 231: Extract the descriptors of the key points, and based on the descriptors of the key points, construct a feature library, where the descriptor represents the local feature encoding of the key points in the first image and the second image, and the feature library includes the position information of the preset key points and the descriptors of the position information of the preset key points; In this step, the feature library refers to a data set that stores a series of known key points and their descriptors; For example, after identifying several key points around the weld seam, the SIFT algorithm is used to extract the descriptors of these key points, and these descriptors represent the state of the parts before welding. Based on these descriptors, a feature library is established, which contains the position information of the key points around the weld seam before welding and their descriptors, and this feature library will be used as a reference standard.

[0048] Step 233: Use the feature matching algorithm to find the preset key points in the feature library that match the key point descriptors; For example, extract the key point descriptors with the same positions as the key points around the weld seam before welding from the second image, and use the ORB algorithm to find the key points in the feature library with a matching degree higher than the preset threshold for these descriptors.

[0049] Step 234: Evaluate the reliability of the matching result to determine that the matched key points have a confidence level higher than the preset threshold; In this step, the confidence level refers to the credibility of the matching result; in this embodiment, if the matched key points have a confidence level higher than the preset threshold, the matching result is considered reliable.

[0050] For example, a confidence threshold is preset at 90%. Only when the matching score exceeds this threshold is the matching considered reliable; for matches below the threshold, they are marked as suspicious and further inspected.

[0051] Step 235: Determine the position change of the key points of the match during the welding process and the correlation between the key points of the match and the position change, and generate a matching result; Among them, the calculation formula for the correlation is as follows: ; Among them, represents the correlation coefficient of the key point ; represents the variable of the welding process; represents the key point of the position change; In this step, the position change refers to the change in the position of the same key point in the image before and after welding; the correlation refers to the degree of mutual dependence between two variables; in this embodiment, the relationship between the position change of the key point and the variable in the welding process.

[0052] For each reliable match in this step, calculate the position change of this key point before and after welding; use the correlation formula to calculate the relationship between these position changes and the variables in the welding process. For example, it is calculated that the faster the welding speed, the greater the position change of key point A.

[0053] The embodiments of the present invention can achieve the following beneficial effects through the above steps: It is beneficial for engineers to better understand the possible displacements during the welding process and improve production safety; Predict the welding quality, discover potential problem points in advance, and thus improve the welding quality and production efficiency; Improve the automation level of detection and achieve real-time monitoring of welding quality.

[0054] Welding is a key link in industrial production, and its quality directly affects the performance and safety of products. In order to ensure the consistency and reliability of welding, it is necessary to strictly control each key parameter during the welding process. Based on this, the present invention provides a specific embodiment. In step 235, determine the position change of the key points of the match during the welding process and the correlation between the key points of the match and the position change, and generate a matching result. Specifically, it further includes the following steps: Step 241: Define the variables of the welding process, and the variables include: welding temperature, welding speed, welding time, and current intensity; Among them, the calculation formula for the variables is as follows: ; Among them, represents a set of welding process states, and the set of welding process states contains multiple variables that describe the states at moments during the welding process; represents the temperature value at moment during the welding process; is the initial temperature at the start of welding; and are coefficients related to the characteristics of the welding equipment and materials; represents the speed of the welding head movement during the welding process; represents the initial welding speed; and are coefficients related to the welding process; represents the time elapsed from the start of welding to moment; represents the current time; represents the time point when welding starts; represents the current magnitude of the current during the welding process at moment; is the initial current intensity, and are coefficients related to the characteristics of the welding equipment and materials.

[0055] This step describes the state of the welding process by defining four variables during the welding process and combining them into a set of welding process states. In this way, the deformation of the cylinder body of the hydraulic support during the welding process can be more intuitively reflected, and the welding process can be optimized accordingly.

[0056] The embodiments of the present invention can achieve the beneficial effects as follows through the above steps: Defining and strictly controlling these variables can help optimize the welding process, making the strength, toughness, and corrosion resistance of the welded joint reach the best state, thereby improving the overall quality of the final product; By precisely controlling the temperature, speed, time, and current intensity during the welding process, product defects caused by improper welding can be reduced, the scrap rate can be lowered, and raw materials and production costs can be saved; Clear setting of welding parameters helps to maintain the consistency and repeatability of the process, and a stable welding effect can be maintained even between different operators or different equipment; Reasonably setting the welding speed and time can balance the welding quality and production efficiency, avoiding low efficiency caused by being too slow or quality problems caused by being too fast; Controlling the welding temperature is not only to ensure the welding quality, but also helps to protect the safety of the operators and prevent adverse effects on health caused by high temperature; When welding problems occur, possible causes can be found by reviewing the variable settings during the welding process, which facilitates quickly locating the problem and taking corresponding adjustment or improvement measures.

[0057] The thermal stress generated during the welding process will cause deformation of the workpiece, which not only affects the appearance but may also pose a safety hazard. Therefore, it is particularly important to accurately measure and analyze the deformation caused by welding. Based on this, the present invention provides a specific embodiment. In step 103, according to the key position information, determine the key position information of the first image and the key position information of the second image to quantify the deformation degree of the cylinder body of the hydraulic support during the welding process and obtain a deformation quantification result, which specifically includes the following steps: Step 301: According to the key position information, determine the key position information of the first image and the key position information of the second image; For example, in the first image, the starting coordinate of the weld seam is while in the second image, the coordinate of the same starting point of the weld seam is .

[0058] Step 302: Compare the key position information of the first image and the key position information of the second image to obtain a coordinate difference; In this step, the coordinate difference refers to the position difference of the same key point in the image coordinate system between the first image and the second image.

[0059] For example, compare the coordinate of the starting point of the weld seam in the first image with the coordinate of the same starting point of the weld seam in the second image, and calculate that the coordinate difference of the starting point of the weld seam is , .

[0060] Step 303: Compare the coordinate differences, calculate the displacement vectors of each key point to quantify the deformation degree of the cylinder body of the hydraulic support during the welding process; In this step, the displacement vector refers to the position change of the key point before and after welding, usually represented by a two-dimensional or three-dimensional vector, including direction and magnitude.

[0061] In this step, for each matched key point, calculate its displacement vector, that is, the coordinate difference vector or ; count the displacement vectors of all key points and analyze the deformation of the cylinder body of the hydraulic support during the welding process. For example, if the displacement vectors of multiple key points point in the same direction and have similar magnitudes, it indicates that the cylinder body of the hydraulic support has undergone uniform deformation during the welding process.

[0062] Step 304: Based on the coordinate differences, establish a deformation quantification model to obtain a deformation quantification result; In this step, the deformation quantification model refers to a mathematical model used to describe and quantify the deformation degree of the cylinder body of the hydraulic support cylinder during the welding process; the deformation quantification result refers to the specific value of the deformation degree of the cylinder body of the hydraulic support cylinder during the welding process obtained by analyzing the coordinate difference and displacement vector.

[0063] This step is based on the coordinate difference and displacement vector to establish a deformation quantification model, which can be a simple linear model or a complex non-linear model, used to describe the deformation law of the cylinder body of the hydraulic support cylinder during the welding process; through the calculation of the deformation quantification model, the deformation quantification result is obtained, specifically including the displacement magnitude and direction of each key point, as well as the overall deformation degree.

[0064] For example, this embodiment provides a more specific method for calculating the deformation quantification result. Among them, the deformation quantification result calculation formula is as follows: ; Wherein, represents the deformation quantification result; represents the number of all key points; represents the th key point's deformation degree; represents the influence factor of multiple variables on the deformation during the welding process; represents the temperature value at the moment during the welding process; represents the speed of the welding head movement during the welding process; represents the time elapsed from the start of welding to the moment; represents the current magnitude at the moment during the welding process; represents the displacement vector of the th key point; represents the sum of the influence of the th key point by other key points except itself; is the weight between key point and key point , reflecting the interaction strength between key point and key point ; represents the coordinate difference of key point .

[0065] The embodiments of the present invention can achieve the following beneficial effects through the above steps: By calculating the coordinate difference and analyzing the displacement vector, the deformation degree of the cylinder body of the hydraulic support cylinder during the welding process can be more accurately quantified, improving the detection accuracy; The output deformation quantization results provide detailed deformation information, including the displacement magnitude and direction of each key point, providing a scientific basis for subsequent quality management and process improvement; Through the quantitative analysis of the deformation degree of the hydraulic support cylinder body during the welding process, problems existing in the welding process can be discovered in a timely manner, process parameters can be optimized, and welding quality can be improved; By establishing a deformation quantization model, the deformation situation during the welding process can be better represented and controlled, thereby strengthening production management and ensuring the consistency of product quality.

[0066] To provide a scientific basis and a summary description for the optimization of the welding process, based on this, the present invention provides a specific embodiment. In step 104, according to the deformation quantization results, the deformation state of the welding area is monitored and recorded, which specifically includes the following steps: Step 401: Record the deformation quantization results to form a record of the deformation state of the welding area changing with time; This step stores the deformation quantization results obtained each time to form a record of the deformation state in a time series.

[0067] Step 402: Based on the deformation state record, analyze the deformation trend of the hydraulic support cylinder body during the welding process to obtain a deformation trend analysis result; This step statistically analyzes the data in the deformation state record to observe the variation law of the deformation quantity with time; by analyzing the data, identify whether there is a certain deformation pattern or law, such as whether the deformation increases linearly or non-linearly with time; extract the analysis results, including statistical data such as the maximum value, minimum value, and average value of the deformation, as well as a graphical representation of the deformation trend.

[0068] Step 403: Generate a deformation monitoring report, summarize the deformation trend analysis results, and provide a summary description of the deformation quantization of the welding area; This step prepares a deformation monitoring report based on the deformation trend analysis results; add charts and curves of the deformation trend to the report for easy understanding by the reader; summarize the results of the deformation trend analysis in the report and put forward possible reasons and suggestions.

[0069] The embodiments of the present invention can achieve the following beneficial effects through the above steps: The deformation state record and the trend analysis results help engineers discover problems in a timely manner, adjust welding parameters, and improve welding quality; By analyzing the deformation trend, possible welding failures can be predicted, and measures can be taken in advance to reduce the scrap rate; The deformation monitoring report provides detailed analysis results, which helps process optimization and makes the production process more stable and reliable; Detailed deformation quantification records provide a solid data foundation for subsequent product design and manufacturing.

[0070] Figure 2 This application provides a structural schematic diagram of a hydraulic support cylinder body welding deformation detection system based on image processing for the embodiments of the present application. As Figure 2 shown, the system includes: An acquisition module 21, configured to acquire sample image data of the welding area of the hydraulic support cylinder body captured by a sensor, where the image data includes a first image before welding and a second image after welding is completed; An identification module 22, configured to apply key point positioning technology to identify the key position information of the welding area in the sample image data; A quantification module 23, configured to determine the key position information of the first image and the key position information of the second image according to the key position information, so as to quantify the deformation degree of the hydraulic support cylinder body during the welding process and obtain a deformation quantification result; A monitoring module 24, configured to monitor and record the deformation state of the welding area according to the deformation quantification result.

[0071] Figure 2 The described hydraulic support cylinder body welding deformation detection system based on image processing can execute Figure 1 the described hydraulic support cylinder body welding deformation detection method in the embodiments shown. The implementation principle and technical effects will not be elaborated further. For the above-mentioned hydraulic support cylinder body welding deformation detection system in the embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0072] Figure 2 The described hydraulic support cylinder body welding deformation detection in the embodiments shown can be implemented as a computing device. As Figure 3 shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component 32.

[0073] The processing component 32 is configured to: obtain sample image data of the welded area of the hydraulic support cylinder block captured by the sensor, where the image data includes a first image before welding and a second image after welding is completed; apply key-point positioning technology to identify the key position information of the welded area in the sample image data; determine the key position information of the first image and the key position information of the second image according to the key position information to quantify the deformation degree of the hydraulic support cylinder block during the welding process, and obtain a deformation quantification result; monitor and record the deformation state of the welded area according to the deformation quantification result.

[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 (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), 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 the cloud computing platform.

[0080] An embodiment of the present invention also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 shown embodiment of a method for detecting welding deformation of a hydraulic support cylinder block based on image processing.

[0081] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above 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 solutions, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable 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 and are not intended 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 the embodiments of the present invention.

Claims

1. A method for detecting welding deformation of a hydraulic support cylinder body based on image processing, characterized in that: include: Acquire sample image data of a welding area of ​​a hydraulic support cylinder body captured by a sensor, wherein the sample image data includes a first image before welding and a second image after welding; Using key point positioning technology to identify key position information of the welding area in the sample image data; Determine the key position information of the first image and the key position information of the second image according to the key position information, so as to quantify the deformation degree of the cylinder body of the hydraulic support during welding, and obtain the deformation quantification result; According to the deformation quantification result, the deformation state of the welding area is monitored and recorded.

2. The method according to claim 1, characterized in that The acquiring of sample image data of the welding area of ​​the hydraulic support cylinder body captured by the sensor, wherein the image data includes a first image before welding and a second image after welding, includes: Control the sensor's rotation angle of view to ensure that the key welding parts of the hydraulic support cylinder body are within the sensor's visual range; Setting a collection time interval or trigger condition of the sensor to collect image data in the welding area, and recording the capture time and position information of the image data; The image data is processed by applying image stabilization technology and image stitching algorithm to obtain sample image data.

3. The method according to claim 2, characterized in that The key position information of the welding area in the sample image data identified by the key point positioning technology includes: Preprocessing the sample image data to obtain target image data, wherein the target image data includes: a starting point of a weld, a midpoint of a weld, a center line of a weld, and a position of a welding defect; Filter key points in the target image data according to preset conditions; Matching the key points with the key points in the feature library using feature matching technology, determining the position information of the key points and the correlation between the key points and the position change, and obtaining a matching result; Based on the matching results, construct a key position information model of the welding area; The key position information model is optimized by a machine learning algorithm, and the position coordinates and descriptors of each key point in the welding area are output to obtain key position information, wherein the key position information includes the position information of the starting point of the weld, the position information of the end point of the weld, and the position information of the edge points of the welding area.

4. The method according to claim 3, characterized in that The use of feature matching technology to match the key points with the key points in the feature library, determining the position information of the key points and the correlation between the key points and the position change, and obtaining the matching results includes: Extracting descriptors of the key points, and constructing a feature library based on the descriptors of the key points, wherein the descriptors represent local feature codes for the key points in the first image and the second image, and the feature library includes position information of preset key points and descriptors of the position information of the preset key points; Using a feature matching algorithm, searching for a preset key point matching the key point descriptor in the feature library; Evaluate the reliability of the matching results and determine whether the matched key points have a confidence level higher than a preset threshold; Determine the position change of the matched key point during the welding process and the correlation between the matched key point and the position change, and generate a matching result; The calculation formula of the correlation is as follows: ； in, Indicates key points The correlation coefficient of Variables representing the welding process; Indicates key points position changes.

5. The method according to claim 4, characterized in that The method further comprises: Defining welding process variables, the variables including welding temperature, welding speed, welding time and current intensity; The calculation formula of the variables is as follows: ； in, Represents a welding process state set, which contains multiple descriptions of the welding process The state variables at the moment; Indicates the welding process Temperature value at the moment; is the initial temperature at the start of welding; and is a coefficient related to welding equipment and material characteristics; Indicates the speed at which the welding head moves during welding; Indicates the initial welding speed; and is a coefficient related to the welding process; From welding to the time elapsed by a moment; Indicates the current time; Indicates the time point when welding starts; Indicates the welding process The current magnitude at the moment; is the initial current intensity, and is a coefficient related to welding equipment and material characteristics.

6. The method according to claim 3, characterized in that Determining the key position information of the first image and the key position information of the second image according to the key position information to quantify the deformation degree of the cylinder body of the hydraulic support during welding to obtain the deformation quantification result includes: Determining key position information of the first image and key position information of the second image according to the key position information; Comparing the key position information of the first image with the key position information of the second image to obtain a coordinate difference; By comparing the coordinate differences, the displacement vectors of the key points are calculated to quantify the degree of deformation of the hydraulic support cylinder body during the welding process; Based on the coordinate difference, a deformation quantification model is established to obtain a deformation quantification result.

7. The method according to claim 6, characterized in that The deformation quantification results monitor and record the deformation state of the welding area and generate a deformation monitoring report including: Recording the deformation quantification results to form a deformation state record of the welding area changing with time; Based on the deformation state record, the deformation trend of the hydraulic support cylinder body during the welding process is analyzed to obtain a deformation trend analysis result; A deformation monitoring report is generated, summarizing the deformation trend analysis results and providing a summary description of the deformation quantification of the weld area.

8. A hydraulic support cylinder body welding deformation detection system based on image processing, characterized in that: include: An acquisition module, used to acquire sample image data of a welding area of ​​a hydraulic support cylinder body captured by a sensor, wherein the image data includes a first image before welding and a second image after welding; An identification module, used for identifying key position information of the welding area in the sample image data by applying key point positioning technology; A quantification module, used to determine the key position information of the first image and the key position information of the second image according to the key position information, so as to quantify the deformation degree of the cylinder body of the hydraulic support during welding and obtain a deformation quantification result; The monitoring module is used to monitor and record the deformation state of the welding area according to the deformation quantification result.

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 hydraulic support cylinder body welding deformation detection method 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 welding deformation of a hydraulic support cylinder body based on image processing as described in any one of claims 1 to 7 is implemented.

Images