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

Abstract

The application provides a hydraulic support oil cylinder body welding deformation detection method and system based on image processing, wherein, in the embodiment of the application, image data of a welding area of a hydraulic support oil cylinder body captured by a sensor is obtained, the image data includes a first image before welding and a second image after welding is completed; a key point positioning technology is applied to identify key position information of the welding 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 oil cylinder body in the welding process and obtain a deformation quantization result; and according to the deformation quantization result, the deformation state of the welding area is monitored and recorded. The technical scheme provided by the application improves the precision and efficiency of the deformation detection of the hydraulic support oil cylinder body in the welding process, reduces the labor cost, and improves the production safety.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of industrial image processing, and particularly relates to a hydraulic support oil cylinder body welding deformation detection method and system based on image processing. BACKGROUND

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

[0003] At present, the detection of the welding deformation of the hydraulic support oil cylinder body mainly depends on manual visual inspection or traditional mechanical measuring tools, such as vernier caliper, micrometer and the like. These methods still have certain limitations in actual application. The manual visual inspection method is easily affected by the experience and subjective judgment of the operator, resulting in inconsistent detection results; the traditional mechanical measuring tools are relatively cumbersome in operation, and it is difficult to realize the all-around detection of the complex welding structure. SUMMARY

[0004] The embodiment of the present application provides a hydraulic support oil cylinder body welding deformation detection method and system based on image processing, to solve the problems of inconsistent detection results, cumbersome operation and difficult to realize all-around detection of the complex welding structure in the prior art.

[0005] In a first aspect, the embodiment of the present application provides a hydraulic support oil cylinder body welding deformation detection method based on image processing, comprising:

[0006] Acquiring sample image data of a welding area of a hydraulic support oil cylinder body captured by a sensor, the image data comprising a first image before welding and a second image after welding is completed;

[0007] Applying a key point positioning technology to identify key position information of the welding area in the sample image data;

[0008] According to the key position information, determining the key position information of the first image and the key position information of the second image, to quantify the deformation degree of the hydraulic support oil cylinder body in the welding process, and obtaining a deformation quantization result;

[0009] According to the deformation quantization result, monitoring and recording the deformation state of the welding area.

[0010] Optionally, the acquiring sample image data of a welding area of a hydraulic support oil cylinder body captured by a sensor, the image data comprising a first image before welding and a second image after welding is completed comprises:

[0011] The rotation angle of the sensor is controlled to ensure that the key welding positions of the hydraulic support oil cylinder body are within the visual range of the sensor.

[0012] The image data of the welding area is collected, and the capture time and position information of the image data are recorded.

[0013] The image data is processed using image stabilization technology and image stitching algorithms to obtain sample image data.

[0014] Optionally, the application of key point positioning technology to identify the key position information of the welding area in the sample image data includes:

[0015] The sample image data is preprocessed to obtain target image data, which includes the start point of the weld, the midpoint of the weld, the weld centerline, and the welding defect position.

[0016] The key points in the target image data are filtered according to a preset condition.

[0017] The key points are matched with key points in a feature library using feature matching technology to determine the position information of the key points and the correlation of the key points with position changes, obtaining a matching result.

[0018] Based on the matching result, a key position information model of the welding area is constructed.

[0019] The key position information model is optimized through a machine learning algorithm, and the position coordinates and descriptors of each key point in the welding area are output, obtaining key position information, which includes the position information of the start 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.

[0020] Optionally, the matching of the key points with key points in the feature library using feature matching technology to determine the position information of the key points and the correlation of the key points with position changes, obtaining a matching result includes:

[0021] The descriptors of the key points are extracted, and a feature library is constructed based on the descriptors of the key points, wherein the descriptors represent local feature encodings 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.

[0022] Using feature matching algorithms, the feature library is searched for preset key points that match the key point descriptors.

[0023] The reliability of the matching result is evaluated to determine that the matched key points have a confidence level higher than a preset threshold.

[0024] determining a position change of the matched key points in the welding process and a correlation of the matched key points and the position change, to generate a matching result;

[0025] wherein, the correlation is calculated according to the following formula:

[0026] ;

[0027] wherein, represents a correlation coefficient of the key point ; represents a variable of the welding process; represents a position change of the key point .

[0028] Optionally, the method further comprises:

[0029] defining a variable of the welding process, wherein the variable comprises a welding temperature, a welding speed, a welding time and a current intensity;

[0030] wherein, the variable is calculated according to the following formula:

[0031] ;

[0032] wherein, represents a set of welding process states, wherein the set of welding process states comprises a plurality of variables describing states at a moment in the welding process; represents a temperature value at a moment in the welding process; is an initial temperature at the beginning of the welding; and are coefficients related to the characteristics of the welding equipment and materials; represents a speed of the welding head movement in the welding process; represents an initial welding speed; and are coefficients related to the welding process; represents a time experienced from the beginning of the welding to the moment ; represents a current time; represents a time point at which the welding starts; represents a current intensity at a moment in the welding process; represents an initial current intensity, and are coefficients related to the characteristics of the welding equipment and materials.

[0033] ​​​Optionally, the 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 oil cylinder body in the welding process to obtain a deformation quantization result comprises:

[0034] According to the key position information, the key position information of the first image and the key position information of the second image are determined.

[0035] The key position information of the first image and the key position information of the second image are compared to obtain a coordinate difference.

[0036] The coordinate difference is compared, and a displacement vector of each key point is calculated to quantify the deformation degree of the hydraulic support oil cylinder body in the welding process.

[0037] Based on the coordinate difference, a deformation quantization model is established to obtain a deformation quantization result.

[0038] Optionally, the deformation quantization result, the deformation state of the welding area is monitored and recorded, and a deformation monitoring report is generated, comprising:

[0039] The deformation quantization result is recorded to form a deformation state record of the welding area over time.

[0040] Based on the deformation state record, the deformation trend of the hydraulic support oil cylinder body in the welding process is analyzed to obtain a deformation trend analysis result.

[0041] A deformation monitoring report is generated, the deformation trend analysis result is summarized, and a summary description about the deformation quantization of the welding area is provided.

[0042] In a second aspect, the embodiments of the present application provide a hydraulic support oil cylinder body welding deformation detection system based on image processing, comprising:

[0043] An acquisition module is configured to acquire sample image data of a welding area of a hydraulic support oil cylinder body captured by a sensor, wherein the image data comprises a first image before welding and a second image after welding is completed.

[0044] An identification module is configured to identify key position information of the welding area in the sample image data by applying a key point positioning technology.

[0045] A quantization module is 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 to quantify the deformation degree of the hydraulic support oil cylinder body in the welding process to obtain a deformation quantization result.

[0046] A monitoring module is configured to monitor and record the deformation state of the welding area according to the deformation quantization result.

[0047] In a third aspect, an embodiment of the present application provides a computing device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the image processing-based hydraulic support oil cylinder body welding deformation detection method according to any one of the first aspect.

[0048] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the image processing-based hydraulic support oil cylinder body welding deformation detection method according to any one of the first aspect.

[0049] In the embodiment of the present application, image data of a welding area of a hydraulic support oil cylinder body captured by a sensor is obtained, the image data includes a first image before welding and a second image after welding is completed; a key point positioning technology is applied to identify key position information of the welding 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 oil cylinder body in the welding process, and a deformation quantization result is obtained; and the deformation state of the welding area is monitored and recorded according to the deformation quantization result. The technical solution provided by the present application improves the precision and efficiency of the deformation detection of the hydraulic support oil cylinder body in the welding process, reduces the labor cost, and improves the production safety.

[0050] These aspects or other aspects of the present application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0052] Figure 1 A flow chart of the image processing-based hydraulic support oil cylinder body welding deformation detection method provided by the embodiment of the present application is shown in the figure;

[0053] Figure 2 A structural schematic diagram of the image processing-based hydraulic support oil cylinder body welding deformation detection system provided by the embodiment of the present application is shown in the figure;

[0054] Figure 3 A structural schematic diagram of the computing device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0055] In order to better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application.

[0056] In some of the processes described in this specification, including the description of the drawings and the claims, operations in the processes are not necessarily performed in the order in which they appear. The operations in the processes are not necessarily performed in the order in which they appear in the text. The order of the operations can be changed, and operations can be performed in parallel or in series. Also, some of the processes described in this specification can include more or fewer operations than those described. Furthermore, some of the processes described in this specification can include operations in addition to those described. The description of the first, second, etc. message, device, module, etc. is merely used to distinguish the different messages, devices, modules, etc. and does not limit the order of the first and second.

[0057] The technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0058] The hydraulic support is an important supporting device in coal mining, and the welding quality of the oil cylinder body directly affects the safety and service life of the support. The existing welding deformation detection methods mostly rely on manual inspection or traditional mechanical measurement methods, and these methods have problems such as low efficiency, low precision and inability to realize automation. Based on this, the present application provides a hydraulic support oil cylinder body welding deformation detection method based on image processing, as shown in Figure 1 , comprising:

[0059] Step 101: Obtain image data of the welding area of the hydraulic support oil cylinder body captured by the sensor, the image data comprising a first image before welding and a second image after welding is completed;

[0060] In this step, the sensor refers to a device for capturing images; the welding area refers to the part that needs to be welded on the hydraulic support oil cylinder body; the image data refers to the image information captured by the sensor, including digital image files; the first image refers to the image data before welding; and the second image refers to the image data after welding is completed.

[0061] This step uses a high-precision visual sensor to capture the welding area of the hydraulic support oil cylinder body before welding, obtaining first image data; after welding is completed, the same area is captured again to obtain second image data; ensure that the shooting conditions of the two images, such as light and angle, are as consistent as possible for subsequent comparison.

[0062] Step 102: Apply key point positioning technology to identify key position information of the welding area.

[0063] In this step, key point positioning technology refers to a technology for identifying specific points in an image, commonly used in image registration and feature matching fields; key position information refers to position point information in the welding area that is important for detecting deformation.

[0064] This step uses feature detection algorithms to detect significant feature points in the welding area from the first image and extract descriptors of these feature points; similarly, the same feature point detection and descriptor extraction operations are performed on the second image; using feature matching algorithms, the feature points of the first image are matched with the feature points of the second image to determine the key position information of the key points.

[0065] 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 hydraulic support oil cylinder body during welding, obtaining deformation quantization results.

[0066] In this step, deformation quantization results refer to the deformation degree of the hydraulic support oil cylinder body calculated by comparing the position differences of key points before and after welding.

[0067] This step determines the key position information of the first image and the second image according to the key position information, preliminarily estimates the deformation of the welding area, calculates the deformation quantization results, and combines the variables in the welding process to obtain the final deformation quantization results.

[0068] Step 104: Monitor and record the deformation state of the welding area according to the deformation quantization results.

[0069] In this step, the deformation state refers to the shape change of the welding area before and after welding.

[0070] This step records the deformation quantization results and stores them in the database for subsequent data analysis and quality monitoring; analyzes the deformation quantization results to evaluate the impact of the welding process on the hydraulic support oil cylinder body, providing a basis for improving the welding process; if the deformation quantization results exceed the predetermined range, an alarm is issued to prompt the operator to take measures.

[0071] The embodiment of the present application can realize the beneficial effects as follows through the above steps:

[0072] Through image processing technology and key point positioning technology, the deformation of the welding area can be more accurately detected, and the precision is higher than that of the traditional manual detection method;

[0073] The image data is automatically acquired, and through analysis, the need for manual intervention is reduced, and the detection efficiency is improved;

[0074] The deformation state of the welding area is monitored in real time, potential quality problems are found and solved in time, and the quality of the product is ensured to be stable;

[0075] By recording and analyzing the deformation quantitative results in each welding process, rich data support is provided for long-term quality management and process improvement, which helps to further improve the level of welding process.

[0076] In modern manufacturing, ensuring the welding quality is crucial for improving product performance and safety. The welding of hydraulic support oil cylinder body is particularly important, and any welding defect may cause serious safety hazards. Based on this, the present application provides a specific embodiment, wherein the step 101, sample image data of the welding area of the hydraulic support oil cylinder body captured by the sensor is acquired, the image data includes a first image before welding and a second image after welding is completed, and specifically includes the following steps:

[0077] Step 111: control the rotation angle of the sensor to ensure that the key welding parts of the hydraulic support oil cylinder body are located within the visual range of the sensor;

[0078] In this step, the rotation angle refers to adjusting the angle or position of the sensor to 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 located within the visual range of the sensor.

[0079] This step installs the sensor around the hydraulic support oil cylinder body to ensure that the sensor can cover the entire welding area; by controlling the rotation mechanism of the sensor, the angle is adjusted to ensure that the key welding parts of the hydraulic support oil cylinder body are located within the visual range of the sensor. This step can be realized by presetting the rotation angle or manually adjusting through the software interface; preliminary test is conducted to ensure that all key parts can clearly appear in the field of view of the sensor, and necessary calibration is performed to ensure image quality.

[0080] Step 112: set the collection time interval or trigger condition of the sensor, collect the image data in the welding area, and record the capture time and position information of the image data;

[0081] In this step, the time interval refers to the frequency of repeated image acquisition by the sensor within a certain time; the trigger condition refers to the behavior of starting image acquisition according to the occurrence of certain specific events.

[0082] For example, according to the characteristics of the welding process, the time interval of image acquisition by the sensor is set in advance, such as setting to acquire an image every second or every 5 seconds, to ensure that the key moments before and after welding can be captured; at the same time of image acquisition, 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.

[0083] Step 113: applying image stabilization techniques and image stitching algorithms to process the image data to obtain sample image data;

[0084] In this step, image stabilization techniques refer to techniques for reducing image blur and jitter, improving image quality, common image stabilization techniques include feature point-based image stabilization algorithms; image stitching algorithms refer to techniques for merging multiple partially overlapping images into a complete image, common image stitching algorithms include feature matching-based image stitching techniques.

[0085] For example, using feature point-based image stabilization algorithms, reduce the image blur phenomenon caused by sensor movement or external vibration, ensure the clarity of each frame of image; apply image stitching techniques such as feature matching-based image stitching techniques to stitch multiple images into a complete image, ensure 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 quantization analysis.

[0086] The embodiment of the present application can achieve the beneficial effects as follows through the above steps:

[0087] By adjusting the rotation angle of the sensor, it is ensured that all key welding parts are within the visible range, avoiding the omission of important information due to angle limitation;

[0088] Setting the acquisition time interval or trigger condition of the sensor and recording the capture time and position information ensures the time synchronization of the image data, which is convenient for subsequent analysis;

[0089] Applying image stabilization techniques and image stitching algorithms improves the quality of image data, ensuring the clarity and integrity of the image, providing a reliable data basis for subsequent analysis.

[0090] After obtaining the sample image data, it needs to be processed to extract effective information. Based on this, the present application provides a specific embodiment, the step 102, the key point positioning technology is applied to identify the key position information of the welding area in the sample image data, and specifically includes the following steps:

[0091] Step 201: Preprocessing the sample image data to obtain target image data, the target image data includes: the starting point of the weld, the midpoint of the weld, the center line of the weld and the welding defect position;

[0092] This step improves the quality of the sample image data by various preprocessing methods, for example, applying a Gaussian filter algorithm to remove noise in the image, enhancing the contrast of the image by histogram equalization technology, making the feature points more prominent; convert the color image to a grayscale image to simplify the subsequent processing steps; use Harris corner detection algorithm to identify the starting point of the weld, the midpoint of the weld, the center line of the weld and the welding defect position, and mark them out; integrate the above feature point information together to form the target image data.

[0093] Step 202: According to the preset condition, screen the key points in the target image data;

[0094] In this step, the key point refers to a point with obvious features, which can be used for image matching and positioning. In this embodiment, the key point refers to a specific position point in the welding area, such as the starting point of the weld, the end point of the weld, etc.

[0095] This step presets which feature points are key points, such as the starting point of the weld, the end point of the weld, and specific points on the center line, etc.; according to the preset condition, screen out the key points that meet the condition from the target image data.

[0096] Step 203: Match the key points with the key points in the feature library using feature matching technology to determine the position information of the key points and the correlation of the key points and position changes, and obtain the matching result;

[0097] In this step, the feature matching technology refers to a technology for finding corresponding points between two images, and common methods include scale-invariant feature transform (SIFT), speeded up robust features (SURF), etc.

[0098] 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 that have a similarity higher than a preset threshold with the key point descriptors; 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.

[0099] Step 204: Based on the matching result, construct a key position information model of the welding area;

[0100] For example, according to the matching result, a model is constructed to describe the state of the welding joint, which can distinguish between normal welds and welds with defects.

[0101] Step 205: optimizing the key position information model by a machine learning algorithm, and outputting the position coordinates and descriptors of each key point in the welding area to obtain key position information, which includes the position information of the start point of the weld, the position information of the end point of the weld, and the position information of the edge point of the welding area.

[0102] 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 more accurately reflect the actual state of the welding area; the descriptor refers to a vector used to describe the characteristics of a point in an image for feature matching; in this embodiment, the descriptor is used to represent the characteristics of the key points in the welding area.

[0103] For example, a deep neural network is used to optimize the key position information model to more accurately reflect the actual state of the welding area; the position coordinates and descriptors of each key point in the welding area are output, including the position information of the start point of the weld, the position information of the end point of the weld, and the position information of the edge point of the welding area.

[0104] The embodiment of the present application can achieve the following beneficial effects through the above steps:

[0105] Through preprocessing and feature matching technology, the quality of image data is improved, making the extraction of key position information more accurate;

[0106] Using feature matching technology and machine learning algorithms, automatic extraction and optimization of key position information are achieved, reducing the need for manual intervention and improving detection efficiency;

[0107] The output key position information provides detailed data support for subsequent deformation quantization;

[0108] Optimizing the key position information model by a machine learning algorithm improves the accuracy and robustness of the model and enhances the adaptability of the system.

[0109] To further analyze the key points to accurately capture the small position change information in the welding process. Based on this, the present application provides a specific embodiment, wherein step 203 matches the key points with the key points in the feature library using feature matching technology, determines the position information of the key points and the correlation between the key points and position changes, and obtains a matching result, which specifically includes the following steps:

[0110] Step 231: extracting the 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 of the key points in the first image and the second image, and the feature library comprises position information of preset key points and descriptors of the position information of the preset key points;

[0111] In this step, the feature library refers to a data set storing a series of known key points and their descriptors;

[0112] For example, after several key points around the weld are identified, the descriptors of these key points are extracted using the SIFT algorithm, which 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 before welding and their descriptors, which will be used as a reference standard.

[0113] Step 233: using a feature matching algorithm to find preset key points in the feature library that match the key point descriptors;

[0114] For example, key point descriptors with the same position as the key points around the weld before welding are extracted from the second image, and the ORB algorithm is used to find key points in the feature library that match these descriptors with a matching degree higher than a preset threshold.

[0115] Step 234: evaluating the reliability of the matching results to determine whether the matched key points have a confidence level higher than a preset threshold;

[0116] In this step, the confidence level refers to the degree of reliability of the matching results; in this embodiment, if the matched key points have a confidence level higher than a preset threshold, the matching results are considered reliable.

[0117] For example, a confidence threshold of 90% is preset, and only when the matching score exceeds this threshold, the matching is considered reliable; for matching below the threshold, it is marked as suspicious and further checked.

[0118] Step 235: determining the position change of the matched key points during the welding process and the correlation of the matched key points with the position change, and generating the matching results;

[0119] The formula for calculating the correlation is as follows:

[0120] ;

[0121] wherein, represents the correlation coefficient of key point ; represents the variable of the welding process; represents the position change of key point ;

[0122] In this step, position change refers to the change in the position of the same key point in the image before and after welding; correlation refers to the degree of interdependence between two variables; in this embodiment, the relationship between the position change of the key point and the variables in the welding process.

[0123] This step calculates the positional changes of the critical point before and after welding for each reliable match; correlation formulas are then used to calculate the relationship between these positional changes and variables in the welding process. For example, calculations show that the faster the welding speed, the greater the positional change of critical point A.

[0124] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0125] This helps engineers better understand the displacements that may occur during the welding process, thus improving production safety;

[0126] Predict welding quality and identify potential problems in advance, thereby improving welding quality and production efficiency;

[0127] Improve the level of automation in inspection to achieve real-time monitoring of welding quality.

[0128] Welding, as a crucial step in industrial production, directly impacts product performance and safety. To ensure weld consistency and reliability, strict control of key parameters during the welding process is essential. Based on this, the present invention provides a specific embodiment where step 235, determining the positional changes of the matching key points during the welding process and the correlation between the matching key points and these positional changes, and generating a matching result, further includes the following steps:

[0129] Step 241: Define the variables of the welding process, including: welding temperature, welding speed, welding time, and current intensity;

[0130] The calculation formula for the variables is as follows:

[0131] ;

[0132] in, This represents a welding process state set, which contains multiple states describing the welding process. The variable representing the state at any given moment; Indicating the welding process Temperature value at any given time; It is the initial temperature at the start of welding; and It is a coefficient related to the properties of welding equipment and materials; This indicates the speed at which the welding head moves during the welding process; Indicates the initial welding speed; and It is a coefficient related to the welding process; Indicates from the start of welding to The time elapsed at any given moment; Indicates the current time; Indicates the time point at which welding begins; Indicating the welding process The magnitude of the current at any given moment; It is the initial current intensity, and It is a coefficient related to the properties of welding equipment and materials.

[0133] This step describes the welding process by defining four variables and combining them into a welding process state set. This method provides a more intuitive view of the deformation of the hydraulic support cylinder body during welding, allowing for optimization of the welding process.

[0134] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0135] Defining and strictly controlling these variables can help optimize the welding process, so that the strength, toughness and corrosion resistance of the welded joint are at their best, thereby improving the overall quality of the final product.

[0136] By precisely controlling the temperature, speed, time, and current intensity during the welding process, product defects caused by improper welding can be reduced, scrap rates can be lowered, and raw materials and production costs can be saved.

[0137] Clearly defined welding parameter settings help maintain process consistency and repeatability, ensuring stable welding results even between different operators or different equipment.

[0138] Setting the welding speed and time appropriately can balance welding quality and production efficiency, avoiding inefficiency caused by being too slow or quality problems caused by being too fast.

[0139] Controlling welding temperature is not only to ensure welding quality, but also to help protect the safety of operators and prevent high temperatures from having adverse health effects.

[0140] When welding problems occur, the possible causes can be found by reviewing the variable settings in the welding process, which makes it easier to quickly locate the problem and make corresponding adjustments or improvements.

[0141] The heat stress generated in the welding process can cause the workpiece to deform, which not only affects the appearance, but also can cause safety hazards, and it is particularly important to accurately measure and analyze the deformation caused by welding. Based on this, the present application provides a specific embodiment, the step 103, according to the key position information, the key position information of the first image and the key position information of the second image are determined, the deformation degree of the hydraulic support oil cylinder body in the welding process is quantified, and the deformation quantization result is obtained, which specifically includes the following steps:

[0142] Step 301: According to the key position information, the key position information of the first image and the key position information of the second image are determined;

[0143] For example, in the first image, the starting point coordinates of the weld are , and in the second image, the coordinates of the starting point of the same weld are .

[0144] Step 302: Compare the key position information of the first image and the key position information of the second image to obtain the coordinate difference;

[0145] In this step, the coordinate difference refers to the position difference of the same key point in the image coordinate system in the first image and the second image.

[0146] For example, the coordinates of the starting point of the weld in the first image and the coordinates of the same starting point of the weld in the second image are compared, and the coordinate difference of the starting point of the weld is calculated , .

[0147] Step 303: Compare the coordinate difference to calculate the displacement vector of each key point to quantify the deformation degree of the hydraulic support oil cylinder body in the welding process;

[0148] In this step, the displacement vector refers to the position change of the key point before and after welding, which is usually represented by a two-dimensional or three-dimensional vector, including direction and size.

[0149] This step calculates the displacement vector of each matched key point, i.e. the coordinate difference vector or ; Statistics of the displacement vectors of all key points can analyze the deformation of the hydraulic support oil cylinder body in the welding process. For example, if the displacement vectors of multiple key points point in the same direction and have similar sizes, it indicates that the hydraulic support oil cylinder body has undergone uniform deformation during the welding process.

[0150] Step 304: Based on the coordinate difference, a deformation quantization model is established to obtain the deformation quantization result;

[0151] In this step, the deformation model refers to a mathematical model used to describe and quantify the degree of deformation of the hydraulic support cylinder body during the welding process; the deformation result refers to the specific numerical value of the degree of deformation of the hydraulic support cylinder body during the welding process obtained by analyzing coordinate differences and displacement vectors.

[0152] This step establishes a deformation model based on coordinate differences and displacement vectors. This model can be a simple linear model or a complex nonlinear model, used to describe the deformation law of the hydraulic support cylinder body during welding. Through the deformation model calculation, the deformation results are obtained, specifically including the displacement magnitude and direction of each key point, as well as the overall degree of deformation.

[0153] For example, this embodiment provides a more specific method for calculating the deformation result, wherein the formula for calculating the deformation result is as follows:

[0154] ;

[0155] in, This represents the result of the derivation; This indicates the number of all key points; Indicates the first The degree of deformation at each key point; This represents the influence factors of multiple variables on deformation during the welding process; Indicating the welding process Temperature value at any given time; This indicates the speed at which the welding head moves during the welding process; Indicates from the start of welding to The time elapsed at any given moment; Indicating the welding process The magnitude of the current at any given moment; Indicates the first Displacement vectors of key points; Indicates the first Each key point is affected by other key points besides itself. The sum of the effects; This is the key point. and key points The weights between them reflect the key points. and key points The strength of their interaction; Indicate key points The coordinate differences.

[0156] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0157] By coordinate difference calculation and displacement vector analysis, the deformation degree of the hydraulic support oil cylinder body during welding can be quantified more accurately, and the detection precision is improved.

[0158] The output deformation quantification result provides detailed deformation information, including the displacement size and direction of each key point, which provides a scientific basis for subsequent quality management and process improvement.

[0159] Through quantitative analysis of the deformation degree of the hydraulic support oil cylinder body during welding, problems existing in the welding process can be found in time, process parameters can be optimized, and welding quality can be improved.

[0160] By establishing a deformation quantification model, the deformation during welding can be better represented and controlled, thereby strengthening production management and ensuring the consistency of product quality.

[0161] To provide a scientific basis and summary description for welding process optimization, based on this, the present application provides a specific embodiment, wherein the step 104, according to the deformation quantification result, monitors and records the deformation state of the welding area, specifically including the following steps:

[0162] Step 401: record the deformation quantification result to form a deformation state record of the welding area changing with time;

[0163] This step stores the deformation quantification result obtained each time to form a time sequence deformation state record.

[0164] Step 402: based on the deformation state record, analyze the deformation trend of the hydraulic support oil cylinder body during welding to obtain a deformation trend analysis result;

[0165] This step statistically analyzes the data in the deformation state record to observe the change law of the deformation variable with time; by analyzing the data, it is identified whether there is a certain deformation mode or law, such as whether the deformation increases linearly or nonlinearly with time; the analysis result is extracted, including statistical data such as maximum value, minimum value, average value of the deformation, and graphical representation of the deformation trend.

[0166] Step 403: generate a deformation monitoring report, summarize the deformation trend analysis result, and provide a summary description of the deformation quantification of the welding area;

[0167] This step compiles a deformation monitoring report based on the deformation trend analysis result; the deformation trend chart and curve are added in the report to facilitate the reader to understand; the results of the deformation trend analysis are summarized in the report, and possible reasons and suggestions are proposed.

[0168] The embodiment of the present application can achieve the beneficial effects as follows through the above steps:

[0169] The deformation state record and trend analysis result help engineers find problems in time, adjust welding parameters, and improve welding quality;

[0170] Through analysis of the deformation trend, possible welding failure can be predicted, and measures can be taken in advance to reduce the scrap rate;

[0171] The deformation monitoring report provides detailed analysis results, which helps to optimize the process and make the production process more stable and reliable;

[0172] Detailed deformation quantization records provide a solid data foundation for subsequent product design and manufacturing.

[0173] Figure 2 A structure diagram of a hydraulic support oil cylinder body welding deformation detection system based on image processing is provided for the embodiments of the present application, as shown in Figure 2 The system comprises:

[0174] The acquisition module 21 is configured to acquire sample image data of the welding area of the hydraulic support oil cylinder body captured by the sensor, wherein the image data comprises a first image before welding and a second image after welding is completed;

[0175] The identification module 22 is configured to identify key position information of the welding area in the sample image data by applying a key point positioning technology;

[0176] The quantization module 23 is 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, to quantify the deformation degree of the hydraulic support oil cylinder body during welding, and obtain a deformation quantization result;

[0177] The monitoring module 24 is configured to monitor and record the deformation state of the welding area according to the deformation quantization result.

[0178] Figure 2 The image processing-based hydraulic support oil cylinder body welding deformation detection system can perform Figure 1 The implementation principle and technical effects of the image processing-based hydraulic support oil cylinder body welding deformation detection method described in the embodiments shown in the above are not described again. For the specific manner in which each module, unit of the image processing-based hydraulic support oil cylinder body welding deformation detection system described in the above embodiments performs operations, it has been described in detail in the embodiments related to the method, and will not be described in detail here.

[0179] Figure 2 The image processing-based hydraulic support oil cylinder body welding deformation detection can be implemented as a computing device, as shown in Figure 3 The computing device can comprise a storage component 31 and a processing component 32;

[0180] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0181] The processing component 32 is configured to obtain sample image data of a welding area of a hydraulic support oil cylinder body captured by a sensor, the image data including a first image before welding and a second image after welding is completed; apply a key point positioning technology to identify key position information of the welding area in the sample image data; determine key position information of the first image and key position information of the second image according to the key position information, so as to quantify a deformation degree of the hydraulic support oil cylinder body in the welding process, and obtain a deformation quantization result; and monitor and record a deformation state of the welding area according to the deformation quantization result.

[0182] 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 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 elements, for executing the above method.

[0183] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be realized by any type of volatile or non-volatile storage device or their combination, 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 storage, flash memory, magnetic disk or optical disk.

[0184] The computing device also includes other components, such as an input / output interface, a display component, a communication component.

[0185] The input / output interface provides an interface between the processing component and peripheral interface modules, which can be output devices, input devices.

[0186] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0187] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform, and the computing device can be a cloud server. The processing component, the storage component, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0188] The embodiment of the present application further provides a computer storage medium, which stores a computer program, and the computer program can realize the above-mentioned method when being executed by a computer. Figure 1 The embodiment of the present application further provides a computer storage medium, which stores a computer program, and the computer program can realize the above-mentioned method when being executed by a computer.

[0189] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-mentioned system, device and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0190] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme. Those skilled in the art can understand and implement without creative labor.

[0191] Through the foregoing description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the foregoing technical solutions can be embodied in the form of software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions for making a computer device (which can be a personal computer, server, or network device, etc.) execute the method described in each embodiment or some part of the embodiment.

[0192] Finally, it should be noted that: the foregoing embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the foregoing embodiments of the present application have been described in detail, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some 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 application.

Claims

1. A method for detecting welding deformation of hydraulic support cylinder body based on image processing, characterized in that, include: Acquire sample image data of the welding area of ​​the hydraulic support cylinder body captured by a sensor, the sample image data including a first image before welding and a second image after welding; Key point localization technology is used to identify key location information of the welding area in the sample image data; Based on the key position information, the key position information of the first image and the key position information of the second image are determined to quantify the degree of deformation of the hydraulic support cylinder body during the welding process and obtain the deformation quantification result. Based on the deformation results, monitor and record the deformation state of the welding area; The key point localization technique is used to identify key location information of the welding area in the sample image data, including: The sample image data is preprocessed to obtain target image data, which includes: the start point of the weld, the midpoint of the weld, the center line of the weld, and the location of welding defects. Key points in the target image data are filtered according to preset conditions; The key points are matched with key points in the feature library using feature matching technology to determine the location information of the key points and the correlation between the key points and location changes, thereby obtaining the matching results. Based on the matching results, a key location information model of the welding area is constructed; The key location information model is optimized by machine learning algorithm, and the position coordinates and descriptors of each key point in the welding area are output to obtain key location information, which includes the position information of the weld start point, the position information of the weld end point, and the position information of the edge points of the welding area. Feature matching technology is used to match the key points with key points in the feature library, determine the location information of the key points and the correlation between the key points and location changes, and obtain the matching results, including: Extract the descriptors of the key points, and construct a feature library based on the descriptors of the key points, wherein the descriptors represent local feature encodings for key points in the first image and the second image, and the feature library includes the location information of preset key points and the descriptors of the location information of preset key points; Using a feature matching algorithm, a preset key point that matches the key point descriptor is found in the feature library; Assess the reliability of the matching results and determine whether the key points of the matching have a confidence level higher than a preset threshold; Determine the positional changes of the matching key points during the welding process and the correlation between the matching key points and the positional changes, and generate matching results; The formula for calculating the correlation is as follows: ； in, Indicate key points The correlation coefficient; Variables representing the welding process; Indicate key points The change in position.

2. The method according to claim 1, characterized in that, The acquisition of sample image data of the welding area of ​​the hydraulic support cylinder body captured by the sensor, the image data including a first image before welding and a second image after welding, includes: The rotation angle of the sensor is controlled to ensure that the key welded parts of the hydraulic support cylinder body are all within the sensor's field of view. Set the acquisition time interval or trigger condition of the sensor, acquire image data within the welding area, and record the acquisition time and location information of the image data; The image data is processed using image stabilization techniques and image stitching algorithms to obtain sample image data.

3. The method according to claim 1, characterized in that, The method further includes: Define the variables for the welding process, including: welding temperature, welding speed, welding time, and current intensity; The calculation formula for the variables is as follows: ； in, This represents a welding process state set, which contains multiple states describing the welding process. The variable representing the state at any given moment; Indicating the welding process Temperature value at any given time; It is the initial temperature at the start of welding; and It is a coefficient related to the properties of welding equipment and materials; This indicates the speed at which the welding head moves during the welding process; Indicates the initial welding speed; and It is a coefficient related to the welding process; Indicates from the start of welding to The time elapsed at any given moment; Indicates the current time; Indicates the time point at which welding begins; Indicating the welding process The magnitude of the current at any given moment; It is the initial current intensity, and It is a coefficient related to the properties of welding equipment and materials.

4. The method according to claim 1, characterized in that, The step of determining the key position information of the first image and the second image based on the key position information to quantify the deformation degree of the hydraulic support cylinder body during welding and obtain the deformation quantification result includes: Based on the key location information, determine the key location information of the first image and the key location information of the second image; The key position information of the first image and the key position information of the second image are compared to obtain the coordinate difference; By comparing the coordinate differences, the displacement vectors of each key point are calculated to quantify the degree of deformation of the hydraulic support cylinder body during the welding process. Based on the aforementioned coordinate differences, a deformation model is established, and the deformation results are obtained.

5. The method according to claim 1, characterized in that, The deformation results are used to monitor and record the deformation state of the welded area, and generate a deformation monitoring report, including: Record the deformation results to form a record of the deformation state of the welded area over time; Based on the deformation state record, the deformation trend of the hydraulic support cylinder body during the welding process is analyzed to obtain the deformation trend analysis results. Generate a deformation monitoring report, summarize the deformation trend analysis results, and provide a summary description of the deformation changes in the welded area.

6. A hydraulic support cylinder body welding deformation detection system based on image processing, characterized in that, include: The acquisition module is used to acquire sample image data of the welding area of ​​the hydraulic support cylinder body captured by the sensor. The image data includes a first image before welding and a second image after welding. The identification module is used to identify key location information of the welding area in the sample image data by applying key point localization technology; The quantization module is used to determine the key position information of the first image and the key position information of the second image based on the key position information, so as to quantify the degree of deformation of the hydraulic support cylinder body during the welding process and obtain the deformation quantification result. The monitoring module is used to monitor and record the deformation state of the welding area based on the deformation results. The key point localization technique is used to identify key location information of the welding area in the sample image data, including: The sample image data is preprocessed to obtain target image data, which includes: the start point of the weld, the midpoint of the weld, the center line of the weld, and the location of welding defects. Key points in the target image data are filtered according to preset conditions; The key points are matched with key points in the feature library using feature matching technology to determine the location information of the key points and the correlation between the key points and location changes, thereby obtaining the matching results. Based on the matching results, a key location information model of the welding area is constructed; The key location information model is optimized by machine learning algorithm, and the position coordinates and descriptors of each key point in the welding area are output to obtain key location information, which includes the position information of the weld start point, the position information of the weld end point, and the position information of the edge points of the welding area. Feature matching technology is used to match the key points with key points in the feature library, determine the location information of the key points and the correlation between the key points and location changes, and obtain the matching results, including: Extract the descriptors of the key points, and construct a feature library based on the descriptors of the key points, wherein the descriptors represent local feature encodings for key points in the first image and the second image, and the feature library includes the location information of preset key points and the descriptors of the location information of preset key points; Using a feature matching algorithm, a preset key point that matches the key point descriptor is found in the feature library; Assess the reliability of the matching results and determine whether the key points of the matching have a confidence level higher than a preset threshold; Determine the positional changes of the matching key points during the welding process and the correlation between the matching key points and the positional changes, and generate matching results; The formula for calculating the correlation is as follows: ； in, Indicate key points The correlation coefficient; Variables representing the welding process; Indicate key points The change in position.

7. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the image processing-based hydraulic support cylinder body welding deformation detection method as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a method for detecting welding deformation of hydraulic support cylinder body based on image processing, as described in any one of claims 1 to 5.

Images