A method and system for predicting the quality of a truck steel structure based on the welding results of the girder

Abstract

The present application discloses a method and system for predicting the quality of a truck steel structure based on the welding results of a girder, relating to the technical field of predicting the welding quality of a truck steel structure. The present application provides a method for predicting the quality of a truck steel structure based on the welding results of a girder, including: obtaining the positions of welding points arranged in sequence of a weld seam according to the weld seam image at the welding position of the girder; obtaining the spacing distribution characteristics of adjacent welding points according to the positions of the welding points; evaluating the first welding quality of the weld seam according to the spacing distribution characteristics; obtaining at least one weld seam patch containing a preset number of welding points according to the positions of the welding points, performing weld defect identification on the weld seam patch, and obtaining the defect category of the weld seam image; obtaining the defect degree of all the weld seam patches according to the defect category; evaluating the second welding quality of the weld seam according to the defect degree; predicting the quality of the truck steel structure according to the first welding quality and the second welding quality.

Description

Technical Field

[0001] This application relates to the technical field of truck steel structure welding quality prediction, and particularly to a method and system for predicting the quality of truck steel structures based on the welding results of the girder. Background Art

[0002] In modern industrial production, trucks, as important logistics transportation tools, the quality of their steel structures is directly related to the safety, durability, and transportation efficiency of the vehicles. Especially the girder part of the truck, as a key structure for bearing the vehicle body weight and cargo load, its welding quality is even more crucial. However, due to various variables existing in the welding process, such as welding parameters, material properties, operation techniques, etc., it is often difficult to accurately evaluate the quality of the girder welds by a single means.

[0003] Traditional truck girder welding quality inspections usually rely on manual visual inspections or simple measuring tools. These methods are not only inefficient but also greatly affected by human factors, making it difficult to ensure the objectivity and accuracy of the inspection results. Summary of the Invention

[0004] The main purpose of this application is to provide a method and system for predicting the quality of truck steel structures based on the welding results of the girder, aiming to solve the technical problem that traditional truck girder welding quality inspections usually rely on manual visual inspections or simple measuring tools, and these methods are not only inefficient.

[0005] To achieve the above object, in the first aspect, this application provides a method for predicting the quality of truck steel structures based on the welding results of the girder, including:

[0006] Obtain the solder joint positions of the weld in order according to the weld image of the girder welding position;

[0007] Obtain the spacing distribution characteristics of adjacent solder joints according to the solder joint positions;

[0008] Evaluate the first welding quality of the weld according to the spacing distribution characteristics;

[0009] Obtain at least one weld patch containing a preset number of solder joints according to the solder joint positions, perform weld defect identification on the weld patch, and obtain the defect categories of the weld image;

[0010] Obtain the defect degrees of all the weld patches according to the defect categories;

[0011] Evaluate the second welding quality of the weld according to the defect degrees;

[0012] Predict the quality of the truck steel structure according to the first welding quality and the second welding quality.

[0013] Optionally, the step of obtaining the spacing distribution characteristics of adjacent solder joints according to the solder joint positions includes:

[0014] According to the arrangement order of the solder joints on the weld seam, pair two adjacent solder joints to obtain paired solder joints, and take the Euclidean distance between the center points of each group of paired solder joints as the solder joint spacing;

[0015] According to the solder joint distances of all paired solder joints, obtain the average solder joint spacing of the weld seam, compare each group of solder joint spacings with the average solder joint spacing, and obtain the spacing distribution characteristics of the paired solder joints, where the spacing distribution characteristics characterize the solder joint uniformity of the weld seam.

[0016] Optionally, the step of obtaining the average solder joint spacing of the weld seam according to the solder joint distances of all paired solder joints, comparing each group of solder joint spacings with the average solder joint spacing, and obtaining the spacing distribution characteristics of the paired solder joints includes:

[0017] According to the solder joint distances of all paired solder joints, obtain the maximum solder joint spacing, the minimum solder joint spacing, and the average solder joint spacing;

[0018] Obtain the maximum solder joint spacing, the minimum solder joint spacing, and the average solder joint spacing, and obtain the normal solder joint spacing interval;

[0019] Compare each group of solder joint spacings with the normal solder joint spacing, obtain abnormal paired solder joints, and send abnormal information.

[0020] Optionally, the step of evaluating the first welding quality of the weld seam according to the spacing distribution characteristics includes:

[0021] The formula for evaluating the first welding quality of the weld seam:

[0022]

[0023] where, d i represents the spacing between the i-th and the (i + 1)-th solder joints, there are n solder joints in total, D represents the average welding gap between adjacent solder joints, and K is a coefficient.

[0024] Optionally, the step of obtaining at least one weld seam tile containing a preset number of solder joints according to the solder joint positions, performing weld seam defect identification on the weld seam tile, and obtaining the defect category of the weld seam image includes:

[0025] Process the weld seam tile to obtain a grayscale image, calculate the gray level co-occurrence matrix of the grayscale image, and provide texture features;

[0026] Set a threshold according to the gray value or texture features, segment the grayscale image into foreground and background, and detect the edge information of the defects in the foreground through an edge detection operator;

[0027] Obtain the defect category of the weld image according to the edge information.

[0028] Optionally, the step of obtaining the defect degree of all weld patches according to the defect category includes:

[0029] Set the window parameters for each defect category. When the defect categories are porosity and spatter defects, the calculation formula for the defect degree is:

[0030]

[0031] where w i represents the weight of the i-th type of defect; I(x, y) represents the gray value of the pixel at the position (x, y) in the weld patch; μ represents the average gray value of the weld patch; K i (x, y) represents the Gaussian kernel function value corresponding to the i-th type of defect centered on (x, y).

[0032] Optionally, the step of obtaining the defect degree of all weld patches according to the defect category includes:

[0033] Set the window parameters for each defect category. When the defect categories are lack of fusion and defects, the calculation formula for the defect degree is:

[0034]

[0035] where w i represents the weight of the i-th type of defect, ΔI i (x, y) represents the gray value difference of the i-th type of defect at the position (x, y), and ΔI weld (x, y) represents the gray value difference of the weld area at the position (x, y), and γ represents a constant.

[0036] Optionally, the step of evaluating the second welding quality of the weld according to the defect degree includes:

[0037] According to the defect degrees of all weld patches, perform weighted aggregation according to the defect types to evaluate the second welding quality of the weld.

[0038] Optionally, the step of predicting the quality of the truck steel structure according to the first welding quality and the second welding quality includes:

[0039] According to the first welding quality and the second welding quality, perform weighted calculation to obtain a comprehensive score, and characterize the quality of the truck steel structure through the comprehensive score.

[0040] In a second aspect, the present application provides a truck steel structure quality prediction system based on the welding results of the girder, including:

[0041] A solder joint position acquisition module, which is configured to acquire the solder joint positions arranged in sequence of the weld seam according to the weld seam image of the girder welding position;

[0042] A spacing distribution characteristic acquisition module, which is configured to acquire the spacing distribution characteristics of adjacent solder joints according to the solder joint positions;

[0043] A first welding quality evaluation module, which is configured to evaluate the first welding quality of the weld seam according to the spacing distribution characteristics;

[0044] A defect category acquisition module, which is configured to acquire at least one weld seam tile containing a preset number of solder joints according to the solder joint positions, perform weld seam defect identification on the weld seam tile, and obtain the defect category of the weld seam image;

[0045] A defect degree acquisition module, which is configured to acquire the defect degrees of all the weld seam tiles according to the defect categories;

[0046] A second welding quality acquisition module, which is configured to evaluate the second welding quality of the weld seam according to the defect degrees;

[0047] A truck steel structure quality prediction module, which is configured to predict the quality of the truck steel structure according to the first welding quality and the second welding quality.

[0048] The beneficial effects that can be achieved by this application:

[0049] A method and system for predicting the quality of a truck steel structure based on the welding result of a girder proposed in an embodiment of this application provide a comprehensive evaluation of the weld seam quality by comprehensively considering the solder joint positions, spacing distribution characteristics of the weld seam, and the categories and degrees of weld seam defects. This multi-dimensional analysis method can more accurately reflect the actual quality status of the weld seam compared with the traditional single-feature analysis, thereby improving the accuracy of the evaluation. Description of the Drawings

[0050] Figure 1 It is a schematic flowchart of the method for predicting the quality of a truck steel structure based on the welding result of a girder in this application;

[0051] The realization, functional characteristics, and advantages of the purpose of this application will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to 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 the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If this specific posture changes, the directional indications will also change accordingly.

[0054] In the present invention, unless otherwise clearly defined and limited, terms such as "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0055] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or a solution where A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0056] Embodiment 1

[0057] Referring to Figure 1 , the embodiment of the present application provides a method for predicting the quality of a truck steel structure based on the welding results of a girder, including the following operation steps:

[0058] S10. Obtain the positions of welding spots arranged in sequence of the weld seam according to the weld seam image at the welding position of the girder.

[0059] Optionally, the girder is welded to the truck chassis to form the truck steel structure, and several weld points form a weld seam. Select a suitable industrial camera and lens to ensure that they can meet the resolution and clarity requirements for weld seam image acquisition. According to the welding process and drawings, determine the specific position and direction of the weld seam, and use a robotic arm, guide rail or other positioning device to accurately move the industrial camera above the weld seam to ensure that the camera lens maintains an appropriate distance and angle from the weld seam. After obtaining the weld seam image, preprocess the weld seam image, including denoising, enhancing contrast, correcting distortion, etc., to ensure that the image quality meets the requirements for subsequent processing. Use image processing algorithms (such as edge detection, template matching, etc.) to detect the positions of the weld points in the preprocessed weld seam image. According to the actual positions of the weld points on the weld seam, sort the detected weld points to form a list of weld point positions arranged in order.

[0060] S20. Obtain the spacing distribution characteristics of adjacent weld points according to the weld point positions.

[0061] Optionally, traverse the list of weld point positions and calculate the spacing between adjacent weld points. Conduct statistical analysis on the calculated spacings, such as calculating the average spacing, the standard deviation of the spacings, the distribution pattern of the spacings, etc., to obtain the spacing distribution characteristics.

[0062] S30. Evaluate the first welding quality of the weld seam according to the spacing distribution characteristics.

[0063] Optionally, based on industry experience or experimental data, formulate evaluation criteria for the spacing distribution characteristics, such as the allowable range of the spacing, the maximum value of the standard deviation, etc. Compare the actual spacing distribution characteristics with the evaluation criteria to evaluate the first welding quality of the weld seam, such as determining whether the weld points of the weld seam are uniform and whether there are excessive spacing fluctuations. By analyzing the positions of the weld points, the first welding quality of the weld seam is characterized by the uniformity of the weld points. The reasons for non-uniform weld points may be unstable welding speed, unsteady movement of the welding torch, etc. The uniformity of the weld points can be further used to guide the setting of welding parameters, etc.

[0064] S40. Obtain at least one weld seam tile containing a preset number of weld points according to the weld point positions, and perform weld defect identification on the weld seam tile to obtain the defect categories of the weld seam image.

[0065] Optionally, according to the weld point positions and the preset tile size, extract weld seam tiles containing a preset number of weld points from the weld seam image. Use machine learning algorithms or image processing techniques (such as convolutional neural networks, morphological processing, etc.) to perform defect identification on the weld seam tiles, and identify defect categories such as pores, spatter, lack of fusion, and overlap.

[0066] S50. Obtain the defect degrees of all the weld seam tiles according to the defect categories.

[0067] Optionally, further analyze the weld seam blocks. For different defect types, the locations where defects occur are different. By further subdividing the defect degree of the weld seam, the defect degree can be accurately analyzed.

[0068] S60. Evaluate the second welding quality of the weld seam according to the defect degree.

[0069] Optionally, formulate an evaluation standard for the second welding quality of the weld seam according to the defect category and degree, such as the maximum allowable degree of defects, the maximum value of the number of defects, etc. Compare the actual defect degree with the evaluation standard to evaluate the second welding quality of the weld seam.

[0070] S70. Predict the quality of the truck steel structure according to the first welding quality and the second welding quality.

[0071] Optionally, comprehensively consider the first welding quality and the second welding quality to comprehensively evaluate the overall quality of the weld seam. According to the overall quality of the weld seam, combined with the force analysis and fatigue life prediction of the truck steel structure, etc., predict the overall quality of the truck steel structure, such as judging whether the truck steel structure meets the design requirements and whether there are potential safety hazards.

[0072] In this embodiment, by comprehensively considering the consistency of the solder joint spacing and the condition of the weld seam defects, the weld seam quality can be more comprehensively evaluated, thereby improving the accuracy of the truck steel structure quality prediction. Timely quality prediction helps to discover potential problems in the production process, guide production adjustment, reduce the defective rate, optimize the production process, and reduce costs. Accurate prediction of the truck steel structure quality can ensure the reliability and safety of the vehicle structure, reduce the risk of safety accidents caused by structural problems, and provide strong support for the manufacturing and quality control of the truck steel structure.

[0073] Embodiment 2

[0074] Based on Embodiment 1, this embodiment provides a method for predicting the quality of a truck steel structure based on the welding result of the girder, including the following operation steps:

[0075] S10. Obtain the solder joint positions of the weld seam arranged in order according to the weld seam image at the welding position of the girder.

[0076] S20. Obtain the spacing distribution characteristics of adjacent solder joints according to the solder joint positions.

[0077] Optionally, the step of obtaining the spacing distribution characteristics of adjacent solder joints according to the solder joint positions includes:

[0078] S201. According to the arrangement order of the solder joints on the weld seam, pair two adjacent solder joints to obtain paired solder joints, and take the Euclidean distance between the center points of each group of paired solder joints as the solder joint spacing.

[0079] Specifically, all the positions of the solder joints are accurately identified in the weld seam image through image processing techniques (such as edge detection, template matching or deep learning algorithms), and the solder joints are sorted according to the welding sequence or the spatial position relationship in the image. According to the arrangement order of the solder joints, two adjacent solder joints are grouped into a pair to form paired solder joints. Ensure that each pair of solder joints is directly adjacent on the weld seam without omission or repetition. For each group of paired solder joints, calculate the Euclidean distance between their center points, that is, the solder joint spacing. The Euclidean distance is the most direct and commonly used distance metric between two points, which can accurately reflect the actual interval between the solder joints.

[0080] Through solder joint pairing and spacing calculation, the distribution of solder joints on the weld seam can be quantified, providing basic data for subsequent analysis of the spacing distribution characteristics. Accurate solder joint identification and sorting are the keys to ensuring the correctness of spacing calculation, which helps to reduce errors and misjudgments.

[0081] S202. Obtain the average solder joint spacing of the weld seam according to the solder joint distances of all paired solder joints, compare each group of solder joint spacings with the average solder joint spacing, and obtain the spacing distribution characteristics of the paired solder joints, where the spacing distribution characteristics characterize the solder joint uniformity of the weld seam.

[0082] Specifically, calculate the average solder joint spacing of the weld seam according to the solder joint spacings of all paired solder joints. This can be achieved by adding up all the solder joint spacings and then dividing by the number of paired solder joints. Compare each group of solder joint spacings with the average solder joint spacing, and analyze the characteristics such as the dispersion degree and fluctuation range of the solder joint spacings. These characteristics can reflect the solder joint uniformity of the weld seam, that is, whether the solder joint spacings are consistent and whether there are abnormal spacings. According to the comparison results, quantify and characterize the distribution characteristics of the solder joint spacings, such as calculating statistical indicators such as standard deviation and coefficient of variation, or drawing a spacing distribution diagram to visually display the distribution of the solder joints.

[0083] Through the analysis of the spacing distribution characteristics, potential problems such as uneven distribution of solder joints, too large or too small spacings in the weld seam can be detected in a timely manner, providing a strong basis for production adjustment. Just from the perspective of the solder joint positions, the more uniform the solder joint distribution, the higher the welding quality. Accurate analysis of the spacing distribution characteristics helps to optimize the welding process parameters, improve the weld seam quality and production efficiency, and reduce costs and the defective rate.

[0084] Optionally, the step of obtaining the average solder joint spacing of the weld seam according to the solder joint distances of all paired solder joints, comparing each group of solder joint spacings with the average solder joint spacing, and obtaining the spacing distribution characteristics of the paired solder joints includes:

[0085] S2021. Obtain the maximum solder joint spacing, the minimum solder joint spacing and the average solder joint spacing according to the solder joint distances of all paired solder joints.

[0086] Specifically, based on the calculated solder joint spacings of all paired solder joints, further calculate the maximum value, minimum value, and average value of these spacings. The maximum solder joint spacing represents the maximum distance between adjacent solder joints in the weld seam. The minimum solder joint spacing represents the minimum distance between adjacent solder joints in the weld seam. The average solder joint spacing is the sum of all solder joint spacings divided by the number of paired solder joints, which is used to reflect the overall level of solder joint spacings. By calculating the maximum value, minimum value, and average value of solder joint spacings, an initial understanding of the overall distribution of solder joints in the weld seam can be obtained, laying a foundation for subsequent analysis of the spacing distribution characteristics.

[0087] S2022. Obtain the maximum solder joint spacing, minimum solder joint spacing, and average solder joint spacing, and obtain the normal solder joint spacing range.

[0088] Specifically, based on the statistically obtained maximum solder joint spacing, minimum solder joint spacing, and average solder joint spacing, combined with production process requirements and welding standards, determine a reasonable normal solder joint spacing range. This range can be adjusted according to the actual situation to ensure that it can include most normal solder joint spacings and effectively identify abnormal solder joint spacings. Determining the normal solder joint spacing range is the basis for identifying abnormal solder joint spacings, which helps to accurately distinguish normal and abnormal solder joint pairs in subsequent steps.

[0089] S2023. Compare the solder joint spacing of each group with the normal solder joint spacing to obtain abnormal paired solder joints and send abnormal information.

[0090] Specifically, compare the solder joint spacing of each group with the normal solder joint spacing range to determine whether the solder joint spacing of each group falls within the range. If the solder joint spacing of a certain group is not within the normal range, mark this group of solder joints as abnormal paired solder joints. For the identified abnormal paired solder joints, the system should send abnormal information, such as notifying relevant personnel for handling through interface display, sound alarm, or sending emails. By identifying abnormal paired solder joints, potential quality problems in the weld seam, such as uneven solder joint distribution and welding deviation, can be detected in a timely manner. Sending abnormal information helps to promptly remind relevant personnel to take measures for intervention, avoiding potential quality risks and safety hazards.

[0091] S30. Evaluate the first welding quality of the weld seam according to the spacing distribution characteristics.

[0092] Optionally, the step of evaluating the first welding quality of the weld seam according to the spacing distribution characteristics includes:

[0093] Formula for evaluating the first welding quality of the weld seam:

[0094]

[0095] where d irepresents the spacing between the \(i\)-th and the \((i + 1)\)-th solder joints. There are \(n\) solder joints in total. \(D\) represents the average solder gap between adjacent solder joints, and \(K\) is a coefficient.

[0096] Specifically, the denominator part in the above formula calculates the standard deviation of the difference between the solder joint spacing and the average solder gap (or the square root of the mean square error), which reflects the dispersion degree of the solder joint spacing. When the solder joint spacing is closer to the average solder gap, the standard deviation is smaller, the denominator is smaller, and thus the evaluation value \(S\) is larger, indicating that the solder joint distribution of the weld seam is more uniform and the welding quality is higher. The coefficient \(K\) is used to adjust the numerical range of the evaluation result to make it more in line with the actual application needs. This formula provides a quantitative method to evaluate the uniformity of the solder joint distribution of the weld seam, thereby indirectly reflecting the welding quality. Just calculate the solder joint spacing and the average solder gap, and then substitute them into the formula to obtain the evaluation result, which is simple to operate. Compared with simply observing with the naked eye or simple measurement, this formula can more accurately reflect the dispersion degree of the solder joint distribution, thereby improving the accuracy of welding quality evaluation.

[0097] S40. According to the positions of the solder joints, obtain at least one weld seam patch containing a preset number of solder joints, perform weld seam defect identification on the weld seam patch, and obtain the defect category of the weld seam image.

[0098] Optionally, the step of obtaining at least one weld seam patch containing a preset number of solder joints according to the positions of the solder joints, performing weld seam defect identification on the weld seam patch, and obtaining the defect category of the weld seam image includes:

[0099] S401. Process the weld seam patch to obtain a grayscale image, calculate the gray-level co-occurrence matrix of the grayscale image, and provide texture features.

[0100] Specifically, first, convert the weld seam patch from the original color image to a grayscale image. This is to simplify subsequent processing while retaining the main structural information of the image. Use an appropriate grayscale conversion algorithm, such as the weighted average method, to ensure that the grayscale image can accurately reflect the color information of the original image. The gray-level co-occurrence matrix (GLCM) is a method for describing image texture. Select appropriate distance and direction parameters to calculate the GLCM to capture the texture features in the weld seam image. Extract texture features such as contrast, energy, and entropy from the GLCM, and these features will be used for subsequent defect identification.

[0101] S402. Set a threshold according to the gray value or texture features, segment the grayscale image into foreground and background, and detect the edge information of the defects in the foreground through an edge detection operator.

[0102] Specifically, set a threshold according to the grayscale value or the previously extracted texture features. Use a threshold segmentation method (such as the Otsu algorithm) to segment the grayscale image into foreground (weld area) and background. Apply an edge detection operator (such as the Canny operator, Sobel operator, or Prewitt operator) to detect the edge information of defects in the foreground. The edge detection operator can identify the places where the grayscale value changes drastically in the image, which are usually the edges of defects.

[0103] S403. Obtain the defect category of the weld image according to the edge information.

[0104] Specifically, extract the features of the defect from the detected edge information, such as shape, size, direction, etc. Use a machine learning algorithm (such as support vector machine, decision tree, or neural network) or a template matching method to classify the defect according to the extracted features. Welding defects include lack of fusion, porosity, overlap, and spatter. For the image blocks with lack of fusion or overlap, set the defect category as the first category. For the image blocks with spatter, set the defect category as the second category. For the image blocks with porosity, set the defect category as the third category.

[0105] Porosity refers to the cavities formed in the weld metal due to the inability of gas to escape. For example, during manual arc welding, if the shielding gas entrains air, or the welding materials (such as welding wire, flux) contain too much moisture, porosity may form in the weld. Porosity may appear in the form of evenly distributed porosity, surface porosity, worm-like, etc., seriously affecting the density and strength of the weld. Porosity reduces the effective working cross-section of the weld and lowers the mechanical strength of the joint. In welded parts requiring tightness, porosity may also affect the tightness of the welded part.

[0106] Spatter refers to the phenomenon that molten metal particles spatter out from the weld during welding. For example, in resistance spot welding, if the welding current is too large or the electrode pressure is insufficient, it may cause the liquid fusion core to break through the plastic metal ring around the weld spot under pressure, resulting in spatter. Spatter can be divided into surface spatter and internal spatter. The former affects the surface quality of the weld spot, while the latter may affect the mechanical properties of the weld spot. Spatter not only affects the appearance quality of the weld, but also may reduce the service life of the electrode and even lead to a decrease in the mechanical properties of the welded joint.

[0107] Lack of fusion refers to the phenomenon that the weld metal is not fully fused to the base metal or between weld layers, forming local lack of fusion. For example, during butt welding, if the root face is too large, the root gap is too small, or the welding heat input is insufficient, root lack of fusion may occur. In multi-layer and multi-pass welding, if the interlayer cleaning is not thorough or the welding parameters are inappropriate, interlayer lack of fusion may also occur. Lack of fusion greatly reduces the working cross-section of the weld, causing serious stress concentration, thereby reducing the strength of the joint. It often becomes the root cause of weld cracking, seriously affecting the safety and reliability of the welded structure.

[0108] A weld bead refers to a metal lump formed when molten metal flows onto the unmelted base metal outside the weld during the welding process. For example, in vertical welding and horizontal welding, if the welding current is too large, the electrode angle is incorrect, or the operating gesture is improper, the molten metal may flow outside the weld under its own weight, forming a weld bead. A weld bead usually appears as a raised metal lump on the weld surface. Weld beads not only affect the appearance quality of the weld but may also hide defects such as lack of penetration under the weld bead. The presence of weld beads may also cause deviations in the actual size of the weld, forming stress concentration areas, thereby reducing the strength and toughness of the welded joint.

[0109] S50. Obtain the defect degree of all weld map blocks according to the defect category.

[0110] Optionally, the step of obtaining the defect degree of all weld map blocks according to the defect category includes:

[0111] S501. Set the window parameters for each defect category. When the defect categories are porosity and spatter defects, the calculation formula for the defect degree is:

[0112]

[0113] where, w i represents the weight of the i-th type of defect; I(x, y) represents the gray value of the pixel at position (x, y) in the weld map block; μ represents the average gray value of the weld map block; K i (x, y) represents the Gaussian kernel function value corresponding to the i-th type of defect centered on (x, y).

[0114] Specifically, S i represents the defect degree of the i-th type of defect (porosity or spatter). ∑ (x,y)∈boundary |I(x, y) - μ|·K i (x, y) represents the summation of all pixel points (x, y) on the defect boundary. Here, boundary refers to the boundary area of the defect, which can be determined by methods such as image segmentation and edge detection. |I(x, y) - μ| represents the absolute difference between the gray value of the pixel point (x, y) and the average gray value μ of the weld map block. This difference reflects the difference between the pixel point and the overall gray level of the weld. The larger the difference, the more obvious the defect may be. K i (x, y) is the Gaussian kernel function value corresponding to the i-th type of defect centered on the pixel point (x, y). The Gaussian kernel function is a commonly used weight function, and its value gradually decreases as the distance from the center point increases. Here, it is used to weight the pixel points on the defect boundary, making the pixel points closer to the defect center contribute more to the defect degree.

[0115] K iThe formula for (x, y) is as follows:

[0116]

[0117] where (x c , y c ) represents the center coordinates of the window; σ i 2 represents the Gaussian kernel variance of the i-th type of defect, which is related to the window radius r i . Usually, but the specific relationship may vary according to the application.

[0118] According to the influence degrees of porosity and spatter defects on the weld quality, corresponding weight values w i are set; the gray values of all pixel points in the weld patch are summed up, and then divided by the total number of pixel points to obtain the average gray value μ. By methods such as image segmentation and edge detection, the boundary region of the porosity or spatter defect is determined. For each pixel point (x, y) on the defect boundary, calculate the absolute difference between its gray value and the average value μ, and multiply it by the corresponding Gaussian kernel function value K i (x, y). Sum up the contributions of all pixel points on the defect boundary, and multiply by the weight w i to obtain the final defect degree value.

[0119] Through the above formula, we can quantitatively evaluate the severity of porosity and spatter defects, providing strong support for the evaluation and control of weld quality. At the same time, since factors such as weight, gray difference, and Gaussian kernel function are considered in the formula, the evaluation results are more accurate and reliable.

[0120] Optionally, the step of obtaining the defect degrees of all weld patches according to the defect categories includes:

[0121] S502. Set the window parameters for each defect category. When the defect categories are lack of fusion and overlap bead defects, the calculation formula for the defect degree is:

[0122]

[0123] where w i represents the weight of the i-th type of defect, ΔI i (x, y) represents the gray value difference of the i-th type of defect at the position (x, y), and ΔI weld (x, y) represents the gray value difference of the weld area at the position (x, y), and γ represents a constant.

[0124] The formula for calculating the gray value difference is:

[0125] ΔI i(x,y) = |I(x,y) - μ|·K i (x,y)

[0126] In the above formula, I(x,y) represents the grayscale value of the pixel at position (x, y) in the weld map block; μ represents the average grayscale value of the weld map block; K_i(x,y) represents the Gaussian kernel function value corresponding to the i-th type of defect centered on (x, y).

[0127] For porosity and spatter defects, mainly focus on the grayscale value fluctuations in the boundary region; for lack of fusion and overlap defects, focus on the grayscale value fluctuations in the entire region (including the center and boundary).

[0128] It should be added that:

[0129] Regarding the window size: Set it according to the typical size of the defect and the width of the weld. For lack of fusion and overlap defects, the window should be large enough to cover the entire defect area, but not too large to avoid introducing too much irrelevant information.

[0130] Regarding the window shape: Usually choose a rectangular or elliptical window to adapt to the shape of the weld and the distribution of the defects. For welds or defects with irregular shapes, a custom-shaped window can be considered.

[0131] Regarding the window position: Dynamically adjust the window position according to the output of the defect detection algorithm to cover the defect area. For lack of fusion defects, the window should mainly cover the unfused part of the weld; for overlap defects, the window should include the overlap and the surrounding weld area.

[0132] Weight w i : Set according to the degree of influence of the defect on the welding quality. For example, lack of fusion defects may lead to a reduction in the strength of the welded joint, so a higher weight should be given. Although overlap defects may not necessarily affect the joint strength, they may affect the appearance and dimensional accuracy, and an appropriate weight should also be given.

[0133] The constant is used to adjust the influence of the grayscale value difference in the internal region on the total defect degree. When more attention needs to be paid to the changes inside the defect, the value of γ can be increased; when more attention needs to be paid to the changes in the entire defect area, the value of γ can be decreased.

[0134] Moreover, before calculating the defect degree, the image should be preprocessed, such as denoising, enhancing contrast, etc., to improve the accuracy and reliability of defect detection. Window parameters, weights, and constants should be optimized and adjusted according to the actual situation. The defect degree calculation results under different parameter settings can be compared through experiments or simulations, and the best parameter combination can be selected. Compare and verify the calculation results with the actual welding quality to ensure the accuracy and effectiveness of the defect degree calculation method.

[0135] S60. Evaluate the second welding quality of the weld seam according to the degree of defect.

[0136] Optionally, the step of evaluating the second welding quality of the weld seam according to the degree of defect includes:

[0137] According to the degree of defect of all weld seam blocks, perform weighted aggregation according to the type of defect to evaluate the second welding quality of the weld seam.

[0138] Specifically, first, we need to obtain data on the degree of defect from all weld seam blocks. These data may include the degree values of various defects such as pores, spatter, incomplete welding, and weld beads. Different types of defects have different degrees of influence on the weld quality. Therefore, we need to assign a weight to each type of defect according to factors such as the severity of the defect, its impact on the performance of the welded joint, and the frequency of occurrence. The size of the weight can reflect the importance of the defect to the weld quality. For example, for defects that seriously affect the strength and tightness of the welded joint (such as cracks, lack of fusion, etc.), a higher weight should be given. Using the method of weighted summation, aggregate the degree values of various defects in each weld seam block according to their corresponding weights. Obtain a comprehensive defect degree index, which can reflect the overall quality status of the weld seam. According to the aggregated defect degree index, we can evaluate the second welding quality of the weld seam.

[0139] S70. Predict the quality of the truck steel structure according to the first welding quality and the second welding quality.

[0140] Optionally, the step of predicting the quality of the truck steel structure according to the first welding quality and the second welding quality includes:

[0141] Perform weighted calculation according to the first welding quality and the second welding quality to obtain a comprehensive score, and characterize the quality of the truck steel structure through the comprehensive score.

[0142] Specifically, deeply analyze the specific impacts of the first welding quality and the second welding quality on the quality of the truck steel structure. This includes considering multiple aspects such as the strength, tightness, and durability of the welded joint. Based on the above analysis, assign reasonable weights to the first welding quality and the second welding quality. The size of the weight should reflect their respective importance to the quality of the truck steel structure. In order to eliminate the dimensional differences between different welding quality indicators, we may need to perform standardization processing on the first welding quality and the second welding quality to convert them into dimensionless values. Use the assigned weights to perform weighted summation on the standardized first welding quality and the second welding quality to obtain a comprehensive score. The calculation formula for the comprehensive score can be expressed as:

[0143] Comprehensive score = First welding quality standardization value × First welding quality weight + Second welding quality standardization value × Second welding quality weight

[0144] According to historical data or industry standards, set the threshold range of the comprehensive score to judge the quality of the truck steel structure. Compare the calculated comprehensive score with the set threshold to evaluate the quality grade of the truck steel structure. For example, a comprehensive score higher than a certain threshold may indicate excellent quality, and lower than another threshold may indicate unqualified quality. Effectively predict the quality of the truck steel structure and provide strong support for production, quality control, and continuous improvement.

[0145] Embodiment 3

[0146] Based on Embodiment 1, this embodiment provides a truck steel structure quality prediction system based on the welding results of the girder, including:

[0147] A solder joint position acquisition module configured to acquire the solder joint positions arranged in sequence of the weld according to the weld image of the girder welding position;

[0148] A spacing distribution characteristic acquisition module configured to acquire the spacing distribution characteristics of adjacent solder joints according to the solder joint positions;

[0149] A first welding quality evaluation module configured to evaluate the first welding quality of the weld according to the spacing distribution characteristics;

[0150] A defect category acquisition module configured to acquire at least one weld tile containing a preset number of solder joints according to the solder joint positions, perform weld defect identification on the weld tile, and obtain the defect category of the weld image;

[0151] A defect degree acquisition module configured to acquire the defect degrees of all weld tiles according to the defect categories;

[0152] A second welding quality acquisition module configured to evaluate the second welding quality of the weld according to the defect degrees;

[0153] A truck steel structure quality prediction module configured to predict the quality of the truck steel structure according to the first welding quality and the second welding quality.

[0154] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A truck steel structure quality prediction method based on beam welding results, characterized in that: include: According to the weld image of the beam welding position, the weld point positions of the weld are obtained in order; According to the positions of the solder joints, obtaining the spacing distribution characteristics of adjacent solder joints; evaluating a first welding quality of the weld according to the spacing distribution characteristic; Formula for assessing the first weld quality of a weld: Among them, d i represents the distance between the ith and i+1th welding points, there are n welding points in total, D represents the average welding gap between adjacent welding points, and K is the coefficient; According to the positions of the weld spots, obtaining at least one weld image block including a preset number of weld spots, performing weld defect recognition on the weld image block, and obtaining a defect category of the weld image; According to the defect category, the defect degree of all weld seam blocks is obtained; Set the window parameters for each defect category. When the defect category is pore and spatter defects, the calculation formula for the defect degree is: Among them, w i represents the weight of the i-th defect; I(x, y) represents the gray value of the pixel at position (x, y) in the weld image; μ represents the mean gray value of the weld image; K i (x, y) represents the Gaussian kernel function value corresponding to the i-th defect centered at (x, y); According to the defect degree of all weld seam blocks, weighted summary is performed according to defect type to evaluate the second welding quality of the weld seam; The quality of the steel structure of the truck is predicted according to the first welding quality and the second welding quality.

2. The truck steel structure quality prediction method based on beam welding results according to claim 1 is characterized in that: The step of obtaining the spacing distribution characteristics of adjacent solder joints according to the solder joint positions includes: According to the arrangement order of the welding points on the weld, two adjacent welding points are paired to obtain paired welding points, and the Euclidean distance between the center points of each group of paired welding points is used as the welding point spacing; The average weld point spacing of the weld is obtained according to the weld point distances of all paired weld points, and the weld point spacing of each group is compared with the average weld point spacing to obtain the spacing distribution characteristics of the paired weld points, wherein the spacing distribution characteristics characterize the weld point uniformity of the weld.

3. The truck steel structure quality prediction method based on beam welding results as claimed in claim 2, characterized in that: The step of obtaining an average weld point spacing of a weld according to the weld point distances of all paired weld points, and comparing each group of weld point spacings with the average weld point spacing to obtain the spacing distribution characteristics of the paired weld points includes: According to the solder joint distances of all paired solder joints, the maximum solder joint spacing, the minimum solder joint spacing and the average solder joint spacing are obtained; Get the maximum solder point spacing, minimum solder point spacing and average solder point spacing, and get the normal solder point spacing range; Compare the spacing between each group of solder joints with the normal spacing between solder joints, obtain abnormal paired solder joints, and send abnormal information.

4. The truck steel structure quality prediction method based on beam welding results according to claim 1 is characterized in that: The step of obtaining at least one weld image block including a preset number of welds according to the weld position, performing weld defect recognition on the weld image block, and obtaining the defect category of the weld image includes: Process the weld image to obtain a grayscale image, calculate the grayscale co-occurrence matrix of the grayscale image, and provide texture features; A threshold is set according to grayscale value or texture feature, the grayscale image is segmented into foreground and background, and edge information of defects in the foreground is detected by an edge detection operator; The defect category of the weld image is obtained according to the edge information.

5. The truck steel structure quality prediction method based on beam welding results according to claim 1, characterized in that: The step of obtaining the defect levels of all weld seam blocks according to the defect categories includes: Set the window parameters for each defect category. When the defect category is under-welding and weld bead defects, the calculation formula for the defect degree is: Among them, w i represents the weight of the i-th defect, ΔI i (x, y) represents the gray value difference of the i-th defect at the (x, y) position, ΔI weld (x, y) represents the gray value difference of the weld area at the position (x, y), and γ represents a constant.

6. The truck steel structure quality prediction method based on beam welding results according to claim 1, characterized in that: The step of predicting the quality of the truck steel structure according to the first welding quality and the second welding quality comprises: A weighted calculation is performed according to the first welding quality and the second welding quality to obtain a comprehensive score, and the quality of the truck steel structure is characterized by the comprehensive score.

7. A truck steel structure quality prediction system based on beam welding results, characterized in that: include: A welding point position acquisition module, which is configured to acquire welding point positions of the welds arranged in order according to the weld image of the beam welding position; A spacing distribution characteristic acquisition module, which is configured to acquire the spacing distribution characteristics of adjacent solder joints according to the solder joint positions; A first welding quality assessment module, configured to assess a first welding quality of the weld according to the spacing distribution characteristic; Formula for assessing the first weld quality of a weld: Among them, d i represents the distance between the ith and i+1th welding points, there are n welding points in total, D represents the average welding gap between adjacent welding points, and K is the coefficient; A defect category acquisition module, configured to acquire at least one weld image block including a preset number of welds according to the weld position, perform weld defect recognition on the weld image block, and obtain a defect category of the weld image; A defect degree acquisition module, which is configured to acquire the defect degrees of all weld seam blocks according to the defect category; Set the window parameters for each defect category. When the defect category is pore and spatter defects, the calculation formula for the defect degree is: Among them, w i represents the weight of the i-th defect; I(x, y) represents the gray value of the pixel at position (x, y) in the weld image; μ represents the mean gray value of the weld image; K i (x, y) represents the Gaussian kernel function value corresponding to the i-th defect centered at (x, y); A second welding quality acquisition module is configured to evaluate the second welding quality of the weld by weighted aggregation based on the defect levels of all weld seam blocks and defect types; A truck steel structure quality prediction module is configured to predict the truck steel structure quality according to the first welding quality and the second welding quality.

Images