技术领域Technical Field
本发明涉及焊缝图像分析技术领域，尤其涉及一种网架杆件焊接视觉识别系统。The invention relates to the technical field of weld image analysis, and in particular to a grid rod welding visual recognition system.
背景技术Background Art
在现代建筑和大型工程结构中，网架杆件作为一种重要的结构组成，广泛应用于体育场馆、展览中心、机场候机楼以及各种大跨度的覆盖结构中。网架结构以其高强度、轻质量、良好的空间刚度和经济性而受到青睐，网架杆件通常由钢管、角钢或其他金属材料制成，大部分通过焊接成网状结构，以承受各种静态和动态荷载，网架杆件的焊接质量直接关系到整个结构的安全性和可靠性，然而，焊接过程的复杂性以及焊接质量的不确定性，一直是影响结构性能和安全的主要因素，传统的焊缝质量评估方法主要依赖于人工检测和简单的非破坏检测技术，如目视检查、超声波检测和射线检测，这些方法不仅耗时耗力，而且在一定程度上受到检测人员经验和技能的限制，难以实现对焊接过程中微观结构变化和残余应力分布的精确评估。In modern buildings and large-scale engineering structures, grid members are widely used as an important structural component in stadiums, exhibition centers, airport terminals and various large-span covering structures. Grid structures are favored for their high strength, light weight, good spatial stiffness and economy. Grid members are usually made of steel pipes, angle steels or other metal materials, most of which are welded into a mesh structure to withstand various static and dynamic loads. The welding quality of grid members is directly related to the safety and reliability of the entire structure. However, the complexity of the welding process and the uncertainty of welding quality have always been the main factors affecting structural performance and safety. Traditional weld quality assessment methods mainly rely on manual inspection and simple non-destructive testing techniques such as visual inspection, ultrasonic testing and radiographic testing. These methods are not only time-consuming and labor-intensive, but also to a certain extent limited by the experience and skills of the inspectors, making it difficult to achieve accurate assessment of microstructural changes and residual stress distribution during welding.
随着计算机视觉、图像处理和有限元模拟技术的快速发展，利用这些高科技手段对焊缝进行实时监测和质量评估，成为提高焊接质量和结构可靠性的有效途径。特别是，焊缝中的微观结构特征和残余应力状态对焊接结构的力学性能和长期稳定性具有重要影响，因此，开发一种能够全面评估焊缝微观结构特征和预测残余应力分布的系统，对于优化焊接工艺参数、提高焊接结构的设计和维护效率，以及降低故障和事故风险具有重要意义。With the rapid development of computer vision, image processing and finite element simulation technology, the use of these high-tech means to monitor and evaluate the quality of welds in real time has become an effective way to improve welding quality and structural reliability. In particular, the microstructural characteristics and residual stress state in welds have an important influence on the mechanical properties and long-term stability of welded structures. Therefore, the development of a system that can comprehensively evaluate the microstructural characteristics of welds and predict the residual stress distribution is of great significance for optimizing welding process parameters, improving the design and maintenance efficiency of welded structures, and reducing the risk of failures and accidents.
然而，当前存在的技术手段和系统在处理焊接过程中的复杂现象，如热影响区(HAZ)的晶粒细化程度、晶界分布以及相变和残余应力产生机理等方面，仍存在一定的局限性，这些局限性主要表现在对焊接热影响区微观结构的精确识别和分析能力不足，以及缺乏有效的方法来预测和评估焊接过程中产生的残余应力对结构长期稳定性的影响。因此，迫切需要一种新的技术方案，以更加科学和系统的方法来解决上述问题，从而提升焊接质量控制的水平和焊接结构的整体性能。However, the existing technical means and systems still have certain limitations in dealing with complex phenomena in the welding process, such as the degree of grain refinement in the heat affected zone (HAZ), grain boundary distribution, and the mechanism of phase transformation and residual stress generation. These limitations are mainly manifested in the lack of accurate identification and analysis of the microstructure of the welding heat affected zone, and the lack of effective methods to predict and evaluate the impact of residual stress generated during welding on the long-term stability of the structure. Therefore, a new technical solution is urgently needed to solve the above problems in a more scientific and systematic way, so as to improve the level of welding quality control and the overall performance of the welded structure.
发明内容Summary of the invention
基于上述目的，本发明提供了一种网架杆件焊接视觉识别系统。Based on the above purpose, the present invention provides a grid rod welding visual recognition system.
一种网架杆件焊接视觉识别系统，包括图像采集模块、图像处理与特征提取模块以及焊缝识别分析模块，其中；A grid rod welding visual recognition system includes an image acquisition module, an image processing and feature extraction module, and a weld recognition and analysis module, wherein;
所述图像采集模块用于捕获焊缝及其HAZ(热影响区域)的图像；The image acquisition module is used to capture images of the weld and its HAZ (heat affected zone);
所述图像处理与特征提取模块对采集到的图像进行预处理，并采用图像处理技术提取焊缝关键特征以及HAZ微观结构特征，焊缝关键特征包括焊缝几何形态、微裂纹、气孔，HAZ微观结构特征包括晶粒细化程度、晶界分布以及相变；The image processing and feature extraction module pre-processes the collected images and uses image processing technology to extract key weld features and HAZ microstructure features. The key weld features include weld geometry, microcracks, and pores. The HAZ microstructure features include grain refinement, grain boundary distribution, and phase change.
所述焊缝识别分析模块具体包括：The weld identification and analysis module specifically includes:
焊缝缺陷识别与评估子模块：基于提取的焊缝关键特征，分析焊缝关键特征对焊缝整体质量的影响，评估焊缝的疲劳寿命和抗断裂能力；Weld defect identification and evaluation submodule: Based on the extracted key features of the weld, analyze the impact of the key features of the weld on the overall quality of the weld, and evaluate the fatigue life and fracture resistance of the weld;
微观结构与残余应力分析子模块：综合分析HAZ微观结构特征，进行残余应力预测，评估HAZ的应力状态和长期稳定性，分析材料微观组织变化对焊缝性能的影响，以及这些变化如何与残余应力分布相互作用，共同决定焊接结构的性能。Microstructure and residual stress analysis submodule: Comprehensively analyze the HAZ microstructure characteristics, predict residual stress, evaluate the stress state and long-term stability of the HAZ, analyze the impact of material microstructure changes on weld performance, and how these changes interact with residual stress distribution to jointly determine the performance of the welded structure.
进一步的，所述图像采集模块包括一台或多台工业相机，工业相机配置有自动或手动调整焦距和光圈的高清镜头，以适应不同焊接环境的照明条件和焊接区域的大小；Furthermore, the image acquisition module includes one or more industrial cameras, which are equipped with high-definition lenses that automatically or manually adjust the focus and aperture to adapt to the lighting conditions of different welding environments and the size of the welding area;
还包括定位驱动组件，用于控制工业相机沿焊缝和HAZ的预定路径移动，确保能够覆盖焊缝及HAZ，工业相机在焊接过程自动捕获高清图像，或在操作者的手动控制下捕获图像，捕获的图像将实时传输至图像处理与特征提取模块进行后续分析。It also includes a positioning drive component for controlling the industrial camera to move along a predetermined path of the weld and HAZ to ensure that the weld and HAZ are covered. The industrial camera automatically captures high-definition images during the welding process, or captures images under the manual control of the operator. The captured images will be transmitted in real time to the image processing and feature extraction module for subsequent analysis.
进一步的，所述图像处理与特征提取模块中的预处理包括去噪、对比度增强和边缘检测，以提高焊缝和HAZ特征的可识别度；Furthermore, the preprocessing in the image processing and feature extraction module includes denoising, contrast enhancement and edge detection to improve the recognizability of weld and HAZ features;
所述焊缝关键特征的提取包括：使用形态学分析算法来确定焊缝的几何形态，包括宽度、深度和对接质量；采用裂纹检测算法来识别焊缝中的微裂纹；通过气孔检测算法来定位和评估焊缝中的气孔大小和分布；The extraction of the key features of the weld includes: using a morphological analysis algorithm to determine the geometric shape of the weld, including width, depth and butt quality; using a crack detection algorithm to identify microcracks in the weld; and using a pore detection algorithm to locate and evaluate the size and distribution of pores in the weld.
所述HAZ微观结构特征提取包括：利用纹理分析和图像分割技术来评估晶粒的细化程度和晶界分布；通过颜色和灰度变化分析来识别不同相变区域。The HAZ microstructure feature extraction includes: using texture analysis and image segmentation technology to evaluate the grain refinement and grain boundary distribution; and identifying different phase change areas through color and grayscale change analysis.
进一步的，所述形态学分析算法使用膨胀和腐蚀操作来强调或减弱焊缝区域，具体如下；Furthermore, the morphological analysis algorithm uses dilation and erosion operations to emphasize or weaken the weld area as follows;
膨胀操作:Expansion operation:
腐蚀操作:Corrosion Operation:
其中，A是原始图像，B是结构元素，z表示图像中的像素位置，和Bz分别表示结构元素B在位置z的反射和平移，通过组合膨胀和腐蚀操作，进行开运算和闭运算，以去除小物体或填充小洞；Where A is the original image, B is the structural element, and z represents the pixel position in the image. and Bz represent the reflection and translation of the structural element B at position z, respectively. By combining dilation and erosion operations, opening and closing operations are performed to remove small objects or fill small holes;
所述裂纹检测算法利用Canny边缘检测器实现，Canny边缘检测器包括平滑、梯度计算、非极大值抑制和滞后阈值，梯度计算公式表示为:其中，G是梯度幅值，Gx和Gy分别是图像在x和y方向上的一阶导数，通过Sobel算子计算；The crack detection algorithm is implemented using the Canny edge detector, which includes smoothing, gradient calculation, non-maximum suppression and hysteresis threshold. The gradient calculation formula is expressed as: Where G is the gradient magnitude,Gx andGy are the first-order derivatives of the image in the x and y directions, respectively, calculated using the Sobel operator;
所述气孔检测算法通过分析图像中的亮度来识别气孔，使用阈值分割：其中，f(x,y)是二值化后的图像，I(x,y)是原始图像在点(x,y)的亮度值，T是选定的阈值；The pore detection algorithm identifies pores by analyzing the brightness in the image, using threshold segmentation: Where f(x,y) is the binarized image, I(x,y) is the brightness value of the original image at point (x,y), and T is the selected threshold;
所述纹理分析基于灰度共生矩阵GLCM，GLCM中的元素P(i,j|d,θ)表示在图像中，当像素间距为d且方向为θ时，灰度级i和j的像素对出现的频率,基于GLCM，计算多个纹理特征，包括对比度、均匀性和熵；The texture analysis is based on the gray level co-occurrence matrix GLCM. The element P(i, j|d, θ) in the GLCM represents the frequency of occurrence of pixel pairs of gray levels i and j in the image when the pixel spacing is d and the direction is θ. Based on the GLCM, multiple texture features are calculated, including contrast, uniformity and entropy.
所述图像分割技术用来识别和分隔出图像中的不同区域，包括晶粒区域和晶界，基于Otsu's方法自动计算最佳阈值以分割图像；The image segmentation technology is used to identify and separate different regions in the image, including grain regions and grain boundaries, and automatically calculate the optimal threshold value based on Otsu's method to segment the image;
所述相变区域的识别通过分析图像中的颜色和灰度变化来实现，不同相变区域会因为晶体结构的不同而在图像上呈现不同的颜色或灰度级，通过直方图分析来识别不同的颜色或灰度级别，计算图像中每个像素值的频率分布，对于灰度图像，直方图显示不同灰度级的分布情况，通过分析直方图的峰值和谷值，确定代表不同相变区域的灰度级或颜色范围，进而通过预设阈值来分割区域。The identification of the phase change area is achieved by analyzing the color and grayscale changes in the image. Different phase change areas will present different colors or grayscale levels on the image due to different crystal structures. Different colors or grayscale levels are identified by histogram analysis, and the frequency distribution of each pixel value in the image is calculated. For grayscale images, the histogram shows the distribution of different grayscale levels. By analyzing the peaks and valleys of the histogram, the grayscale or color range representing different phase change areas is determined, and then the area is segmented by a preset threshold.
进一步的，所述焊缝缺陷识别与评估子模块具体包括：Furthermore, the weld defect identification and assessment submodule specifically includes:
几何形态分析：通过计算焊缝的宽度、深度以及对接质量参数，评估焊缝的连续性和均匀性；Geometric analysis: evaluate the continuity and uniformity of the weld by calculating the weld width, depth and butt quality parameters;
微裂纹和气孔影响评估：利用提取的微裂纹和气孔特征，结合断裂力学原理，评估缺陷的尺寸、位置和分布对焊缝抗断裂能力的影响，通过计算裂纹尖端开度位移CTOD，预测焊缝在不同载荷条件下的疲劳裂纹扩展速率；Microcrack and porosity impact assessment: Using the extracted microcrack and porosity features and combining the principles of fracture mechanics, the impact of defect size, location and distribution on the weld's fracture resistance is assessed. By calculating the crack tip opening displacement CTOD, the fatigue crack growth rate of the weld under different load conditions is predicted;
统计分析：采用统计方法，根据焊缝中缺陷的统计数据来评估焊缝的疲劳寿命，通过建立缺陷尺寸与疲劳寿命之间的统计关系，预测在具体使用条件下焊缝的可靠性和寿命。Statistical analysis: Statistical methods are used to evaluate the fatigue life of welds based on the statistical data of defects in welds. By establishing a statistical relationship between defect size and fatigue life, the reliability and life of welds under specific use conditions are predicted.
进一步的，所述几何形态分析中的计算通过图像分析直接量化，焊缝的宽度W和深度D通过像素计数的方法确定：Furthermore, the calculations in the geometric analysis are directly quantified by image analysis, and the width W and depth D of the weld are determined by pixel counting:
焊缝宽度W：在图像中，焊缝宽度通过沿焊缝横截面计算非背景像素的数量来确定，若图像分辨率为r(单位：像素/单位长度)，则宽度W表示为：W＝nw/r其中，nw是焊缝宽度方向上非背景像素的数量；Weld width W: In the image, the weld width is determined by counting the number of non-background pixels along the cross section of the weld. If the image resolution is r (unit: pixel/unit length), the width W is expressed as: W =nw /r, wherenw is the number of non-background pixels in the weld width direction;
焊缝深度D：与焊缝宽度W计算同理，焊缝深度通过在垂直方向上计数非背景像素来确定：D＝nd/r其中，nd是焊缝深度方向上非背景像素的数量。Weld depth D: Similar to the calculation of weld width W, the weld depth is determined by counting non-background pixels in the vertical direction: D =nd /r, wherend is the number of non-background pixels in the weld depth direction.
进一步的，所述微裂纹和气孔影响评估中的裂纹尖端开度位移CTOD用于评估材料抗断裂能力，CTOD通过下式估算：Furthermore, the crack tip opening displacement CTOD in the microcrack and pore impact assessment is used to assess the material's fracture resistance, and the CTOD is estimated by the following formula:
其中，K是应力强度因子，E′是有效弹性模量，对于平面应力条件，E′＝E，对于平面应变条件，E′＝E/(1-ν2)，E是材料的弹性模量，ν是泊松比，应力强度因子K对于一个具有初始裂纹的杆件通过下式估算： Where K is the stress intensity factor, E' is the effective elastic modulus, for plane stress conditions, E' = E, for plane strain conditions, E' = E/(1-ν2 ), E is the elastic modulus of the material, ν is Poisson's ratio, and the stress intensity factor K for a bar with an initial crack is estimated by the following formula:
应力强度因子其中，σ是远场应力，a是裂纹长度。Stress Intensity Factor where σ is the far-field stress and a is the crack length.
进一步的，所述统计分析中的疲劳寿命通过Weibull分布进行，Weibull分布用于描述材料失效概率，其累积分布函数CDF为：Furthermore, the fatigue life in the statistical analysis is performed using the Weibull distribution, which is used to describe the probability of material failure, and its cumulative distribution function CDF is:
Weibull分布其中，t是寿命，η是尺度参数，用于表征疲劳寿命的特征值，β是形状参数，用于描述故障率随时间的变化；Weibull distribution Where t is the life, η is the scale parameter used to characterize the characteristic value of fatigue life, and β is the shape parameter used to describe the change of failure rate over time;
通过拟合实验数据到Weibull分布，估算出焊缝在具体使用条件下的疲劳寿命和可靠性。By fitting the experimental data to the Weibull distribution, the fatigue life and reliability of the weld under specific service conditions are estimated.
进一步的，所述微观结构与残余应力分析子模块具体包括：Furthermore, the microstructure and residual stress analysis submodule specifically includes:
残余应力预测：结合HAZ微观结构特征，采用数值模拟方法来预测HAZ区域的残余应力分布，数值模拟方法考虑焊接过程中的热循环对材料微观结构的影响，以及微观结构变化如何影响材料的力学行为和残余应力的产生；Residual stress prediction: Combined with the microstructural characteristics of the HAZ, numerical simulation methods are used to predict the residual stress distribution in the HAZ area. The numerical simulation method considers the influence of thermal cycles during welding on the microstructure of the material, and how microstructural changes affect the mechanical behavior of the material and the generation of residual stress;
应力状态和长期稳定性评估：基于残余应力预测结果，分析HAZ区域的应力状态，包括应力集中区域和应力释放路径，结合材料力学性能和历史数据，评估应力状态对HAZ区域及整个焊接结构的长期稳定性的潜在影响。Stress state and long-term stability assessment: Based on the residual stress prediction results, the stress state of the HAZ area is analyzed, including the stress concentration area and the stress release path. Combined with the material mechanical properties and historical data, the potential impact of the stress state on the long-term stability of the HAZ area and the entire welded structure is evaluated.
进一步的，所述数值模拟方法基于有限元分析技术，具体包括：Furthermore, the numerical simulation method is based on finite element analysis technology, and specifically includes:
几何模型和网格划分：在有限元软件中建立HAZ的几何模型，对几何模型进行网格划分，将其划分为多个有限的元素；Geometric model and meshing: Establish the geometric model of HAZ in the finite element software, mesh the geometric model and divide it into multiple finite elements;
模拟焊接过程的热源：使用高斯分布的面热源，其热流量q表示为：其中，P是热源功率，r是距离热源中心的半径，R是热源半径，热流量q用于描述热流量如何随着距离热源中心的增加而指数性减少；Heat source for simulating welding process: Use Gaussian distributed surface heat source, and its heat flux q is expressed as: Where P is the power of the heat source, r is the radius from the center of the heat source, R is the radius of the heat source, and the heat flux q is used to describe how the heat flux decreases exponentially as the distance from the center of the heat source increases;
边界条件和材料属性：施加温度边界条件和机械边界条件，定义材料的温度依赖性属性，包括热导率、热膨胀系数、杨氏模量；Boundary conditions and material properties: Apply temperature boundary conditions and mechanical boundary conditions to define the temperature-dependent properties of the material, including thermal conductivity, thermal expansion coefficient, and Young's modulus;
热分析和残余应力计算：进行热分析模拟焊接过程中温度的分布和演变，热分析的基本方程为热传导方程：其中，ρ是材料密度，c是比热容，T是温度，t是时间，k是热导率，Q是单位体积的热源，热分析后，使用得到的温度分布作为输入，进行机械分析来计算由热膨胀和冷却引起的应力和变形，残余应力通过弹塑性材料模型计算得到，涉及材料的应力-应变关系和屈服准则，残余应力分布可以从机械分析的结果中得到，表现为模型中每个节点的应力状态，在HAZ区域，残余应力的分布将显示出由于焊接引起的局部热循环的效果。Thermal analysis and residual stress calculation: Thermal analysis is performed to simulate the distribution and evolution of temperature during welding. The basic equation of thermal analysis is the heat conduction equation: Where ρ is the material density, c is the specific heat capacity, T is the temperature, t is the time, k is the thermal conductivity, and Q is the heat source per unit volume. After thermal analysis, the obtained temperature distribution is used as input for mechanical analysis to calculate the stress and deformation caused by thermal expansion and cooling. The residual stress is calculated using an elastic-plastic material model, which involves the stress-strain relationship and yield criterion of the material. The residual stress distribution can be obtained from the results of the mechanical analysis, which is expressed as the stress state of each node in the model. In the HAZ area, the distribution of residual stress will show the effect of local thermal cycles caused by welding.
本发明的有益效果：Beneficial effects of the present invention:
本发明，通过先进的图像处理技术和算法，能够精确识别和量化焊缝中的关键缺陷，如微裂纹和气孔，利用断裂力学原理，该模块不仅能评估这些缺陷的尺寸和分布对焊缝抗断裂能力的影响，还能预测在不同载荷条件下焊缝的疲劳裂纹扩展速率，这一全面的评估能够显著提高焊接质量的监控和控制能力，降低由于焊缝缺陷引起的结构失效风险，从而提高焊接结构的可靠性和安全性。The present invention, through advanced image processing technology and algorithms, can accurately identify and quantify key defects in welds, such as microcracks and pores. Using the principles of fracture mechanics, this module can not only evaluate the impact of the size and distribution of these defects on the weld's fracture resistance, but also predict the fatigue crack growth rate of the weld under different load conditions. This comprehensive evaluation can significantly improve the monitoring and control capabilities of welding quality, reduce the risk of structural failure caused by weld defects, and thus improve the reliability and safety of welded structures.
本发明，综合应用图像分析、纹理分析和有限元模拟技术，深入分析HAZ区域的微观结构变化，并准确预测焊接过程中产生的残余应力分布，通过识别应力集中区域和可能的应力释放路径，以及结合材料的力学性能和历史数据评估残余应力对HAZ区域及整个焊接结构长期稳定性的影响，该模块为焊接参数优化、材料选择以及后续结构设计提供了科学依据，有效提升了结构在长期服役中的稳定性和耐久性。The present invention comprehensively applies image analysis, texture analysis and finite element simulation technology to deeply analyze the microstructural changes in the HAZ area and accurately predict the residual stress distribution generated during welding. By identifying stress concentration areas and possible stress release paths, and combining the mechanical properties of the material with historical data, the influence of residual stress on the long-term stability of the HAZ area and the entire welded structure is evaluated. This module provides a scientific basis for welding parameter optimization, material selection and subsequent structural design, effectively improving the stability and durability of the structure in long-term service.
本发明，能够从微观到宏观全面评估焊接质量和焊接结构的稳定性，不仅能够及时识别和评估焊接过程中可能出现的缺陷，还能够预测和分析这些缺陷对结构长期性能的影响，为焊接工艺的改进和焊接结构的可靠性设计提供强有力的技术支撑，这种全面的评估和预测能力，大大提高了焊接结构的设计和维护效率，降低了故障和事故的风险，对提高工业焊接质量和安全性具有重要意义。The present invention can comprehensively evaluate the welding quality and the stability of the welding structure from micro to macro. It can not only timely identify and evaluate the defects that may occur in the welding process, but also predict and analyze the impact of these defects on the long-term performance of the structure, and provide strong technical support for the improvement of welding technology and the reliability design of welding structures. This comprehensive evaluation and prediction capability greatly improves the design and maintenance efficiency of welding structures, reduces the risk of failures and accidents, and is of great significance to improving the quality and safety of industrial welding.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
图1为本发明实施例的系统功能模块示意图；FIG1 is a schematic diagram of system function modules according to an embodiment of the present invention;
图2为本发明实施例的焊缝缺陷识别与评估子模块示意图。FIG. 2 is a schematic diagram of a weld defect identification and assessment submodule according to an embodiment of the present invention.
具体实施方式DETAILED DESCRIPTION
为使本发明的目的、技术方案和优点更加清楚明白，以下结合具体实施例，对本发明进一步详细说明。In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
需要说明的是，除非另外定义，本发明使用的技术术语或者科学术语应当为本发明所属领域内具有一般技能的人士所理解的通常意义。本发明中使用的“第一”、“第二”以及类似的词语并不表示任何顺序、数量或者重要性，而只是用来区分不同的组成部分。“包括”或者“包含”等类似的词语意指出现该词前面的元件或者物件涵盖出现在该词后面列举的元件或者物件及其等同，而不排除其他元件或者物件。“连接”或者“相连”等类似的词语并非限定于物理的或者机械的连接，而是可以包括电性的连接，不管是直接的还是间接的。“上”、“下”、“左”、“右”等仅用于表示相对位置关系，当被描述对象的绝对位置改变后，则该相对位置关系也可能相应地改变。It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
如图1-2所示，一种网架杆件焊接视觉识别系统，包括图像采集模块、图像处理与特征提取模块以及焊缝识别分析模块，其中；As shown in FIG1-2, a grid bar welding visual recognition system includes an image acquisition module, an image processing and feature extraction module, and a weld recognition and analysis module, wherein;
图像采集模块用于捕获焊缝及其HAZ(热影响区域)的图像；The image acquisition module is used to capture images of the weld and its HAZ (heat affected zone);
图像处理与特征提取模块对采集到的图像进行预处理，并采用图像处理技术提取焊缝关键特征以及HAZ微观结构特征，焊缝关键特征包括焊缝几何形态、微裂纹、气孔，HAZ微观结构特征包括晶粒细化程度、晶界分布以及相变；The image processing and feature extraction module pre-processes the collected images and uses image processing technology to extract key weld features and HAZ microstructure features. The key weld features include weld geometry, microcracks, and pores. The HAZ microstructure features include grain refinement, grain boundary distribution, and phase change.
焊缝识别分析模块具体包括：The weld identification and analysis module specifically includes:
焊缝缺陷识别与评估子模块：基于提取的焊缝关键特征，分析焊缝关键特征对焊缝整体质量的影响，评估焊缝的疲劳寿命和抗断裂能力；Weld defect identification and evaluation submodule: Based on the extracted key features of the weld, analyze the impact of the key features of the weld on the overall quality of the weld, and evaluate the fatigue life and fracture resistance of the weld;
微观结构与残余应力分析子模块：综合分析HAZ微观结构特征，进行残余应力预测，评估HAZ的应力状态和长期稳定性，分析材料微观组织变化对焊缝性能的影响，以及这些变化如何与残余应力分布相互作用，共同决定焊接结构的性能。Microstructure and residual stress analysis submodule: Comprehensively analyze the HAZ microstructure characteristics, predict residual stress, evaluate the stress state and long-term stability of the HAZ, analyze the impact of material microstructure changes on weld performance, and how these changes interact with residual stress distribution to jointly determine the performance of the welded structure.
图像采集模块包括一台或多台工业相机，工业相机配置有自动或手动调整焦距和光圈的高清镜头，以适应不同焊接环境的照明条件和焊接区域的大小；The image acquisition module includes one or more industrial cameras, which are equipped with high-definition lenses that can automatically or manually adjust the focus and aperture to adapt to the lighting conditions of different welding environments and the size of the welding area;
还包括定位驱动组件，用于控制工业相机沿焊缝和HAZ的预定路径移动，确保能够覆盖焊缝及HAZ，工业相机在焊接过程自动捕获高清图像，或在操作者的手动控制下捕获图像，捕获的图像将实时传输至图像处理与特征提取模块进行后续分析。It also includes a positioning drive component for controlling the industrial camera to move along a predetermined path of the weld and HAZ to ensure that the weld and HAZ are covered. The industrial camera automatically captures high-definition images during the welding process, or captures images under the manual control of the operator. The captured images will be transmitted in real time to the image processing and feature extraction module for subsequent analysis.
定位驱动组件包括一套线性导轨和伺服电机组合，该组合控制工业相机沿着焊缝和HAZ的预定路径进行精确移动，该定位驱动组件还包含一个编码器，用于实时监控工业相机的位置，确保图像捕获点的准确性，伺服电机的速度和加速度根据焊缝的特性和HAZ的宽度进行调节，以适应不同焊接速度和热输入条件下的图像采集需求。此外，定位驱动组件还配备有振动抑制系统，用于减少操作环境中的振动对工业相机定位精度的影响，保证在动态焊接过程中也能获得稳定、清晰的图像。通过这种精密控制，工业相机能够沿焊缝和HAZ执行复杂的移动轨迹，包括直线、曲线以及焊接接头周围的环形路径，从而全面捕获焊接区域的高清晰度图像，为后续的图像处理和特征提取提供准确的数据基础。The positioning drive assembly includes a set of linear guides and servo motors, which control the industrial camera to move precisely along the predetermined path of the weld and HAZ. The positioning drive assembly also contains an encoder for real-time monitoring of the position of the industrial camera to ensure the accuracy of the image capture point. The speed and acceleration of the servo motor are adjusted according to the characteristics of the weld and the width of the HAZ to meet the image acquisition requirements under different welding speeds and heat input conditions. In addition, the positioning drive assembly is also equipped with a vibration suppression system to reduce the impact of vibration in the operating environment on the positioning accuracy of the industrial camera, ensuring that stable and clear images can be obtained even during dynamic welding. Through this precision control, the industrial camera is able to perform complex movement trajectories along the weld and HAZ, including straight lines, curves, and circular paths around the weld joint, thereby fully capturing high-definition images of the welding area and providing an accurate data basis for subsequent image processing and feature extraction.
图像处理与特征提取模块中的预处理包括去噪、对比度增强和边缘检测，以提高焊缝和HAZ特征的可识别度；Preprocessing in the image processing and feature extraction module includes denoising, contrast enhancement, and edge detection to improve the recognizability of weld and HAZ features;
焊缝关键特征的提取包括：使用形态学分析算法来确定焊缝的几何形态，包括宽度、深度和对接质量；采用裂纹检测算法来识别焊缝中的微裂纹；通过气孔检测算法来定位和评估焊缝中的气孔大小和分布；The extraction of key weld features includes: using morphological analysis algorithms to determine the geometry of welds, including width, depth, and butt quality; using crack detection algorithms to identify microcracks in welds; and using pore detection algorithms to locate and evaluate the size and distribution of pores in welds.
HAZ微观结构特征提取包括：利用纹理分析和图像分割技术来评估晶粒的细化程度和晶界分布；通过颜色和灰度变化分析来识别不同相变区域。The extraction of HAZ microstructure features includes: using texture analysis and image segmentation technology to evaluate the degree of grain refinement and grain boundary distribution; and identifying different phase change areas through color and grayscale change analysis.
形态学分析算法使用膨胀和腐蚀操作来强调或减弱焊缝区域，具体如下；The morphological analysis algorithm uses dilation and erosion operations to emphasize or weaken the weld area as follows;
膨胀操作:Expansion operation:
腐蚀操作：Corrosion Operation:
其中，A是原始图像，B是结构元素，z表示图像中的像素位置，和Bz分别表示结构元素B在位置z的反射和平移，通过组合膨胀和腐蚀操作，进行开运算和闭运算，以去除小物体或填充小洞；Where A is the original image, B is the structural element, and z represents the pixel position in the image. and Bz represent the reflection and translation of the structural element B at position z, respectively. By combining dilation and erosion operations, opening and closing operations are performed to remove small objects or fill small holes;
裂纹检测算法利用Canny边缘检测器实现，Canny边缘检测器包括平滑、梯度计算、非极大值抑制和滞后阈值，梯度计算公式表示为：其中，G是梯度幅值，Gx和Gy分别是图像在x和y方向上的一阶导数，通过Sobel算子计算；The crack detection algorithm is implemented using the Canny edge detector, which includes smoothing, gradient calculation, non-maximum suppression and hysteresis threshold. The gradient calculation formula is expressed as: Where G is the gradient magnitude,Gx andGy are the first-order derivatives of the image in the x and y directions, respectively, calculated using the Sobel operator;
气孔检测算法通过分析图像中的亮度来识别气孔，使用阈值分割：其中，f(x，y)是二值化后的图像，I(x，y)是原始图像在点(x，y)的亮度值，T是选定的阈值；The pore detection algorithm identifies pores by analyzing the brightness in the image, using threshold segmentation: Where f(x, y) is the binarized image, I(x, y) is the brightness value of the original image at point (x, y), and T is the selected threshold;
纹理分析基于灰度共生矩阵GLCM，GLCM中的元素P(i，j|d，θ)表示在图像中，当像素间距为d且方向为θ时，灰度级i和j的像素对出现的频率，基于GLCM，计算多个纹理特征，包括对比度、均匀性和熵：Texture analysis is based on the gray-level co-occurrence matrix GLCM. The element P(i, j|d, θ) in GLCM represents the frequency of occurrence of pixel pairs of gray levels i and j in the image when the pixel spacing is d and the direction is θ. Based on GLCM, multiple texture features are calculated, including contrast, uniformity, and entropy:
对比度＝∑i，j(i-j)2(P(i，j))；Contrast = ∑i, j (ij)2 (P(i, j));
熵＝-∑i，jP(i，j)log(P(i，j))；Entropy=-∑i,j P(i,j)log(P(i,j));
图像分割技术用来识别和分隔出图像中的不同区域，包括晶粒区域和晶界，基于0tsu’s方法自动计算最佳阈值以分割图像，具体表示为：Image segmentation technology is used to identify and separate different areas in the image, including grain areas and grain boundaries. The optimal threshold is automatically calculated based on Otsu’s method to segment the image, which is specifically expressed as:
其中，是类间方差，ω0(t)，ω1(t)是两个类的概率，而μ0(t)，μ1(t)是两个类的平均灰度值，Otsu’s方法通过最大化类间方差来确定最佳阈值t； in, is the inter-class variance, ω0 (t), ω1 (t) are the probabilities of the two classes, and μ0 (t), μ1 (t) are the average gray values of the two classes. Otsu's method determines the optimal threshold t by maximizing the inter-class variance;
相变区域的识别通过分析图像中的颜色和灰度变化来实现，不同相变区域会因为晶体结构的不同而在图像上呈现不同的颜色或灰度级，通过直方图分析来识别不同的颜色或灰度级别，计算图像中每个像素值的频率分布，对于灰度图像，直方图显示不同灰度级的分布情况，通过分析直方图的峰值和谷值，确定代表不同相变区域的灰度级或颜色范围，进而通过预设阈值来分割区域；The identification of phase change regions is achieved by analyzing the color and grayscale changes in the image. Different phase change regions will present different colors or grayscale levels on the image due to different crystal structures. Different colors or grayscale levels are identified through histogram analysis. The frequency distribution of each pixel value in the image is calculated. For grayscale images, the histogram shows the distribution of different grayscale levels. By analyzing the peaks and valleys of the histogram, the grayscale or color range representing different phase change regions is determined, and then the region is segmented by a preset threshold.
结合纹理分析、图像分割技术以及颜色和灰度变化分析，可以有效地评估HAZ中的晶粒细化程度、晶界分布，并识别不同的相变区域。这些分析提供了关于材料微观结构变化的重要信息，对于理解焊接过程对材料性能的影响至关重要。Combining texture analysis, image segmentation technology, and color and grayscale change analysis can effectively evaluate the grain refinement, grain boundary distribution, and identify different phase transformation areas in the HAZ. These analyses provide important information about the changes in the material's microstructure, which is essential for understanding the impact of the welding process on material properties.
直方图H定义为：H(k)＝nk，其中，H(k)是直方图中第k个灰度级的像素数量，nk是图像中灰度级为k的像素数量，k的范围一般是0,L-1,L是图像中可能的灰度级总数(对于8位图像，L＝256)，通过直方图分析，可以识别出图像中的主要灰度级及其分布情况，对于相变区域的识别，特定的相变可能导致材料在图像中呈现特定的灰度级范围，通过观察直方图中的峰值(高频灰度级)和谷值(低频灰度级)，可以确定代表不同相变区域的灰度级范围：The histogram H is defined as: H(k) =nk , where H(k) is the number of pixels at the kth gray level in the histogram,nk is the number of pixels at gray level k in the image, k generally ranges from 0 to L-1, and L is the total number of possible gray levels in the image (for 8-bit images, L = 256). Through histogram analysis, the main gray levels in the image and their distribution can be identified. For the identification of phase change regions, a specific phase change may cause the material to present a specific gray level range in the image. By observing the peaks (high-frequency gray levels) and valleys (low-frequency gray levels) in the histogram, the gray level ranges representing different phase change regions can be determined:
直方图中的一个明显峰值可能表明图像中有一个主要的灰度级，这可能与特定的相变区域对应。A clear peak in the histogram may indicate that there is a major gray level in the image, which may correspond to a specific phase change region.
直方图的谷值可以帮助识别不同相变区域之间的分界线，因为谷值通常表示两个不同区域的过渡。The valleys of the histogram can help identify the boundaries between different phase change regions, as the valleys usually represent the transition between two different regions.
焊缝缺陷识别与评估子模块具体包括：The weld defect identification and assessment submodule specifically includes:
几何形态分析：通过计算焊缝的宽度、深度以及对接质量参数，评估焊缝的连续性和均匀性，焊缝几何形态的不一致性可能导致应力集中，从而影响焊接结构的疲劳寿命；Geometric analysis: evaluate the continuity and uniformity of the weld by calculating the width, depth and butt quality parameters of the weld. Inconsistency in weld geometry may lead to stress concentration, thus affecting the fatigue life of the welded structure.
微裂纹和气孔影响评估：利用提取的微裂纹和气孔特征，结合断裂力学原理，评估缺陷的尺寸、位置和分布对焊缝抗断裂能力的影响，通过计算裂纹尖端开度位移CTOD，预测焊缝在不同载荷条件下的疲劳裂纹扩展速率；Microcrack and porosity impact assessment: Using the extracted microcrack and porosity features and combining the principles of fracture mechanics, the impact of defect size, location and distribution on the weld's fracture resistance is assessed. By calculating the crack tip opening displacement CTOD, the fatigue crack growth rate of the weld under different load conditions is predicted;
统计分析：采用统计方法，根据焊缝中缺陷的统计数据来评估焊缝的疲劳寿命，通过建立缺陷尺寸与疲劳寿命之间的统计关系，预测在具体使用条件下焊缝的可靠性和寿命。Statistical analysis: Statistical methods are used to evaluate the fatigue life of welds based on the statistical data of defects in welds. By establishing a statistical relationship between defect size and fatigue life, the reliability and life of welds under specific use conditions are predicted.
几何形态分析中的计算通过图像分析直接量化，焊缝的宽度W和深度D通过像素计数的方法确定：The calculations in the geometric analysis are directly quantified by image analysis, and the width W and depth D of the weld are determined by pixel counting:
焊缝宽度W：在图像中，焊缝宽度通过沿焊缝横截面计算非背景像素的数量来确定，若图像分辨率为r(单位：像素/单位长度)，则宽度W表示为：W＝nw/r其中，nw是焊缝宽度方向上非背景像素的数量；Weld width W: In the image, the weld width is determined by counting the number of non-background pixels along the cross section of the weld. If the image resolution is r (unit: pixel/unit length), the width W is expressed as: W =nw /r, wherenw is the number of non-background pixels in the weld width direction;
焊缝深度D：与焊缝宽度W计算同理，焊缝深度通过在垂直方向上计数非背景像素来确定：D＝nd/r其中，nd是焊缝深度方向上非背景像素的数量。Weld depth D: Similar to the calculation of weld width W, the weld depth is determined by counting non-background pixels in the vertical direction: D =nd /r, wherend is the number of non-background pixels in the weld depth direction.
微裂纹和气孔影响评估中的裂纹尖端开度位移CTOD用于评估材料抗断裂能力，CTOD通过下式估算：The crack tip opening displacement (CTOD) in the evaluation of microcracks and pores is used to evaluate the material's fracture resistance. CTOD is estimated by the following formula:
其中，K是应力强度因子，E′是有效弹性模量，对于平面应力条件，E′＝E，对于平面应变条件，E′＝E/(1-ν2)，E是材料的弹性模量，ν是泊松比，应力强度因子K对于一个具有初始裂纹的杆件通过下式估算： Where K is the stress intensity factor, E' is the effective elastic modulus, for plane stress conditions, E' = E, for plane strain conditions, E' = E/(1-ν2 ), E is the elastic modulus of the material, ν is Poisson's ratio, and the stress intensity factor K for a bar with an initial crack is estimated by the following formula:
应力强度因子其中，σ是远场应力，a是裂纹长度。Stress Intensity Factor where σ is the far-field stress and a is the crack length.
统计分析中的疲劳寿命通过Weibull分布进行，Weibull分布用于描述材料失效概率，其累积分布函数CDF为：The fatigue life in statistical analysis is carried out through Weibull distribution, which is used to describe the probability of material failure. Its cumulative distribution function CDF is:
Weibull分布其中，t是寿命，η是尺度参数，用于表征疲劳寿命的特征值，β是形状参数，用于描述故障率随时间的变化；Weibull distribution Where t is the life, η is the scale parameter used to characterize the characteristic value of fatigue life, and β is the shape parameter used to describe the change of failure rate over time;
通过拟合实验数据到Weibull分布，估算出焊缝在具体使用条件下的疲劳寿命和可靠性，具体方案如下：By fitting the experimental data to the Weibull distribution, the fatigue life and reliability of the weld under specific service conditions are estimated. The specific scheme is as follows:
1.数据收集：首先收集一组焊缝在具体使用条件下的疲劳寿命数据，这些数据来自标准疲劳测试，记录焊缝在不同应力水平下的疲劳寿命(即，直到焊缝出现疲劳失效的循环次数)。1. Data collection: First, collect a set of fatigue life data of welds under specific service conditions. These data come from standard fatigue tests and record the fatigue life of welds at different stress levels (i.e., the number of cycles until fatigue failure occurs in the weld).
2.数据排序：将收集到的疲劳寿命数据从最小到最大排序，并分配相应的排名。2. Data sorting: Sort the collected fatigue life data from smallest to largest and assign corresponding rankings.
3.估算Weibull分布参数：根据上述Weibull分布的累积分布函数(CDF)，使用线性回归方法来估算Weibull参数η和β，首先，转换WeibullCDF为线性形式：ln(ln(1/(1-F(t))))＝βln(t)-βln(η)，其中，F(t)可使用经验公式估计：i是排名，n是数据点总数，在ln(ln(1/(1-F(ti))))与ln(ti)的图中进行线性回归分析，斜率即为β，截距即为-βln(η)，从而计算出η。3. Estimation of Weibull distribution parameters: Based on the cumulative distribution function (CDF) of the Weibull distribution, the linear regression method is used to estimate the Weibull parameters η and β. First, the Weibull CDF is converted into a linear form: ln(ln(1/(1-F(t))))=βln(t)-βln(η), where F(t) can be estimated using the empirical formula: i is the rank, n is the total number of data points, and linear regression analysis is performed on the plot of ln(ln(1/(1-F(ti )))) versus ln(ti ). The slope is β and the intercept is -βln(η), thereby calculating η.
4.疲劳寿命和可靠性的估算：利用估算出的Weibull参数η和β，计算任意累积失效概率F(t)对应的疲劳寿命t：4. Estimation of fatigue life and reliability: Using the estimated Weibull parameters η and β, calculate the fatigue life t corresponding to any cumulative failure probability F(t):
t＝η(-ln(1-F(t)))1/β；t＝η(-ln(1-F(t)))1/β ；
可靠性R(t)与累积失效概率相对应，定义为在时间t内未发生失效的概率：Reliability R(t) corresponds to the cumulative failure probability, which is defined as the probability that no failure occurs within time t:
通过选择特定的F(t)值(例如，对于设计寿命内的可靠性要求)，计算出对应的疲劳寿命t和可靠R(t)。 By selecting a specific F(t) value (for example, for the reliability requirement within the design life), the corresponding fatigue life t and reliability R(t) are calculated.
利用上述方法，可以得到焊缝在给定应力水平和使用条件下的疲劳寿命预测以及相应的可靠性评估，这些信息对于焊接结构设计、性能评估和寿命预测具有重要价值，实际应用中，参数的估算和数据的拟合依赖统计软件或数学工具包来实现，包括MATLAB、Python(SciPy、NumPy)、R。Using the above method, the fatigue life prediction and corresponding reliability evaluation of the weld under given stress levels and service conditions can be obtained. This information is of great value for welding structure design, performance evaluation and life prediction. In practical applications, parameter estimation and data fitting rely on statistical software or mathematical toolkits, including MATLAB, Python (SciPy, NumPy), and R.
微观结构与残余应力分析子模块具体包括：The microstructure and residual stress analysis submodules include:
残余应力预测：结合HAZ微观结构特征，采用数值模拟方法来预测HAZ区域的残余应力分布，数值模拟方法考虑焊接过程中的热循环对材料微观结构的影响，以及微观结构变化如何影响材料的力学行为和残余应力的产生；Residual stress prediction: Combined with the microstructural characteristics of the HAZ, numerical simulation methods are used to predict the residual stress distribution in the HAZ area. The numerical simulation method considers the influence of thermal cycles during welding on the microstructure of the material, and how microstructural changes affect the mechanical behavior of the material and the generation of residual stress;
应力状态和长期稳定性评估：基于残余应力预测结果，分析HAZ区域的应力状态，包括应力集中区域和应力释放路径，结合材料力学性能和历史数据，评估应力状态对HAZ区域及整个焊接结构的长期稳定性的潜在影响。Stress state and long-term stability assessment: Based on the residual stress prediction results, the stress state of the HAZ area is analyzed, including the stress concentration area and stress release path. Combined with the material mechanical properties and historical data, the potential impact of the stress state on the long-term stability of the HAZ area and the entire welded structure is evaluated.
数值模拟方法基于有限元分析技术，具体包括：The numerical simulation method is based on finite element analysis technology, including:
几何模型和网格划分：在有限元软件中建立HAZ的几何模型，对几何模型进行网格划分，将其划分为多个有限的元素；Geometric model and meshing: Establish the geometric model of HAZ in the finite element software, mesh the geometric model and divide it into multiple finite elements;
模拟焊接过程的热源：使用高斯分布的面热源，其热流量q表示为：其中，P是热源功率，r是距离热源中心的半径，R是热源半径，热流量q用于描述热流量如何随着距离热源中心的增加而指数性减少；Heat source for simulating welding process: Use Gaussian distributed surface heat source, whose heat flux q is expressed as: Where P is the power of the heat source, r is the radius from the center of the heat source, R is the radius of the heat source, and the heat flux q is used to describe how the heat flux decreases exponentially as the distance from the center of the heat source increases;
边界条件和材料属性：施加温度边界条件和机械边界条件，定义材料的温度依赖性属性，包括热导率、热膨胀系数、杨氏模量；Boundary conditions and material properties: Apply temperature boundary conditions and mechanical boundary conditions to define the temperature-dependent properties of the material, including thermal conductivity, thermal expansion coefficient, and Young's modulus;
热分析和残余应力计算：进行热分析模拟焊接过程中温度的分布和演变，热分析的基本方程为热传导方程：其中，ρ是材料密度，c是比热容，T是温度，t是时间，k是热导率，Q是单位体积的热源，热分析后，使用得到的温度分布作为输入，进行机械分析来计算由热膨胀和冷却引起的应力和变形，残余应力通过弹塑性材料模型计算得到，涉及材料的应力-应变关系和屈服准则，残余应力分布可以从机械分析的结果中得到，表现为模型中每个节点的应力状态，在HAZ区域，残余应力的分布将显示出由于焊接引起的局部热循环的效果。Thermal analysis and residual stress calculation: Thermal analysis is performed to simulate the distribution and evolution of temperature during welding. The basic equation of thermal analysis is the heat conduction equation: Where ρ is the material density, c is the specific heat capacity, T is the temperature, t is the time, k is the thermal conductivity, and Q is the heat source per unit volume. After thermal analysis, the obtained temperature distribution is used as input for mechanical analysis to calculate the stress and deformation caused by thermal expansion and cooling. The residual stress is calculated using an elastic-plastic material model, which involves the stress-strain relationship and yield criterion of the material. The residual stress distribution can be obtained from the results of the mechanical analysis, which is expressed as the stress state of each node in the model. In the HAZ area, the distribution of residual stress will show the effect of local thermal cycles caused by welding.
在有限元分析(FEA)中，通过弹塑性材料模型计算残余应力涉及模拟材料在焊接热循环下的非线性行为，弹塑性分析考虑了材料从弹性行为过渡到塑性行为的过程，并能够捕捉由于材料屈服造成的永久变形。以下是计算过程的基本步骤和相关概念：In finite element analysis (FEA), the calculation of residual stresses through the elastic-plastic material model involves simulating the nonlinear behavior of the material under welding thermal cycles. The elastic-plastic analysis takes into account the process of the material transitioning from elastic behavior to plastic behavior and can capture the permanent deformation caused by material yielding. The following are the basic steps and related concepts of the calculation process:
1.材料的应力-应变关系：在弹塑性材料模型中，应力-应变关系包括两部分：弹性部分和塑性部分，弹性行为遵循胡克定律，表示为：σ＝Eεe，其中，σ是应力，E是杨氏模量，εe是弹性应变，当材料达到屈服应力σy时，将开始发生塑性变形。塑性应变εp的增加不再导致应力的增加(对于理想塑性材料)或导致较小的应力增加(对于强化材料)。1. Material stress-strain relationship: In the elastic-plastic material model, the stress-strain relationship consists of two parts: the elastic part and the plastic part. The elastic behavior follows Hooke's law, expressed as: σ = Eεe , where σ is stress, E is Young's modulus, and εe is elastic strain. When the material reaches the yield stress σy , plastic deformation will begin to occur. The increase in plastic strain εp no longer leads to an increase in stress (for ideal plastic materials) or leads to a smaller stress increase (for reinforced materials).
2.屈服准则：屈服准则定义了材料开始发生塑性变形的条件，采用冯米塞斯准则：其中，s是偏应力张量，σy是屈服应力。2. Yield criterion: The yield criterion defines the conditions under which the material begins to undergo plastic deformation, using the von Mises criterion: where s is the deviatoric stress tensor andσy is the yield stress.
3.弹塑性流动法则：当材料屈服后，基于Prandtl-Reuss流动法则来描述塑性变形的发展，它假设塑性应变增量的方向与偏应力张量的偏导数相同：其中，dεp是塑性应变增量，dλ是塑性乘子增量。3. Elastic-plastic flow law: After the material yields, the development of plastic deformation is described based on the Prandtl-Reuss flow law, which assumes that the direction of the plastic strain increment is the same as the partial derivative of the deviatoric stress tensor: Where dεp is the plastic strain increment and dλ is the plastic multiplier increment.
4.残余应力的计算：在FEA中，残余应力是通过逐步加载和卸载过程来计算的，以模拟焊接过程中的热循环对材料的影响。在加载过程中(由于热膨胀)，应用增量载荷和相应的热输入，然后在卸载过程中(冷却)去除这些载荷，但保留由于塑性变形引起的永久变形，残余应力是在整个模型卸载后得到的应力状态。4. Calculation of residual stress: In FEA, residual stress is calculated through a step-by-step loading and unloading process to simulate the effects of thermal cycles on the material during welding. During the loading process (due to thermal expansion), incremental loads and corresponding heat inputs are applied, and then these loads are removed during the unloading process (cooling), but permanent deformations due to plastic deformation are retained. Residual stress is the stress state obtained after the entire model is unloaded.
通过上述过程，有限元软件能够模拟焊接过程中的热效应、应力和变形，包括由于塑性变形引起的残余应力。Through the above process, the finite element software is able to simulate the thermal effects, stresses and deformations during welding, including residual stresses caused by plastic deformation.
应力状态和长期稳定性评估还包括：Stress state and long-term stability assessment also includes:
1.应力状态分析：1. Stress state analysis:
识别应力集中区域：使用有限元分析(FEA)的残余应力结果，识别HAZ及焊缝周围的高应力区域，这些区域是由于焊接过程中的不均匀加热和冷却、材料性能差异以及几何不连续性(如焊缝的起止点)造成的。Identify areas of stress concentration: Use residual stress results from finite element analysis (FEA) to identify high stress areas in the HAZ and around welds that are caused by uneven heating and cooling during welding, differences in material properties, and geometric discontinuities such as the start and end points of welds.
确定应力释放路径：分析结构的应力流线和应力分布，确定应力从高应力区域向低应力区域的可能释放路径，包括评估结构的整体布局、连接方式以及局部几何形状对应力重新分布的影响。Determine stress release paths: Analyze the stress streamlines and stress distribution of the structure to determine possible stress release paths from high stress areas to low stress areas, including evaluating the overall layout of the structure, the connection method, and the impact of local geometry on stress redistribution.
2.材料力学性能评估：2. Material mechanical properties evaluation:
材料塑性特性：考虑HAZ区域及其附近材料的屈服强度、抗拉强度和塑性变形能力，材料特性会受到焊接热循环的影响，导致HAZ区域的力学性能与母材有所不同。Material plastic properties: Considering the yield strength, tensile strength and plastic deformation capacity of the materials in the HAZ area and its vicinity, the material properties will be affected by the welding thermal cycle, resulting in the mechanical properties of the HAZ area being different from those of the parent material.
疲劳与断裂特性：评估HAZ区域材料的疲劳寿命和断裂韧性，残余应力，特别是拉应力，会降低材料的疲劳寿命，增加裂纹扩展的可能性。Fatigue and fracture properties: Evaluate the fatigue life and fracture toughness of materials in the HAZ area. Residual stress, especially tensile stress, will reduce the fatigue life of the material and increase the possibility of crack propagation.
3.历史数据和案例分析：研究历史上与所分析结构类似的焊接结构的失效案例，特别关注与残余应力相关的失效模式，如疲劳裂纹的形成和扩展，参考实验室测试或现场监测得到的数据，包括关于特定焊接材料和工艺的残余应力测量结果，以及这些残余应力如何随时间变化。3. Historical data and case analysis: Study historical failure cases of welded structures similar to the one being analyzed, with a particular focus on failure modes related to residual stresses, such as fatigue crack formation and growth, and refer to data obtained from laboratory testing or field monitoring, including residual stress measurements for specific welding materials and processes, and how these residual stresses change over time.
4.长期稳定性评估：基于残余应力分布和材料的疲劳特性，评估HAZ区域及其附近的疲劳寿命，使用疲劳裂纹扩展理论，来预测裂纹在循环载荷作用下的扩展速率，对于存在高残余拉应力的区域，评估材料的断裂韧性是否足以抵抗由于缺陷(如微裂纹)引起的断裂，考虑实际服役条件下可能的载荷波动、温度变化以及环境因素(如腐蚀)对HAZ区域及整个焊接结构稳定性的影响。4. Long-term stability assessment: Based on the residual stress distribution and fatigue properties of the material, the fatigue life of the HAZ area and its vicinity is evaluated. The fatigue crack growth theory is used to predict the crack growth rate under cyclic load. For areas with high residual tensile stress, the fracture toughness of the material is evaluated to be sufficient to resist fracture caused by defects (such as microcracks). The possible load fluctuations, temperature changes and environmental factors (such as corrosion) under actual service conditions are considered to affect the stability of the HAZ area and the entire welded structure.
所属领域的普通技术人员应当理解：以上任何实施例的讨论仅为示例性的，并非旨在暗示本发明的范围被限于这些例子；在本发明的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明的不同方面的许多其它变化，为了简明它们没有在细节中提供。Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.
本发明旨在涵盖落入权利要求的宽泛范围之内的所有这样的替换、修改和变型。因此，凡在本发明的精神和原则之内，所做的任何省略、修改、等同替换、改进等，均应包含在本发明的保护范围之内。The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410363232.7ACN118758857A (en) | 2024-03-28 | 2024-03-28 | A visual recognition system for welding grid rods |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410363232.7ACN118758857A (en) | 2024-03-28 | 2024-03-28 | A visual recognition system for welding grid rods |
| Publication Number | Publication Date |
|---|---|
| CN118758857Atrue CN118758857A (en) | 2024-10-11 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410363232.7APendingCN118758857A (en) | 2024-03-28 | 2024-03-28 | A visual recognition system for welding grid rods |
| Country | Link |
|---|---|
| CN (1) | CN118758857A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118937626A (en)* | 2024-10-14 | 2024-11-12 | 江苏菲尔浦工程科技有限公司 | Steel structure lap quality detection device and method |
| CN119973299A (en)* | 2025-04-14 | 2025-05-13 | 西南石油大学 | Intelligent tracking method and system for free-curve welds by a robotic arm |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000180422A (en)* | 1998-12-14 | 2000-06-30 | Nkk Corp | Inspection method and apparatus for seam welded thin sheet lap |
| CN105976352A (en)* | 2016-04-14 | 2016-09-28 | 北京工业大学 | Weld seam surface detect feature extraction method based on grayscale image morphology |
| CN110472283A (en)* | 2019-07-12 | 2019-11-19 | 中国核动力研究设计院 | It is a kind of for estimating the loseless method of annular solder structural volume residual stress |
| CN113295688A (en)* | 2021-04-16 | 2021-08-24 | 开封大学 | Detection system and detection method for fatigue strength of welding part |
| CN114862775A (en)* | 2022-04-21 | 2022-08-05 | 广州东焊智能装备有限公司 | Visual identification system of welding robot |
| CN115829965A (en)* | 2022-11-29 | 2023-03-21 | 重庆邮电大学 | A detection method of air hole defects in X-ray images based on deep learning |
| CN116843680A (en)* | 2023-08-29 | 2023-10-03 | 深圳市华盛源机电有限公司 | IGBT power module radiator surface defect identification method |
| CN117283094A (en)* | 2023-11-22 | 2023-12-26 | 内蒙古工业大学 | Welding system capable of automatically tracking and applying ultrasonic assistance |
| CN117705877A (en)* | 2023-12-13 | 2024-03-15 | 北京理工大学 | Unmanned aerial vehicle infrared imaging scanning method for residual stress and fatigue crack of welding seam of U-shaped rib and bridge deck of steel structure bridge box |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000180422A (en)* | 1998-12-14 | 2000-06-30 | Nkk Corp | Inspection method and apparatus for seam welded thin sheet lap |
| CN105976352A (en)* | 2016-04-14 | 2016-09-28 | 北京工业大学 | Weld seam surface detect feature extraction method based on grayscale image morphology |
| CN110472283A (en)* | 2019-07-12 | 2019-11-19 | 中国核动力研究设计院 | It is a kind of for estimating the loseless method of annular solder structural volume residual stress |
| CN113295688A (en)* | 2021-04-16 | 2021-08-24 | 开封大学 | Detection system and detection method for fatigue strength of welding part |
| CN114862775A (en)* | 2022-04-21 | 2022-08-05 | 广州东焊智能装备有限公司 | Visual identification system of welding robot |
| CN115829965A (en)* | 2022-11-29 | 2023-03-21 | 重庆邮电大学 | A detection method of air hole defects in X-ray images based on deep learning |
| CN116843680A (en)* | 2023-08-29 | 2023-10-03 | 深圳市华盛源机电有限公司 | IGBT power module radiator surface defect identification method |
| CN117283094A (en)* | 2023-11-22 | 2023-12-26 | 内蒙古工业大学 | Welding system capable of automatically tracking and applying ultrasonic assistance |
| CN117705877A (en)* | 2023-12-13 | 2024-03-15 | 北京理工大学 | Unmanned aerial vehicle infrared imaging scanning method for residual stress and fatigue crack of welding seam of U-shaped rib and bridge deck of steel structure bridge box |
| Title |
|---|
| 孙正: "基于图像的焊接缺陷提取与识别方法研究", 《中国博士学位论文全文数据库 (信息科技辑)》, no. 1, 15 January 2011 (2011-01-15)* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118937626A (en)* | 2024-10-14 | 2024-11-12 | 江苏菲尔浦工程科技有限公司 | Steel structure lap quality detection device and method |
| CN119973299A (en)* | 2025-04-14 | 2025-05-13 | 西南石油大学 | Intelligent tracking method and system for free-curve welds by a robotic arm |
| Publication | Publication Date | Title |
|---|---|---|
| KR102256181B1 (en) | Method of inspecting and evaluating coating state of steel structure and system for the same | |
| Miao et al. | Cost-effective system for detection and quantification of concrete surface cracks by combination of convolutional neural network and image processing techniques | |
| CN118758857A (en) | A visual recognition system for welding grid rods | |
| CN107782733B (en) | Image recognition nondestructive detection device and method for metal surface defects | |
| CN110175658A (en) | A kind of distress in concrete recognition methods based on YOLOv3 deep learning | |
| CN101413901B (en) | Surface Fatigue Crack Detection Method Based on CCD Image Features | |
| Rimkus et al. | Processing digital images for crack localization in reinforced concrete members | |
| CN112529884B (en) | Welding spot quality evaluation method based on indentation characteristic image recognition | |
| JPWO2017130550A1 (en) | Defect inspection apparatus, method and program | |
| CN110161035A (en) | Body structure surface crack detection method based on characteristics of image and bayesian data fusion | |
| CN118010847B (en) | Method and system for detecting defects of internal thread pipe blank | |
| CN114049543A (en) | Automatic identification method for scrap steel unloading change area based on deep learning | |
| CN118885941A (en) | A fault prediction method based on 360° dynamic image detection system | |
| CN119559175B (en) | Abnormal defect detection method and system applied to intelligent welding of PCB | |
| CN115035081A (en) | Metal internal defect danger source positioning method and system based on industrial CT | |
| CN117392452A (en) | Wall crack detection system and method based on image analysis | |
| Vijayan et al. | A survey on surface crack detection in concretes using traditional, image processing, machine learning, and deep learning techniques | |
| CN119669930A (en) | A subway tunnel lining disease detection method, system, terminal and medium | |
| CN119444722A (en) | Defect recognition method of pipeline inspection robot based on image processing | |
| CN119246570B (en) | Titanium alloy bar quality detection method and system | |
| CN114663763B (en) | A digital twin-based aircraft skin assembly quality inspection method | |
| CN118940584B (en) | A detection method and system for the inside of a switch cabinet based on defect reconstruction technology | |
| CN118090553A (en) | A hydraulic structure detection method and system | |
| CN118150366A (en) | Reinforced concrete beam shear crack monitoring method and device based on digital image technology | |
| CN119850555B (en) | High-ductility cement-based composite material freeze-thawing damage prediction method and system integrating surface multi-scale structure identification |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |