浏览全部资源
扫码关注微信
纸质出版日期： 2024-07-25 ，
扫 描 看 全 文
刘石桥.基于形态学特征的机械零件焊接裂纹无损图像检测方法［J］.电焊机，2024，54（7）：31-37.
LIU Shiqiao.Nondestructive Image Detection Method for Welding Cracks of Mechanical Parts Considering Morphological Characteristics[J].Electric Welding Machine, 2024, 54(7): 31-37.
在机械零件焊接裂纹检测中，由于采集的图像中焊接边界受到反射波干扰，其存在模糊化噪点，导致检测不准确。为解决该问题，基于边界形态中形状基不变原理，提出考虑形态学特征的机械零件焊接裂纹无损图像检测方法。该方法采用机器视觉技术采集机械零件焊接的视觉图像，通过照明反射模型和傅里叶变换，滤除图像受到光学干扰产生的模糊化噪点。通过二层小波分解图像，构建低频近似分量和高频细节分量。引入形态学算法，以结构元素为核心，通过腐蚀和膨胀处理，并且通过优化腐蚀次数和同态滤波进行优化，提取机械零件焊接裂纹的形态学特征，实现机械零件焊接裂纹无损检测。经过试验证明，所提方法采集的视觉图像更加清晰，可以有效提取裂纹形态学特征和裂纹，其机械零件焊接裂纹检测位置与实际位置基本一致，误差仅为0.01，说明该方法检测精度较高。
In the welding crack detection of mechanical parts
because the welding boundary is interfered by reflection wave in the acquired image
there is fuzzy noise
which leads to inaccurate detection. In order to solve this problem
based on the principle of shape basis invariance in boundary morphology
a non-destructive image detection method for welding cracks of mechanical parts considering morphological characteristics was proposed. In this method
machine vision technology is used to collect the visual image of mechanical parts welding
and the fuzzy noise caused by optical interference is filtered by illumination reflection model and Fourier transform. The low frequency approximate component and high frequency detail component are constructed by the two-layer wavelet decomposition. By introducing morphological algorithm
taking structural elements as the core
through corrosion and expansion treatment
and optimization by optimizing corrosion frequency and homomorphic filtering
the morphological characteristics of welding cracks of mechanical parts are extracted
and the non-destructive detection of welding cracks of mechanical parts is realized. The experimental results show that the visual image collected by the proposed method is clearer
and the crack morphological characteristics and cracks can be effectively extracted. The detection location of welding cracks in mechanical parts is basically consistent with the actual location
and the error is only 0.01
indicating that the detection accuracy of the proposed method is high.
机械零件焊接机器视觉同态滤波图像校正小波变换形态学特征
welding of machine partsmachine visionhomomorphic filteringimage correctionwaveletmorphological characteristics
李卓然，迟宏伟. 计算机图像识别技术在农机零件无损检测中的应用［J］. 农机化研究，2023，45（07）：219-223.
LI Z R，CHI H W. Application of Computer Image Recognition Technology in Nondestructive Testing of Agricultural Machinery Parts［J］.Journal of Agricultural Mechanization Research，2023，45（07）：219-223.
张瀚丹，吴一全. 基于视觉的汽车装配件缺陷检测研究进展［J］. 仪器仪表学报，2023，44（08）：1-20.
ZHANG H D，WU Y Q. Research progress of vehicle assembly defect detection methods based on vision［J］.Chinese Journal of Scientific Instrument，2023，44（08）：1-20.
丁伟利，任天赐，谭伟敏，等. 基于视觉的零部件振动裂纹在线监测系统研究［J］.电子测量与仪器学报，2022，36（02）：78-88.
DING W L，REN T C，TAN WM，et al. Online vibration crack detection algorithm based on computer vision［J］.Journal of Electronic Measurement and Instrumentation，2022，36（02）：78-88.
郝博，闫俊伟，尹兴超，等. 多特征联合的薄壁零件表面缺陷检测方法［J］.工具技术，2023，57（08）：147-152.
HAO B，YAN J W，YIN XC，et al. Surface Defect Detection Method for Thin-wall Parts Based on Multi-feature Joint［J］. Tool Engineering，2023，57（08）：147- 152.
Abraham S T，Babu M N，Venkatraman B.A novel ultrasonic non-destructive testing methodology to monitor fatigue crack growth in compact tension specimens［J］.Review of Scientific Instruments，2023，94（3）：035108.
Silva M I，Malitckii E，Santos T G，et al. Review of conventional and advanced non-destructive testing techniques for detection and characterization of small-scale defects［J］.Progress in materials science，2023，138：101155.
程莹，许亚男，侯浩楠，等. 基于机器视觉技术的小粒中药材种子净度快速检测［J］. 中国农业大学学报，2022，27（05）：114-122.
CHENG Y，XU Y N，HOU H N，et al. Rapid small seed clarity detection method of Chinese medicinal plants based on machine vision technology［J］.Journal of China Agricultural University，2022，27（05）：114-122.
林宁. 基于机器视觉技术的电梯曳引轮磨损检测研究［J］. 微特电机，2022，50（03）：26-30.
LIN N. Research on Elevator Traction Wheel Wear Detection Based on Machine Vision Technology［J］. Small & Special Electrical Machines，2022，50（03）：26-30.
刘高平，曲超，张思琪. 傅里叶变换光谱仪非线性光程差分析与校正［J］. 光学学报，2022，42（08）：255-262.
LIU G P，QU C，ZHANG S Q. Analysis and Correction of Nonlinear Optical Path Difference of Fourier Transform Spectrometer［J］. Acta Optica Sinica，2022，42（08）：255-262.
李超，李孟芝，李丹霞，等. 基于傅里叶变换红外光谱指纹技术的艾叶产地溯源研究［J］. 光谱学与光谱分析，2022，42（08）：2532-2537.
LI C，LI M Z，LI D X，et al. Study on Geographical Traceability of Artemisia argyi by Employing the Fourier Transform Infrared Spectral Fingerprinting［J］.Spectroscopy and Spectral Analysis，2022，42（08）：2532-2537.
张淼，吴事煜，冯春寿，等. 一种新型谐振混合型有源电力滤波器［J］. 电力电子技术，2023，57（04）：41-45.
ZHANG M，WU S Y，FENG C S，et al. A New Resonantt Hybrid Active Power Filter［J］. Power Electronics，2023，57（04）：41-45.
王梓璇，王圃，王颖，等. 基于小波分解及遗传BPNN耦合模型的地表水As浓度预测研究［J］. 环境科学学报，2021，41（07）：2942-2950.
WANG Z X，WANG P，WANG Y，et al. Wavelet decomposition and genetic BPNN hybrid model based modelling approach for As concentration prediction in surface water［J］. Acta Scientiae Circumstantiae，2021，41（07）：2942-2950.
徐志祥，杨帆，关守岩，等. 基于小波分解表面波的涂层平板表面缺陷检测方法研究［J］. 激光与红外，2021，51（05）：592-599.
XU Z X，YANG F，GUAN S Y，et al. Research on surface defect detection method of coating plate based on wavelet decomposition surface wave［J］. Laser & Infrared，2021，51（05）：592-599.
杨翠茹，彭向阳，余欣. 结合小波变换与数学形态学的电缆局放信号识别与降噪方法［J］. 沈阳工业大学学报，2023，45（06）：619-624.
YANG C R，PENG X Y，YU X. Recognition and denoising method of cable partial discharge signal based on wavelet transform and mathematical morphology［J］.Journal of Shenyang University of Technology，2023，45（06）：619-624.
康爽，陈长征，刘石，等. 基于最优多尺度集的形态学红外图像缺陷检测研究［J］. 太阳能学报，2022，43（06）：145-152.
KANG S，CHEN C Z，LIU S，et al. Study on Defect Detection of Morphological Infrared Images Based on Optimal Multi-scale Set［J］. ActaEnergiae Solaris Sinica，2022，43（06）：145-152.
相关作者
相关机构
公网安备11010802024621