铆接铝合金板铆钉失效缺陷检测方法研究  

Research on Detection Method of Failure Defects of Rivet on Riveted Aluminum Alloy Plates

作　　者：刘凉[1] 张滢 史晨阳 赵新华[1] 孟宪明[2] 刘增昌 Liu Liang;Zhang Ying;Shi Chenyang;Zhao Xinhua;Meng Xianming;Liu Zengchang(Tianjin University of Technology,Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control,Tianjin 300384;China Automotive Technology&Research Center Co.,Ltd.,Tianjin 300300;Automotive Engineering Corporation,Tianjin 300113)

机构地区：[1]天津理工大学,天津市先进机电系统设计与智能控制重点实验室,天津300384 [2]中国汽车技术研究中心有限公司,天津300300 [3]中国汽车工业工程有限公司,天津300113

出　　处：《汽车工程》2024年第2期366-374,共9页Automotive Engineering

基　　金：国家重点研发计划项目(2017YFB1303502,2017YFB1303501)资助。

摘　　要：针对车身用铝合金板内部铆钉缺陷特征提取难度大、缺陷类型与程度识别准确率低的问题,提出一种基于高斯卷积深度信念网络与双向长短期记忆网络相结合的铆钉失效缺陷诊断模型与检测方法。首先,面向5种铆钉断裂缺陷设计试件并搭建自动检测系统,通过规划和调整探头姿态有效地降低提离效应对检测信号的影响。其次,设计双网络融合诊断模型提取和学习多维度缺陷特征信息,解决检测曲线中由时序变化特性和空间分布状态表征的缺陷信息提取难题。实验结果表明,与传统卷积网络及单一深度信念网络相比,优化后算法诊断模型的平均准确率为99.85%,相比提升了14.54%,且具有良好的通用性和鲁棒性,可实现铆钉内部缺陷的在线诊断。For the difficulties in feature extraction and low recognition rate in defect types and grades of riv⁃et on aluminum alloy plates for car body,the diagnosis model and detection method for rivet failure defects are pro⁃posed based on the Gaussian convolutional deep belief network and long short-term memory network.Firstly,the specimens are designed for five types of fracture defects and an automatic detection system is constructed.The planned path and pose of the probe are set to lower lift-off effect on signals.Secondly,the dual network fusion diag⁃nostic model is designed to extract and learn the multi-dimensional defect feature information,solving the problem of extracting defect information represented by temporal variation characteristics and spatial distribution state in de⁃tection curves.The experiments results show that the optimized model has an average recognition rate of 99.85%,with an increase of 14.54%compared with that of the traditional convolutional network and single deep belief net⁃work.The model has better compatibility and robustness,which can realize online diagnosis of internal defects of rivets.

关 键 词：铆钉内部缺陷 检测系统 模式识别 特征融合 

分 类 号：TG938[金属学及工艺—钳工工艺]