摘要
铝合金薄板激光焊接经常会出现咬边、凹陷等表面缺陷。这两种缺陷由于尺寸小、特征相似,难以通过传统视觉在线检测手段对其进行精确分类和测量。开发了一种基于深度学习缺陷分类-点云测量的在线监测系统,利用高密度的点云数据对缺陷进行识别、分类与测量,解决了上述检测难题。通过双目结构光传感器采集点云数据;利用基于区域推荐网络的卷积神经网络模型识别和定位缺陷;在识别和定位缺陷后,通过对局部缺陷区域的点云进行操作,快速测量缺陷尺寸。高密度点云数据训练的模型的识别准确率达到93%,高于传统二维视觉传感器图像训练的模型。该检测系统在线检测允许的最大焊接速度为316.87 mm/s,适用于大多数激光焊接。
Objective The primary objective of this study is to transform the status quo of laser-welding defect detection.By developing an online deep learning system,this study aims to enable the identification and measurement of surface defects in laser-welded aluminumalloy sheets with high precision and efficiency.The specific focus is on two prevalent defects:undercuts,characterized by the insufficient melting of the base material at the weld toe,and sagging,which is the undesirable downward displacement of the material along the weld seam.The use of high-density point cloud data is key to overcoming the limitations of traditional defect detection methods and enhancing the adaptability of the system to diverse welding conditions.Methods A binocular-structured light sensor capable of capturing detailed point cloud data of defects in laser-welded samples is used.This sensor is strategically positioned to cover the entire welding area,which ensures the collection of comprehensive defect data.The acquired point cloud data undergo meticulous preprocessing to eliminate noise and artifacts,resulting in a clean and informative dataset.The dataset serves as the foundation for training the faster region-based convolutional neural network(Faster RCNN)model,a deep learning architecture renowned for its object detection capabilities.The Faster R-CNN model is augmented with an area recommendation network,a critical addition to improve defect localization precision.The training process involves subjecting the model to various defect scenarios to ensure its adaptability to various welding conditions and defect types.Results and Discussions The trained Faster R-CNN model exhibits an outstanding recognition precision rate of 93%when is tested on high-density point cloud data.This significant improvement compared to that of the model trained on images from a traditional two-dimensional vision sensor demonstrates the efficiency of leveraging point cloud data in defect detection.The ability of the Faster R-CNN model to recognize and locate
作者
张臣
胡佩佩
朱新旺
杨长祺
Zhang Chen;Hu Peipei;Zhu Xinwang;Yang Changqi(The Institute of Technological Sciences,Wuhan University,Wuhan 430072,Hubei,China;Shanghai Spaceflight Precision Machinery Institute,Shanghai 201600,China;Hubei Institute of Measurement and Testing Technology,Wuhan 430223,Hubei,China)
出处
《中国激光》
EI
CAS
CSCD
北大核心
2024年第4期77-88,共12页
Chinese Journal of Lasers
基金
国家自然科学基金(52075393)
装备预研航天科技应用创新项目
湖北省青年拔尖人才项目。
关键词
激光技术
激光焊接
焊接缺陷
实时检测
高密度点云数据
深度学习
laser technique
laser welding
welding defect
real-time detection
high density point cloud data
deep learning
