Automatic quality control of aluminium parts welds based on 3D data and artificial intelligence

作     者：Cardellicchio, Angelo Nitti, Massimiliano Patruno, Cosimo Mosca, Nicola di Summa, Maria Stella, Ettore Reno, Vito 

作者机构：Natl Res Council Italy Inst Intelligent Ind Technol & Syst Adv Mfg CNR STIIMA Via G Amendola 122 D-O I-70126 Bari Italy 

出 版 物：《JOURNAL OF INTELLIGENT MANUFACTURING》 (智能制造业杂志)

年 卷 期：2024年第35卷第4期

页      面：1629-1648页

核心收录：

学科分类：08[工学] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：project "Feasibility study of a system for monitoring the quality of welds on aluminum profiles" 

主　　题：3D laser profilometry Automatic quality control of aluminum weldings Machine learning Deep learning 

摘      要：Detecting defects in welds used in critical or non-critical industrial applications is of intense interest. Several non-destructive inspection methods are available, each allowing the preservation of the integrity of the sample under analysis. However, visual-based inspection methods are the most well-assessed, which usually require human experts to inspect each sample, looking for shallow defects. This process often requires time and effort by the human operator, therefore not allowing to perform real-time defect identification, which may result in unexpected (and undesired) production costs. In recent years, several methods have been proposed to automatically deal with visual-based inspection, mainly through convolutional neural networks. However, while effective, these models require a lot of data and computational power to be trained, which is also time-consuming. This paper proposes a high-throughput data gathering and processing method using laser profilometry, along with an automatic defect detection method based on lightweight machine learning algorithms. Six different machine and deep learning approaches are compared, including SVMs, decision forests, and neural networks, achieving a top-1 accuracy of 99.79% for defect identification and 99.71% for defect categorization. Thanks to its effectiveness and the high data throughput achievable by data gathering, the whole method can be implemented in real production lines to minimize costs and perform real-time monitoring and defects assessment.