On Micro-CT inspection of SPR joints in lightweight structures using vision-based machine learning approach

Abstract

Abstract

The paper presents an innovative non-destructive inspection (NDI) method, via employing a custom vision-based machine learning model, for evaluating the quality of Self-Piercing Rivet (SPR) joints, a commonly used joining technique in light vehicle production. Non-destructive inspection (NDI) is crucial for structural integrity analyses, including fracture and fatigue assessment. Utilizing μ-CT (Micro-Computed Tomography) scans of SPR joints and the Machine Vision AI (artificial intelligence) model, the present approach enables the detection and quantification of key quality parameters. The AI model is trained on images extracted from a comprehensive dataset of μ-CT scans of modified SPR joints. Samples used for training are modified carefully to represent the combined defects commonly found in SPR joints. The trained vision-based AI model is deployed to identify and quantify defects, accounting for cumulative errors from material inconsistencies, manufacturing imperfections, and dimensional tolerances. These parameters comprise cumulative defects that may affect joint integrity.The proposed method provides valuable cumulative measured inputs to numerical models of whole riveted structure, non-destructively, which are essential for evaluating the performance of complex structures incorporating SPRs. By significantly enhancing the prediction of the effects of manufacturing defects on lightweight structures, including fatigue life and joint durability, this approach enables more accurate and reliable assessments of individual joints; unlike current techniques, which depend on assumed, averaged, or estimated defect parameters without direct inspection. Ultimately, the AI-based NDI tool enables the enhancement of error detection precision, contributing to safer and more reliable structural integrity evaluations for a variety of manufacturing applications.