Explainable Models for Multivariate Time-series Defect Classification of Arc Stud Welding

Abstract

Arc Stud Welding (ASW) is widely used in many industries such as automotive and shipbuilding and is employed in building and jointing large-scale structures. While defective or imperfect welds rarely occur in production, even a single low-quality stud weld is the reason for scrapping the entire structure, financial loss and wasting time. Preventive machine learning-based solutions can be leveraged to minimize the loss. However, these approaches only provide predictions rather than demonstrating insights for characterizing defects and root cause analysis. In this work, an investigation on defect detection and classification to diagnose the possible leading causes of low-quality defects is proposed. Moreover, an explainable model to describe network predictions is explored. Initially, a dataset of multi-variate time-series of ASW utilizing measurement sensors in an experimental environment is generated. Next, a set of pre-possessing techniques are assessed. Finally, classification models are optimized by Bayesian black-box optimization methods to maximize their performance. Our best approach reaches an F1-score of 0.84 on the test set. Furthermore, an explainable model is employed to provide interpretations on per class feature attention of the model to extract sensor measurement contribution in detecting defects as well as its time attention.