Quality monitoring of projection welding using machine learning with small data sets

Abstract

Capacitor discharge welding is an efficient, cost-effective and stable process. It is mostly used for projection welding. Real-time monitoring is desired to ensure quality. Until this point, measured process quantities were evaluated through expert systems. This method is strongly restricted to specific welding tasks and needs deep understanding of the process. Another possibility is quality prediction based on process data with machine learning. This requires classified welding experiments to achieve a high prediction probability. In industrial manufacturing, it is rarely possible to generate big sets classified data. Therefore, semi-supervised learning is investigated to enable model development on small data sets. Supervised learning models on large amounts of data are used as a comparison to the semi-supervised models. A total of 389 classified weld tests were performed. With semi-supervised learning methods, the amount of training data necessary was reduced to 31 classified data sets.

The characteristics of dynamic stability in aluminium alloy keyhole weld pool flow

“…As productivity and production accuracy continue to increase, there is a pressing need for effective process control characteristics in automated welding [8]. These characteristics play a crucial role in accurately assessing the welding state [9]. It is widely recognised that the flow of material during VPPAW determines the weld's condition [10].…”