Stability prediction in milling processes using a simulation-based Machine Learning approach

Abstract

Process simulations are increasingly applied to analyze machining processes regarding process stability and the resulting surface quality of the workpiece. Due to their computational time, these simulations are inappropriate for real-time applications. Using Machine Learning approaches, monitoring systems for milling processes can be realized. Unfortunately, a huge amount of experimental data is necessary to train such models. A novel Machine Learning framework, which generates reliable predictions of the process stability, is presented in this paper. The model is designed based on results of a geometric physically-based simulation with varied process parameter values and refined using an active learning approach.