Generating Synthetic Data from Real-Time Simulators for Deep Learning Modeling of Machining

Manufacturers of cutting and machining machines face increasing pressure to optimize performance and sustainability while complying with evolving regulations. Traditional machine learning approaches are often limited by biased and repetitive datasets collected during real operations. This article presents a real-time simulation framework for generating large synthetic datasets to train predictive machining models. A mechanistic model with probabilistic parameters is validated on experimental data and integrated into the simulator, enabling neural networks to predict process metrics such as vibrations, cutting forces, and product quality prior to machining. The framework further supports large-scale optimal control by testing setpoint control strategies for virtual prototyping. This approach allows manufacturers to enhance efficiency, reduce waste, and improve product quality while minimizing operational risks.