A novel artificial neural networks force model for end milling

The physical process of multipoint metal cutting depends on a large number of parameters that are strongly interlinked. A number of empirical and semimechanistic models are described in the literature. This paper uses the artificial neural networks (ANNs) approach to evolve a comprehensive model for critical process parameters, such as cutting force, based on a set of input machining conditions. A set of eight input variables is chosen to represent the machining conditions, and process parameters (such as maximum force and mean force) are predicted. Exhaustive experimentation is conducted to develop the model and to validate it. The model is tested for a typical machining scenario found in industry, namely pocket-milling. Excellent agreement between the simulated and experimental forces is found.