Adaptive Force Control in High-Speed Machining by Using a System of Neural Networks

The contribution discusses the use of combining the methods of neural networks, fuzzy logic and PSO evolutionary strategy in modeling and adaptively controlling the process of ball-end milling. A combination of off-line feedrate optimization and on-line adaptive force control is used to maintain a reference peak cutting force during end milling for safe, accurate, and efficient machining. The basic control principle is based on the neural control scheme (UNKS) consisting of two neural identificators of the process dynamics and primary artificial controller. Design parameters for the adaptive controller are selected using an experimentally validated machining process model. The controller was successfully applied to computer numerical control (CNC) milling machine Heller. Experiments have confirmed efficiency of the adaptive control system, which reflected in improved surface quality and decreased tool wear