Intelligent adaptive control in milling processes

In this paper, two intelligent adaptive controllers for milling processes a re proposed. One is an intelligent adaptive controller with optimization (I ACO) developed based on a neural network and genetic algorithm. The other i s an intelligent adaptive controller with constraints (IACC) developed base d an a neural network and expert rules. In the IACO, a modified back-propag ation neural network (MBPNN), in which a dynamic factor is attached and the learning rate can be adjusted in the learning process is used for the onli ne modelling of the milling system. In addition, a modified genetic algorit hm (MAG), in which the search domain call be adjusted in every generation i s used for the real-time optimal control of the milling process. In IACC, a simplified BP algorithm is used to learn online, the reverse function of t he milling system and realize the real-time adaptive control in the milling process; some expert rules are combined in the BP neural network controlle r so as to ensure the reliability and stability of the adaptive milling sys tem. The experimental results show that not only does the milling system wi th the intelligent adaptive controllers have high robustness and global sta bility, but also the machining efficiency of the milling system with the in telligent adaptive controllers is much higher than the traditional CNC mill ing system.