FPGA-based self-tuning PID controller using RBF neural network and its application in X-Y table

Based on FPGA (Field Programmable Gate Array) technology, the realization of a motion control system using RBF NN (Radial basis function neural network) self-tuning PID controller for X-Y table is proposed in this paper. Firstly, to cope with the system and external load uncertainly, a self-tuning PID controller using RBF NN is adopted and derived for X-Y table. Then, an FPGA-based motion control IC using the aforementioned controller is introduced. The motion controller IC includes two modules. The first module, which performs two PMSM´s position servo controllers for X-Y table, is implemented by hardware in FPGA. The position servo controller adopts self-tuning PID controller. The second module, which performs the motion trajectory planning for X-Y table, is implemented by software in Nios II processor. As the result, the hardware/software co-design technology can make the motion controller of X-Y table more compact, robust, flexible, and less cost.