FPGA-realization of a self-tuning PID controller for X–Y table with RBF neural network identification

Based on field programmable gate array (FPGA) technology, a realization of a servo/motion control system with the self-tuning PID controller for X–Y table is presented in this work. Firstly, to cope with the system and external load uncertainly, a Radial Basis Function Neural Network (RBF NN) is applied to identify the dynamic model of the X-axis table and Y-axis table and to provide the information to adjust the PID controller gains. Then, the design of an FPGA-based motion control IC for X–Y table using the aforementioned controller is described. 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 with RBF NN identification. The second module, which runs 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.