Intelligent position control of permanent magnet synchronous motor using recurrent fuzzy neural cerebellar model articulation network

Abstract

A recurrent fuzzy neural cerebellar model articulation network (RFNCMAN) control is proposed in this paper for position servo drive systems to track various periodical position references with robustness. The adopted position servo drive system is designed using a six-phase PMSM and equipped with a fault-tolerant control scheme. First, an ideal computed torque controller is designed for the tracking of the rotor position reference command. Since the uncertainties of the PMSM position servo drive system are difficult to know in advance, it is impossible to design an ideal computed control law for practical applications. Therefore, the RFNCMAN is proposed to mimic the ideal computed torque controller with a compensated controller to compensate the approximation error. In the RFNCMAN, a recurrent fuzzy cerebellar model articulation network (RFCMAN) is adopted in the first dimension to enhance the online learning rate and localisation learning capability. Moreover, a general recurrent fuzzy neural network (RFNN) is adopted in the second dimension to enhance the generalisation performance and to reduce the required memory and rule numbers. Finally, the proposed position control system is implemented in a 32-bit floating-point DSP. The effectiveness of the proposed RFNCMAN control system is verified by some experimental results.