Development and Implementation of a New Adaptive Intelligent Speed Controller for IPMSM Drive

For controlling nonlinear, time-varying, or ill-defined systems, artificial intelligent controllers have proven to be superior to conventional controllers in design and performance. This paper presents a novel adaptive-network-based fuzzy inference system (ANFIS) for the speed control of interior permanent-magnet synchronous motor (IPMSM) drives. By utilizing a learning technique, the proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. The backpropagation technique is used for the online tuning of ANFIS parameters in order to optimize the performance of the proposed drive. The proposed control technique also provides flux control to control the motor over a wide speed range. The complete drive has been successfully implemented in real time using digital signal processor board DS1104. The performance of the proposed ANFIS-based IPMSM drive is investigated both in simulation and experiment at different operating conditions.