Performance Improvement of Direct Torque Controlled Interior Permanent Magnet Synchronous Motor Drives Using Artificial Intelligence

The main theme of this paper is to present novel controller, which is a genetic based fuzzy Logic controller, for interior permanent magnet synchronous motor drives with direct torque control. A radial basis function network has been used for online tuning of the genetic based fuzzy logic controller. Initially different operating conditions are obtained based on motor dynamics incorporating uncertainties. At each operating condition, a genetic algorithm is used to optimize fuzzy logic parameters in closed-loop direct torque control scheme. In other words, the genetic algorithm finds optimum input and output scaling factors and optimum number of membership functions. This optimization procedure is utilized to obtain the minimum speed deviation, minimum settling time, zero steady-state error. The control scheme has been verified by simulation tests with a prototype interior permanent magnet synchronous motor.