Grant: Discovery Grants Program - Individual

The main criteria of high performance industrial drives (HPIDs) utilized for robotics, rolling mills, electric vehicles, spindle drives, traction drives, high precision machine tools, etc. are: fast and accurate speed response, smooth and quick recovery of speed from any disturbance. Over the years, fixed gain proportional-integral and proportional-integral-derivative controllers and their adaptive versions have been widely utilized for variable speed drives. These schemes have inherent disadvantages as the designs of these controllers depend on exact mathematical model of the system. Furthermore, the fixed gain controllers are sensitive to system uncertainties. The ac motor model is often complex and nonlinear as the parameter varies widely with operating conditions. In order to deal with the nonlinearities and uncertainties of electric motors and overcome the limitations of the existing controllers in recent years, artificial intelligent algorithms (AIA) such as fuzzy logic (FL), artificial neural network (ANN), neuro-fuzzy and genetic algorithm (GA) have emerged as one of the most active and fruitful research areas in HPID systems. Simplicity and less intensive mathematical design requirements are the main features of AIA. Despite tremendous research in this area, industries are still reluctant to apply AIA for real-time industrial drives due to the lack of their systematic development and the high computational burden. Due to growing global concern over energy consumption and the environment, high energy efficiency has become another important factor for HPIDs. The existing loss minimization scheme for motor drive is developed based on motor model which is not capable of handling system uncertainties. The objectives of the proposed project are to develop and implement hybrid intelligent controllers utilizing the merits of FL, ANN and GA in order to achieve high performance and high efficiency of interior permanent magnet synchronous motor and induction motor drives.