On-line genetic optimization of unstructured controllers for electric drives

In this paper, the authors describe a design procedure for cascaded controller for electrical drives based on genetic algorithms (GAs). Most electric drives have two separate controllers for current and speed control, which are in general designed in two consecutive steps (firstly the current controller and then the speed controller). Using a GA devised to test and compare controllers of different orders, the authors search simultaneously for the couple of discrete anti-windup controllers achieving the optimal compromise of weighted cost and performance indices related to both current and speed responses. The search is performed online, on the physical hardware, by continuously downloading and testing new solutions on a micro-processor running the control algorithms in real time. The paper also describes some heuristic mechanisms to avoid the experimentation of unstable controllers. The cascaded control system obtained through genetic search significantly outperforms alternative schemes obtained with linear design techniques.