GP and GA in the design of a constrained control system with disturbance rejection

The design of a robust controller for a constrained SISO linear system is considered. Initially, the study of a solution provided by genetic programming (GP) outlined that the GP search process does not achieve time-optimality. A genetic algorithm (GA) was chosen and implemented to confront the performance of the GP solution. The system presented In this work tuned a set of elements that form the controller structure, namely, a PID core, a feed-forward block, a filter on the derivative and a Butterworth Alter on the feedback. The proposed approach proved to reach time optimality thanks to the achievement of bang-bang control. The control synthesis method also showed versatility when considering load and feedback disturbances on the system. GA appears to be preferable for the computational cost and the quality of the solution obtained.