Controller Parameters Tuning Using Genetic Algorithm and Neural Model

The paper deals with a controller design for the nonlinear processes using genetic algorithm and neural model. The aim was to improve the control performance using genetic algorithm for optimal PID controller tuning. The plant model has been identified via an artificial neural network from measured data. The genetic algorithm represents an optimisation procedure, where the cost function to be minimized comprises the closed-loop simulation of the control process and a selected performance index evaluation. Using this approach the parameters of the PID controller were optimised in order to become the required behaviour of the control process. Testing of quality control process was realized in simulation environment of Matlab Simulink on selected types of nonlinear dynamic processes.