Neuro-approach for intelligent systems development

We propose a method to use neural networks to tune the PID (proportional plus integral plus derivative) gains according to the environmental condition and systems specification. The tuning method is based on the error backpropagation method and it may be trapped in a local minimum. In order to avoid the local minimum problem, we use a genetic algorithm to find the initial values of the connection weights of the neural network and initial values of PID gains. The experimental results show the effectiveness of the present approach.