Neural network based control of PH in a laboratory-scale plant

We analyse the automation of a laboratory-scale pH system. We develop a neural controller based on an internal model control strategy. Feedforward backpropagation neural networks with only one hidden layer and sigmoidal activation functions are used. The training of such networks is based on input-output data of the plant. The results obtained operating the controlled system under different perturbation patterns (changes in set point and in the input water flow rate) show very stable and relatively fast responses within the whole operating range of the system, when compared with classical PID control.