EXPERIENCE OF USING THE NEURAL-NETWORK APPROACH FOR IDENTIFICATION OFMSF DESALINATION PLANTS

Mathematical models of physical and engineering systems are frequently of high dimension, possessing interacting dynamic phenomena. Informat ion processing requirements for experimenting with these models for co ntrol purposes are excessive. It is therefore natural to techniques th at reduce the computational effort. In this paper, the neural network approach for nonlinear identification of the multistage flash desalina tion plant (large scale system) is presented through the manipulation of collected input-output data from the plant. Results of utilizing su ch an approach are also discussed.