CONTROL-AFFINE FUZZY NEURAL-NETWORK APPROACH FOR NONLINEAR PROCESS-CONTROL

An internal model control strategy employing a fuzzy neural network is proposed for SISO nonlinear process. The control-affine model is iden tified from both steady state and transient data using back-propagatio n. The inverse of the process is obtained through algebraic inversion of the process model. The resulting model is easier to interpret than models obtained from the standard neural network approaches. The propo sed approach is applied to the tasks of modelling and control of a con tinuous stirred tank reactor and a pH neutralization process which are not inherently control-affine. The results show a significant perform ance improvement over a conventional PID controller. In addition, an a dditional neural network which models the discrepancy between a contro l-affine model and real process dynamics is added, and is shown to lea d to further improvement in the closed-loop performance.