HYDROXYLATION OF PHENOL TO DIHYDROXYBENZENES - DEVELOPMENT OF ARTIFICIAL NEURAL-NETWORK-BASED PROCESS IDENTIFICATION AND MODEL-PREDICTIVE CONTROL STRATEGIES FOR A PILOT-PLANT SCALE REACTOR

Experiments in a pilot-scale fixed-bed reactor system have been conduc ted to obtain the process input-output data for the titanium-based zeo lite-catalyzed hydroxylation of phenol to dihydroxybenzenes. An artifi cial neural-network-based strategy has been used for identifying the p rocess model covering the range of experimental conditions. The identi fied neural network model has been used to design a model predictive c ontroller that has been tested on the experimental rig.