ELABORATION OF A NEURAL-NETWORK SYSTEM FOR SEMIBATCH REACTOR TEMPERATURE CONTROL - AN EXPERIMENTAL-STUDY

A neural controller is developed and used to regulate the temperature in a semi-batch pilot-plant reactor. The experimental unit employs a m onofluid heating-cooling system to raise the reactor to the operating temperature, and then remove the heat generated by an exothermic react ion. A methodology for installation of the neural controller is presen ted. Preliminary experiments form the neural-network learning database . These involve regulation of the reactor by either an advanced contro l algorithm or by operator (manual control). The results suggest that such neural controllers can provide excellent setpoint-tracking and di sturbance rejection.