Indirect neural control for plant-wide systems: Application to the Tennessee Eastman Challenge Process

摘要: Abstract An autonomous indirect scheme is proposed for multivariable process control and extended to unstable open-loop plant-wide processes. Our principal objective in this work prove the feasibility an industrial plant by a small size neural system without any priori training. The made of adaptive instantaneous model, Neural Controller based on fully connected “Real-Time Recurrent Learning” networks on-line parameters updating law. This applied Tennessee Eastman Challenge Process. Performances such as set point stabilisation, mode switching disturbances rejection are pointed out. Results discussed according Down Vogel objectives.