Multivariable adaptive control using an observer based on a recurrent neural network

Abstract

A real-time learning control technique for a general non-linear multivariable process is presented and applied to a laboratory plant. The proposed technique is a hybrid approach, which combines the ability of a recurrent neural network for modelling purposes and a linear pole placement control law to design the controller, providing a bridge between the field of neural networks and the well-known linear adaptive control methods. An Elman-type recurrent neural network strategy is introduced to model the behaviour of the non-linear plant, using available input–output data (an unmeasurable state problem is assumed). Following a linearization technique a linear time-varying state-space model is obtained, which allows simultaneous estimation of parameters and states. Once the neural model is linearized, some well-established standard linear control strategies can be applied. With simultaneous online training of the neural network and controller synthesis, the resulting structure is an indirect adaptive self-tuning strategy. The identification and control performances of the proposed approach are investigated on a non-linear multivariable three-tank laboratory system. Experimental results show the effectiveness of the proposed hybrid structure. Copyright © 1999 John Wiley & Sons, Ltd.