NONLINEAR CONTROL-STRUCTURES BASED ON EMBEDDED NEURAL SYSTEM MODELS

This paper investigates in detail the possible application of neural n etworks to the modeling and adaptive control of nonlinear systems, Non linear neural-network-based plant modeling is first discussed, based o n the approximation capabilities of the multilayer perceptron. A struc ture is then proposed to utilize feedforward networks within a direct model reference adaptive control strategy, The difficulties involved i n training this network, embedded within the closed-loop are discussed and a novel neural-network-based sensitivity modeling approach propos ed to allow for the backpropagation of errors through the plant to the neural controller, Finally, a novel nonlinear internal model control (LMC) strategy is suggested, that utilizes a nonlinear neural model of the plant to generate parameter estimates over the nonlinear operatin g region for an adaptive linear internal model, without the problems a ssociated with recursive parameter identification algorithms, Unlike o ther neural WIC approaches the linear control law can then be readily designed, A continuous stirred tank reactor (CSTR) was chosen as a rea listic nonlinear case study for the techniques discussed in the paper.