M. Nikravesh et al., DYNAMIC NEURAL-NETWORK CONTROL FOR NONLINEAR-SYSTEMS - OPTIMAL NEURAL-NETWORK STRUCTURE AND STABILITY ANALYSIS, Chemical engineering journal, 68(1), 1997, pp. 41-50
Design techniques for non-linear dynamic systems are closely related t
o their stability properties. Stability results can be used to design
a reliable controller. This paper discusses the stability analysis of
the dynamic neural network control (DNNC). The results from DNNC stabi
lity analysis will be used to define the neural network stability inde
x (NNSI). The NNSI is a practical index which in current form can only
be used with DNNC structures. The NNSI can be used to determine the o
ptimal DNNC network structure. In addition, we will provide guidelines
for the design of an optimal DNNC network structure for the conventio
nal neural network structure for model-based control strategies. In th
is study, DNNC will be designed for a non-isothermal CSTR as an exampl
e of a wide class of non-linear processes. (C) 1997 Elsevier Science S
.A.