Automatica, February 2000, Volume 36, No. 2
The past decade has witnessed a growing body of experimental work suggesting that artificial neural networks can result in improved performance in complex feedback control problems. This is borne out both in simulation studies, as well as actual implementations of neural controllers in industrial systems. More recently, theoretical studies of neural network based control have begun to appear in the literature, and proofs of stability and convergence of algorithms have also been reported. Since it is already well established that neural networks are very adept at solving pattern recognition problems, as well as at providing approximate solutions to complex optimization problems, they appear to be particularly suited for improving performance in complex nonlinear systems in the presence of large uncertainties. Since neural networks are merely conveniently parametrized and easily implementable families of nonlinear maps, neural network based control is a natural extension of adaptive control theory to the nonlinear domain.
In spite of notable advances in the field, the results on neural network feedback control are not generally known widely. In view of this the time is appropriate to bring together the works of researchers doing analytic work in the field, and to expose not only those working in neural networks but also the wider Systems and Control Community to these developments.
Therefore, Automatica is soliciting papers for a Special Issue on "Neural Networks for Feedback Control" to be published in July 2001. Accepted papers will present approaches to the design of neurocontrollers that are mathematically precisely formulated with repeatable design algorithms. The editors will be:
Prof. K. S. Narendra (Invited Editor)
Prof. F. L. Lewis (Corresponding Editor)
Manuscripts should be submitted for review to Professor F.L. Lewis, either by postal mail or electronically, by the
Manuscript Due Date: 1 July 2000For instructions on submissions by post or electronic mail see the Information for Contributors in each Automatica issue or at http://www.math.utwente.nl/eic.