Neural modeling and control of a heat exchanger based on SPSA techniques

Author

Renotte, C. ; Vande Wouwer, A. ; Remy, M.

Author_Institution

Lab. d´´Autom., Faculte Polytech. de Mons, Belgium

Volume

5

fYear

2000

fDate

2000

Firstpage

3299

Abstract

The aim of the paper is twofold: first, we consider a variation of the first-order simultaneous perturbation stochastic approximation (SPSA) algorithm developed by Spall (1992, 1998) which makes use of several numerical artifices, including adaptive gain sequences, gradient smoothing and a step rejection procedure, to enhance convergence and stability. Second, we present numerical studies on a non-trivial test-example, i.e., the water cooling of sulfuric acid in a two-tank system. This numerical evaluation includes the development of a neural model as well as the design of a model-based predictive neural PID controller

Keywords

approximation theory; control system synthesis; convergence; gradient methods; heat exchangers; identification; neurocontrollers; predictive control; sequences; three-term control; SPSA techniques; adaptive gain sequences; first-order simultaneous perturbation stochastic approximation; gradient smoothing; model-based predictive neural PID controller; neural modeling; step rejection procedure; sulfuric acid; two-tank system; water cooling; Approximation algorithms; Convergence of numerical methods; Cooling; Predictive models; Smoothing methods; Stability; Stochastic processes; System testing; Temperature control; Three-term control;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 2000. Proceedings of the 2000

Conference_Location

Chicago, IL

ISSN

0743-1619

Print_ISBN

0-7803-5519-9

Type

conf

DOI

10.1109/ACC.2000.879175

Filename

879175