Approximate nonlinear output regulation based on the universal approximation theorem

✍ Scribed by Jin Wang; Jie Huang; Stephen S.T. Yau

• Publisher: John Wiley and Sons
• Year: 2000
• Tongue: English
• Weight: 243 KB
• Volume: 10
• Category: Article
• ISSN: 1049-8923
• DOI: 10.1002/(sici)1099-1239(20000430)10:5<439::aid-rnc480>3.0.co;2-3

✦ Synopsis

The regulator equations arising from the nonlinear output regulation problem are a set of mixed partial and algebraic equations. Due to the nonlinear nature, it is di$cult to obtain the exact solution of the regulator equations. This paper presents an approximation method for solving the regulator equations based on a class of feedforward neural networks. It is shown that a three-layer neural network can solve the regulator equations up to a prescribed arbitrarily small error, and this small error can be translated into a guaranteed steady-state tracking error for the closed-loop system. The method has led to an e!ective approach to approximately solving the nonlinear output regulation problem.