Amalgamation of adaptive control and AI techniques: applications to generator excitation control

Abstract

Adaptive control can be described as the changing of controller parameters on-line based on the changes in system operating conditions. Whenever an adaptive controller detects changes in system operating conditions, it responds by determining a new set of control parameters. An adaptive controller based on analytical techniques can provide excellent performance and improve the dynamic performance of the plant by allowing the parameters of the controller to adjust as the operating conditions change. However, proper care needs to be taken in the design of the analytical algorithms to make them robust, especially under large disturbances. The controller robustness can be improved by employing artificial intelligence (AI) techniques, such as fuzzy logic and neural networks. It is possible that either the entire algorithm may be implemented using AI techniques or the analytical and AI techniques be integrated such that some functions are performed using analytical approach while the rest are performed using AI techniques. Successful implementation of all three approaches, i.e. purely analytical, purely AI and integrated, is illustrated by application to an adaptive power system stabilizer (PSS) to improve damping and stability of an electric generating unit.