Intelligent control of a boiler-turbine plant based on switching control scheme

Abstract

This paper reports on our present achievement toward the intelligent control of a boiler-turbine power-plant based on switching control scheme, recently revived by some active reports. To overcome strong nonlinearity emerging in load following operations of boiler-turbine power plants, which is not efficiently compensated by the conventional PI-based gain scheduling control, a neural-based nonlinear feed-forward switching control scheme is employed. Owing to its 2-degree freedom type installment in the control system and proper switching of nonlinear feed-forward control by monitoring contribution of inverse dynamics error to control error, effective suppression of nonlinearity is achieved. Decision and Control, 1995., Volume 2, pages 1762-1763 This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. NOTE: At the time of publication, author Daniel Koditschek was affiliated with the University of Michigan. Currently, he is a faculty member in the Department of Electrical and Systems Engineering at the University of Pennsylvania. Comments Copyright 1995 IEEE. Reprinted from Proceedings of the IEEE Conference on AbstractThis paper reports on our present achievement toward the intelligent control of a boiler-turbine power-plant based on switching control scheme, recently revived by some active reports. To overcome strong nonlinearity emerging in load following operations of boiler-turbine power plants, which is not efficiently compensated by the conventional PI-based gain scheduling control, neural-based nonlinear feedforward Switching control scheme is employed. Owing to its 2-degree freedom type installment in the control system and proper switching of nonlinear feedforward control by monitoring contribution of inverse dynamics error to control error, effective suppression of nonlinearity is achieved.

Neural Network‐based Optimal Adaptive Tracking Using Genetic Algorithms

“…This method requires fairly accurate plant models to start with. In [14], some pre-learned fixed neuro-controllers and an adaptive neuro-controller are switched with each other to overcome the nonlinearity in boiler-turbine plants. In [15], a GA based off-line training method was used to best combine two partly-stable, fixed controllers for control of underactuated robots.…”