CONTROL SCHEME OF A BOILER-TURBINE USING ADAPTIVE WAVELET NEURAL NETWORK

Abstract

In power plant control system, the capability to achieve an optimaltracking property of the nonlinear multi-input multi-output (MIMO) unitshas been an important task. This paper proposes a direct adaptive waveletneural network controller of boiler-turbine system for improving theperformance and efficiently achieving the good tracking property to meetthe load demands under load changes, large disturbances and change ofsystem operating points. This paper describes the application of a multiloop direct adaptive wavelet neural network for a drum boiler; threeimportant outputs were controlled using a direct adaptive controller.WNNs are rapidly trained with adaptive learning rates (ALRs) which havebeen derived from the discrete Lyapunov stability theorem and used toguarantee the convergence of the WNN controllers. Simulation resultsshow that the robustness and the good performance of the proposedcontrol system to satisfy stable tracking of the boiler-turbine system.