Universiti Teknologi Malaysia Institutional Repository

Adaptive GRNN for the modelling of dynamic plants

Yusof, Rubiyah and Khalid, Marzuki and Seng, Teo Lian (2002) Adaptive GRNN for the modelling of dynamic plants. In: Proceeding of the 2002 IEEE International Symposium on Intelligent Control, 27th-30th October 2002, Vancouver,Canada.

[img]
Preview
PDF
341Kb

Abstract

An integrated General Regression Neural Network (GRNN) adaptation scheme for dynamic plant modelling is proposed in this paper. It possesses several distinguished features compared to the original GRNN proposed by Specht [1], such as flexible pattern nodes add-in and delete-off mechanism, dynamic initial sigma assignment using non-statistical method, automatic target adjustment and sigma tuning. These adaptation strategies are formulated based on the inherent advantageous features found in GRNN, such as highly localised pattern nodes, good interpolation capability, instantaneous learning, etc.. Good modelling performance was obtained when the GRNN is tested on a linear plant in a noisy environment. It performs better than the well-known Extended Recursive Least Squares identification algorithm. In this paper, analysis on the effects of some of the adaptation parameters involving a nonlinear plant is also investigated. The results show that the proposed methodology is computationally efficient and exhibits several attractive features such as fast learning, flexible network sizing and good robustness, which are suitable for the construction of estimators or predictors for many model-based adaptive control strategies.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Adaptation,dynamic process, general regression neural network (GRNN), modelling, system identification
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:Electrical Engineering
ID Code:7326
Deposited By: Maznira Sylvia Azra Mansor
Deposited On:02 Jan 2009 00:50
Last Modified:01 Jun 2010 15:51

Repository Staff Only: item control page