Title of Paper:NUMERICAL DYNAMIC MODELING AND DATA DRIVEN CONTROL VIA LEAST SQUARE TECHNIQUES AND HEBBIAN LEARNING ALGORITHM

Hits:

Date of Publication:2010-01-01

Journal:INTERNATIONAL JOURNAL OF NUMERICAL ANALYSIS AND MODELING

Included Journals:SCIE、Scopus

Volume:7

Issue:1

Page Number:66-86

ISSN No.:1705-5105

Key Words:Least Square Learning; Fuzzy cognitive map; Takagi_Sugeno model; Complex dynamic system; Hebbian learning algorithm

Abstract:The modelling and controlling for complex dynamic systems which are too complicated to establish conventionally mathematical mechanism models require new methodology that can utilize the existing knowledge, human experience and historical data. Fuzzy cognitive maps (FCMs) are a very convenient, simple, and powerful tool for simulation and analysis of dynamic systems. Since human experts are subjective and can handle only relatively simple FCMs, there is an urgent need to develop methods for automated generation of FCM models using historical data. In this paper, a novel FCM, which is automatically generated from data and can be applied to on-line control, is developed by improving its constitution, introducing Least Square methods and using Hebbian Learning techniques. As an illustrative example, the simulations results of truck backer-upper control problem quantifies the performance of the proposed constructions of FCM and emphasizes its effectiveness and advantageous characteristics of the learning techniques and control ability.