Classification of materials using temperature response curve fitting and fuzzy neural network

This paper describes a system that can be used to classify an unknown mater ial regardless of the change of ambient temperature using temperature respo nse curve fitting and fuzzy neural network (FNN). There are some problems t o realize the classification system using temperature response. lt requires too many memories to store the vast temperature response data and it has t o be filtered to remove noise which occurs in experiment. And the temperatu re response is influenced by the change of ambient temperature. So, this pa per proposes a practical method using curve fitting to remove above problem s of memories and noise. And FNN is proposed to overcome the problem caused by the change of ambient temperature. Using the FNN which is learned by te mperature responses on fixed ambient temperature and known thermal conducti vity (TC), the TC of the material can be inferred on various ambient temper ature. So the material can be classified by the TC. (C) 2001 Elsevier Scien ce B.V. All rights reserved.