Parameter selection for training process of neuro-fuzzy systems for average air temperature estimation

Author

Jassar, Surinder ; Zhao, Lian ; Liao, Zaiyi ; Ng, Ka Long Ringo

Author_Institution

Dept. of Electr. & Comput. Eng., Ryerson Univ., Toronto, ON, Canada

fYear

2009

fDate

9-12 Aug. 2009

Firstpage

1218

Lastpage

1222

Abstract

Adaptive neuro-fuzzy inference systems are used to develop the inferential sensor model for estimating the average air temperature in space water heating systems. Fuzzy inference system structure identification and parameter selection for structure training are the key factors for system performance. This paper describes grid partition based fuzzy inference system, named ANFIS-GRID. The impact of selection of proper parameters for training process using ANFIS-GRID is presented. Results demonstrate that selection of number of MFs, step size and step size increase rate affect the performance of the model.

Keywords

atmospheric temperature; fuzzy neural nets; inference mechanisms; temperature sensors; ANFIS-GRID; adaptive neuro-fuzzy inference systems; average air temperature estimation; grid partition; inferential sensor model; parameter selection; space water heating systems; structure identification; training process; Adaptive systems; Automatic control; Automation; Biological control systems; Boilers; Fuzzy neural networks; Fuzzy systems; Sensor systems; Temperature control; Temperature sensors; ANFIS; ANFIS training; Average air temperature; Grid partition;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, 2009. ICMA 2009. International Conference on

Conference_Location

Changchun

Print_ISBN

978-1-4244-2692-8

Electronic_ISBN

978-1-4244-2693-5

Type

conf

DOI

10.1109/ICMA.2009.5246537

Filename

5246537