Fault diagnosis based on radial basis function neural network in Particleboard Glue Mixing & Dosing System

Author

Liu, Yaqin ; Zhang, Xiaopeng ; Hua, Jun

Author_Institution

Northeast Forestry Univ., Harbin

fYear

2008

fDate

2-4 July 2008

Firstpage

774

Lastpage

778

Abstract

In this paper, a new style radial basis function neural network (RBF NN) is used for fault diagnosis in Particleboard Glue Mixing & Dosing System, which is firstly used in this field. The structure and its training algorithm of the network are discussed and the training algorithm chosen in the article is a self-adapt clustering training algorithm. The results of the simulation and fault tolerance test confirm that the proposed method can diagnose the fault of the system quickly and correctly. Furthermore, it has the ability of forecast warning.

Keywords

adhesives; fault diagnosis; fault tolerance; learning (artificial intelligence); pattern clustering; radial basis function networks; wood processing; RBFNN; dosing system; fault diagnosis; fault tolerance; forecast warning; particleboard glue mixing system; radial basis function neural network; self-adaptive clustering training algorithm; simulation; Clustering algorithms; Fault diagnosis; Feedforward systems; Iterative algorithms; Kernel; MATLAB; Neural networks; Neurons; Pattern clustering; Radial basis function networks; Fault Diagnosis; Particleboard Glue Mixing & Dosing System; Radial Basis Function Neural Network;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference, 2008. CCDC 2008. Chinese

Conference_Location

Yantai, Shandong

Print_ISBN

978-1-4244-1733-9

Electronic_ISBN

978-1-4244-1734-6

Type

conf

DOI

10.1109/CCDC.2008.4597418

Filename

4597418