Residual generation and visualization for understanding novel process conditions

Author

Díaz, Ignacio ; Hollmén, Jaakko

Author_Institution

Area de Ingenieria de Sistemas y Automatica, Univ. of Oviedo, Gijon, Spain

Volume

3

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

2070

Lastpage

2075

Abstract

We study the generation and visualization of residuals for detecting and identifying unseen faults using auto-associative models learned from process data. Least squares and kernel regression models are compared on the basis of their ability to describe the support of the data. Theoretical results show that kernel regression models are more appropriate in this sense. Moreover, experiments on vibration and current data from an asynchronous motor confirm the theory and yield more meaningful results

Keywords

condition monitoring; data visualisation; fault diagnosis; identification; induction motors; least squares approximations; neural nets; statistical analysis; asynchronous motor; autoassociative models; data visualization; fault identification; kernel regression; least squares; neural nets; novelty detection; residual generation; Data visualization; Fault detection; Fault diagnosis; Information science; Kernel; Laboratories; Least squares methods; Mathematical model; Power generation; Technological innovation;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007460

Filename

1007460