Applications of object-oriented approaches to neural networks in fault diagnosis

Shao Hung Chang, Jiann Liang Chen, Huan Wen Tzeng, Chin Ming Hong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A fault diagnosis system incorporating object-oriented programming models into a neural network is developed and reported in the paper. At the same time, to draw an inference efficiently, back-propagation learning rules, statistical process control, and alpha-beta depth-first algorithm are also embedded in the system. For the purpose of fault diagnosis, the object-oriented multilayer perceptron network is first trained by the back-propagation learning rule. Then, the statistical process control is used to analyze the trends by historical data and detect suspicious components. At last, by means of the alpha-beta search technology, the most plausible fault candidates and the rank of those candidates are generated speedily.

Original languageEnglish
Title of host publicationProceedings of the IEEE Conference on Decision and Control
PublisherPubl by IEEE
Pages3708-3709
Number of pages2
ISBN (Print)0780312988
Publication statusPublished - 1993 Dec 1
EventProceedings of the 32nd IEEE Conference on Decision and Control. Part 2 (of 4) - San Antonio, TX, USA
Duration: 1993 Dec 151993 Dec 17

Publication series

NameProceedings of the IEEE Conference on Decision and Control
Volume4
ISSN (Print)0191-2216

Other

OtherProceedings of the 32nd IEEE Conference on Decision and Control. Part 2 (of 4)
CitySan Antonio, TX, USA
Period93/12/1593/12/17

Fingerprint

Statistical Process Control
Statistical process control
Rule Learning
Back Propagation
Fault Diagnosis
Backpropagation
Object-oriented
Failure analysis
Neural Networks
Neural networks
Computer systems programming
Object-oriented Programming
Object oriented programming
Historical Data
Multilayer neural networks
Perceptron
Programming Model
Multilayer
Fault
Trends

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Control and Optimization

Cite this

Chang, S. H., Chen, J. L., Tzeng, H. W., & Hong, C. M. (1993). Applications of object-oriented approaches to neural networks in fault diagnosis. In Proceedings of the IEEE Conference on Decision and Control (pp. 3708-3709). (Proceedings of the IEEE Conference on Decision and Control; Vol. 4). Publ by IEEE.

Applications of object-oriented approaches to neural networks in fault diagnosis. / Chang, Shao Hung; Chen, Jiann Liang; Tzeng, Huan Wen; Hong, Chin Ming.

Proceedings of the IEEE Conference on Decision and Control. Publ by IEEE, 1993. p. 3708-3709 (Proceedings of the IEEE Conference on Decision and Control; Vol. 4).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chang, SH, Chen, JL, Tzeng, HW & Hong, CM 1993, Applications of object-oriented approaches to neural networks in fault diagnosis. in Proceedings of the IEEE Conference on Decision and Control. Proceedings of the IEEE Conference on Decision and Control, vol. 4, Publ by IEEE, pp. 3708-3709, Proceedings of the 32nd IEEE Conference on Decision and Control. Part 2 (of 4), San Antonio, TX, USA, 93/12/15.
Chang SH, Chen JL, Tzeng HW, Hong CM. Applications of object-oriented approaches to neural networks in fault diagnosis. In Proceedings of the IEEE Conference on Decision and Control. Publ by IEEE. 1993. p. 3708-3709. (Proceedings of the IEEE Conference on Decision and Control).
Chang, Shao Hung ; Chen, Jiann Liang ; Tzeng, Huan Wen ; Hong, Chin Ming. / Applications of object-oriented approaches to neural networks in fault diagnosis. Proceedings of the IEEE Conference on Decision and Control. Publ by IEEE, 1993. pp. 3708-3709 (Proceedings of the IEEE Conference on Decision and Control).
@inproceedings{0680ee482c4e461191df13659d518d88,
title = "Applications of object-oriented approaches to neural networks in fault diagnosis",
abstract = "A fault diagnosis system incorporating object-oriented programming models into a neural network is developed and reported in the paper. At the same time, to draw an inference efficiently, back-propagation learning rules, statistical process control, and alpha-beta depth-first algorithm are also embedded in the system. For the purpose of fault diagnosis, the object-oriented multilayer perceptron network is first trained by the back-propagation learning rule. Then, the statistical process control is used to analyze the trends by historical data and detect suspicious components. At last, by means of the alpha-beta search technology, the most plausible fault candidates and the rank of those candidates are generated speedily.",
author = "Chang, {Shao Hung} and Chen, {Jiann Liang} and Tzeng, {Huan Wen} and Hong, {Chin Ming}",
year = "1993",
month = "12",
day = "1",
language = "English",
isbn = "0780312988",
series = "Proceedings of the IEEE Conference on Decision and Control",
publisher = "Publ by IEEE",
pages = "3708--3709",
booktitle = "Proceedings of the IEEE Conference on Decision and Control",

}

TY - GEN

T1 - Applications of object-oriented approaches to neural networks in fault diagnosis

AU - Chang, Shao Hung

AU - Chen, Jiann Liang

AU - Tzeng, Huan Wen

AU - Hong, Chin Ming

PY - 1993/12/1

Y1 - 1993/12/1

N2 - A fault diagnosis system incorporating object-oriented programming models into a neural network is developed and reported in the paper. At the same time, to draw an inference efficiently, back-propagation learning rules, statistical process control, and alpha-beta depth-first algorithm are also embedded in the system. For the purpose of fault diagnosis, the object-oriented multilayer perceptron network is first trained by the back-propagation learning rule. Then, the statistical process control is used to analyze the trends by historical data and detect suspicious components. At last, by means of the alpha-beta search technology, the most plausible fault candidates and the rank of those candidates are generated speedily.

AB - A fault diagnosis system incorporating object-oriented programming models into a neural network is developed and reported in the paper. At the same time, to draw an inference efficiently, back-propagation learning rules, statistical process control, and alpha-beta depth-first algorithm are also embedded in the system. For the purpose of fault diagnosis, the object-oriented multilayer perceptron network is first trained by the back-propagation learning rule. Then, the statistical process control is used to analyze the trends by historical data and detect suspicious components. At last, by means of the alpha-beta search technology, the most plausible fault candidates and the rank of those candidates are generated speedily.

UR - http://www.scopus.com/inward/record.url?scp=0027851971&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027851971&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027851971

SN - 0780312988

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 3708

EP - 3709

BT - Proceedings of the IEEE Conference on Decision and Control

PB - Publ by IEEE

ER -