skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Fault identification by neural network recognition of CUSUM chart patterns

Abstract

At the Mihama nuclear power plant in Japan, Okada and his staff first applied statistical quality control (SQC) methods to plant operations by developing a system for prevention of off-normal events and for improving the performance and reliability of the nuclear power plant. The conceptual design of an advanced diagnostic system, based in part on the method proposed by Okada, was subsequently developed by Heising and Grenzebach. The SQC methods may be viewed as a systematic way of reducing the quantity, and improving the quality, of process data. The output of the SQC methods, however, can still be abstract or complex. Its automatic interpretation is useful in quick isolation of incipient faults. Heising and Grenzebach proposed use of artificial intelligence methods for interpreting the output of SQC methods. This paper proposes neural network recognition of cumulative sum (CUSUM) chart patterns for plant fault identification.

Authors:
;
Publication Date:
OSTI Identifier:
89048
Report Number(s):
CONF-941102-
Journal ID: TANSAO; ISSN 0003-018X; TRN: 95:004215-0114
Resource Type:
Journal Article
Journal Name:
Transactions of the American Nuclear Society
Additional Journal Information:
Journal Volume: 71; Conference: Winter meeting of the American Nuclear Society (ANS), Washington, DC (United States), 13-18 Nov 1994; Other Information: PBD: 1994
Country of Publication:
United States
Language:
English
Subject:
22 NUCLEAR REACTOR TECHNOLOGY; REACTOR OPERATION; NEURAL NETWORKS; REACTOR SAFETY; PERFORMANCE

Citation Formats

Dhanwada, C V, and Heising, C D. Fault identification by neural network recognition of CUSUM chart patterns. United States: N. p., 1994. Web.
Dhanwada, C V, & Heising, C D. Fault identification by neural network recognition of CUSUM chart patterns. United States.
Dhanwada, C V, and Heising, C D. Sat . "Fault identification by neural network recognition of CUSUM chart patterns". United States.
@article{osti_89048,
title = {Fault identification by neural network recognition of CUSUM chart patterns},
author = {Dhanwada, C V and Heising, C D},
abstractNote = {At the Mihama nuclear power plant in Japan, Okada and his staff first applied statistical quality control (SQC) methods to plant operations by developing a system for prevention of off-normal events and for improving the performance and reliability of the nuclear power plant. The conceptual design of an advanced diagnostic system, based in part on the method proposed by Okada, was subsequently developed by Heising and Grenzebach. The SQC methods may be viewed as a systematic way of reducing the quantity, and improving the quality, of process data. The output of the SQC methods, however, can still be abstract or complex. Its automatic interpretation is useful in quick isolation of incipient faults. Heising and Grenzebach proposed use of artificial intelligence methods for interpreting the output of SQC methods. This paper proposes neural network recognition of cumulative sum (CUSUM) chart patterns for plant fault identification.},
doi = {},
url = {https://www.osti.gov/biblio/89048}, journal = {Transactions of the American Nuclear Society},
number = ,
volume = 71,
place = {United States},
year = {1994},
month = {12}
}