Condition Monitoring of a Nuclear Power Plant Check Valve Based on Acoustic Emission and a Neural Network

[+] Author and Article Information
Min-Rae Lee

Department of Mechanical Design Engineering,  Pusan National University, Korealmin97@pusan.ac.kr

Joon-Hyun Lee1

School of Mechanical Engineering, Pusan National University, San 30 Jangjeon-dong, Kumjeong-gu, Pusan, 609-735, Koreajohlee@pusan.ac.kr

Jung-Teak Kim

Man-Machine Interface System Team, Korea Atomic Energy Research Institute Yuseong, Daejeon, 305-600, Koreajtkim@kaeri.re.kr


Corresponding author. School of Mechanical Engineering, Pusan National University, Pusan, 609-735, Korea. Telephone: 82-51-510-2430; Fax: 82-51-512-9835.

J. Pressure Vessel Technol 127(3), 230-236 (Apr 11, 2005) (7 pages) doi:10.1115/1.1991880 History: Received March 02, 2005; Revised April 11, 2005

The analysis of acoustic emission (AE) signals produced during object leakage is promising for condition monitoring of the components. In this study, an advanced condition monitoring technique based on acoustic emission detection and artificial neural networks was applied to a check valve, one of the components being used extensively in a safety system of a nuclear power plant. AE testing for a check valve under controlled flow loop conditions was performed to detect and evaluate disk movement for valve degradation such as wear and leakage due to foreign object interference in a check valve. It is clearly demonstrated that the evaluation of different types of failure modes such as disk wear and check valve leakage were successful by systematically analyzing the characteristics of various AE parameters. It is also shown that the leak size can be determined with an artificial neural network.

Copyright © 2005 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Typical swing type check valve (a) configuration of swing type check valve (b) photograph of swing type check valve (4 in.)

Grahic Jump Location
Figure 2

Simplified depiction of the condition monitoring for the check valve

Grahic Jump Location
Figure 3

Diagnosis algorithm using the neural network

Grahic Jump Location
Figure 4

Four different kinds of artificial defects of check valve. (a) Disc wear, (b) hinge pin wear, (c) foreign objective, (d) improper assembly.

Grahic Jump Location
Figure 5

Direct Vessel Injection (DVI) test loop of the check valve test

Grahic Jump Location
Figure 6

Test configuration of the check valve

Grahic Jump Location
Figure 7

Photograph of experimental setup

Grahic Jump Location
Figure 8

AE r.m.s versus pressure obtained from “disc wear” and “foreign object” failure

Grahic Jump Location
Figure 9

AE r.m.s value versus leak rate obtained from “disc wear” and “foreign object” failure

Grahic Jump Location
Figure 10

Frequency Spectra of leak signals at the 150 kHz sensor (a) “disc wear” (b)“foreign object” failure modes



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In