You need JavaScript to view this

Acoustic leak detection at complicated geometrical structures using fuzzy logic and neural networks

Abstract

An acoustic method based on pattern recognition is being developed. During the learning phase, the localization classifier is trained with sound patterns that are generated with simulated leaks at all locations endangered by leak. The patterns are extracted from the signals of an appropriate sensor array. After training unknown leak positions can be recognized through comparison with the training patterns. The experimental part is performed at an acoustic 1:3 model of the reactor vessel and head and at an original VVER-440 reactor in the former NPP Greifswald. The leaks were simulated at the vessel head using mobile sound sources driven either by compressed air, a piezoelectric transmitter or by a thin metal blade excited through a jet of compressed air. The sound patterns of the simulated leaks are simultaneously detected with an AE-sensor array and with high frequency microphones measuring structure-borne sound and airborne sound, respectively. Pattern classifiers based on Fuzzy Pattern Classification (FPC) and Artificial Neural Networks (ANN) are currently tested for validation of the acoustic emission-sensor array (FPC), leak localization via structure-borne sound (FPC) and the leak localization using microphones (ANN). The initial results show the used classifiers principally to be capable of detecting and locating leaks, but  More>>
Publication Date:
Oct 01, 1993
Product Type:
Technical Report
Report Number:
FZR-93-21
Reference Number:
SCA: 220400; PA: DEN-94:0F5246; EDB-94:067833; NTS-94:022034; SN: 94001190126
Resource Relation:
Other Information: PBD: Oct 1993
Subject:
22 GENERAL STUDIES OF NUCLEAR REACTORS; LEAK TESTING; ACOUSTIC MONITORING; REACTOR MONITORING SYSTEMS; ACOUSTIC EMISSION TESTING; PATTERN RECOGNITION; FUZZY LOGIC; PRESSURE VESSELS; SCALE MODELS; MOCKUP; NEURAL NETWORKS; SIMULATION; GREIFSWALD-5 REACTOR; 220400; CONTROL SYSTEMS
OSTI ID:
10143509
Research Organizations:
Forschungszentrum Rossendorf e.V. (FZR), Rossendorf bei Dresden (Germany)
Country of Origin:
Germany
Language:
English
Other Identifying Numbers:
Other: ON: DE94761048; TRN: DE94F5246
Availability:
OSTI; NTIS (US Sales Only); INIS
Submitting Site:
DEN
Size:
35 p.
Announcement Date:
Jul 05, 2005

Citation Formats

Hessel, G, Schmitt, W, and Weiss, F P. Acoustic leak detection at complicated geometrical structures using fuzzy logic and neural networks. Germany: N. p., 1993. Web.
Hessel, G, Schmitt, W, & Weiss, F P. Acoustic leak detection at complicated geometrical structures using fuzzy logic and neural networks. Germany.
Hessel, G, Schmitt, W, and Weiss, F P. 1993. "Acoustic leak detection at complicated geometrical structures using fuzzy logic and neural networks." Germany.
@misc{etde_10143509,
title = {Acoustic leak detection at complicated geometrical structures using fuzzy logic and neural networks}
author = {Hessel, G, Schmitt, W, and Weiss, F P}
abstractNote = {An acoustic method based on pattern recognition is being developed. During the learning phase, the localization classifier is trained with sound patterns that are generated with simulated leaks at all locations endangered by leak. The patterns are extracted from the signals of an appropriate sensor array. After training unknown leak positions can be recognized through comparison with the training patterns. The experimental part is performed at an acoustic 1:3 model of the reactor vessel and head and at an original VVER-440 reactor in the former NPP Greifswald. The leaks were simulated at the vessel head using mobile sound sources driven either by compressed air, a piezoelectric transmitter or by a thin metal blade excited through a jet of compressed air. The sound patterns of the simulated leaks are simultaneously detected with an AE-sensor array and with high frequency microphones measuring structure-borne sound and airborne sound, respectively. Pattern classifiers based on Fuzzy Pattern Classification (FPC) and Artificial Neural Networks (ANN) are currently tested for validation of the acoustic emission-sensor array (FPC), leak localization via structure-borne sound (FPC) and the leak localization using microphones (ANN). The initial results show the used classifiers principally to be capable of detecting and locating leaks, but they also show that further investigations are necessary to develop a reliable method applicable at NPPs. (orig./HP)}
place = {Germany}
year = {1993}
month = {Oct}
}