Classification of acoustic-emission waveforms for nondestructive evaluation using neural networks

Conference · Sat Mar 31 23:00:00 EST 1990 · Proceedings of SPIE - The International Society for Optical Engineering

DOI:https://doi.org/10.1117/12.21205· OSTI ID:6856343

Barga, Roger S. ^[1]; Friesel, Mark A. ^[1]; Melton, Ronald B. ^[1]

---

1. Pacific Northwest Laboratory (PNL), Richland, WA (United States)

Neural networks were applied to the classification of two types of acoustic emission (AE) events, crack growth and fretting, from a simulated airframe joint specimen. Signals were obtained from four sensors at different locations on the test specimen. Multilayered neural networks were trained to classify the signals using the error backpropagation learning algorithm, enabling AE events arising from crack growth to be distinguished from those caused by fretting. In this paper we evaluate the neural network classification performance for sensor location dependent and sensor location independent training and testing sets. Further, we present a new training strategy which significantly reduces the time required to learn large training sets using the error backpropagation learning algorithm, and improves the generalization performance of the network.

• Research Organization: Pacific Northwest Laboratory (PNL), Richland, WA (United States)
• Sponsoring Organization: USDOE Office of Nuclear Energy (NE)
• DOE Contract Number: AC06-76RL01830
• OSTI ID: 6856343
• Report Number(s): PNL-SA-18095; CONF-9003200--1; ON: DE90017239
• Journal Information: Proceedings of SPIE - The International Society for Optical Engineering, Journal Name: Proceedings of SPIE - The International Society for Optical Engineering Vol. 1294; ISSN 0277-786X
• Publisher: SPIE
• Country of Publication: United States
• Language: English

Related Subjects

36 MATERIALS SCIENCE
360103 -- Metals & Alloys-- Mechanical Properties
360104 -- Metals & Alloys-- Physical Properties
42 ENGINEERING
420500 -- Engineering-- Materials Testing
97 MATHEMATICS AND COMPUTING
99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ACOUSTIC EMISSION TESTING
ACOUSTIC MEASUREMENTS
ACOUSTIC TESTING
AIRCRAFT
ALGORITHMS
CHEMICAL REACTIONS
COMPUTER ARCHITECTURE
CORROSION
CRACK PROPAGATION
DATA ACQUISITION SYSTEMS
EVALUATION
FAILURE MODE ANALYSIS
FEASIBILITY STUDIES
FREQUENCY ANALYSIS
FRETTING CORROSION
FUNCTIONS
IMAGE PROCESSING
LEARNING
MAPPING
MATERIALS TESTING
MATHEMATICAL LOGIC
MEASURING METHODS
NEURAL NETWORKS
NONDESTRUCTIVE TESTING
PARALLEL PROCESSING
PATTERN RECOGNITION
PERFORMANCE
PROCESSING
PROGRAMMING
SYSTEM FAILURE ANALYSIS
SYSTEMS ANALYSIS
TESTING
TRANSDUCERS
TRANSFER FUNCTIONS
WAVE PROPAGATION