A probabilistic approach for acoustic emission based monitoring techniques: with application to structural health monitoring

TL;DR

This paper introduces a probabilistic, nonparametric Bayesian method using Dirichlet processes for automatic detection and characterization of acoustic emission events, improving damage detection and source localization in structural health monitoring.

Contribution

It presents a novel application of Dirichlet process-based Bayesian modeling for AE data analysis, addressing data volume and source identification challenges.

Findings

Effective AE event detection and characterization demonstrated

Applicable to real-world structures like journal bearings and aircraft landing gear

Enhances damage detection accuracy and source localization

Abstract

It has been demonstrated that acoustic-emission (AE), inspection of structures can offer advantages over other types of monitoring techniques in the detection of damage; namely, an increased sensitivity to damage, as well as an ability to localise its source. There are, however, numerous challenges associated with the analysis of AE data. One issue is the high sampling frequencies required to capture AE activity. In just a few seconds, a recording can generate very high volumes of data, of which a significant portion may be of little interest for analysis. Identifying the individual AE events in a recorded time-series is therefore a necessary procedure to reduce the size of the dataset. Another challenge that is also generally encountered in practice, is determining the sources of AE, which is an important exercise if one wishes to enhance the quality of the diagnostic scheme. In this paper, a state-of-the-art technique is presented that can automatically identify AE events, and simultaneously help in their characterisation from a probabilistic perspective. A nonparametric Bayesian approach, based on the Dirichlet process (DP), is employed to overcome some of the challenges associated with these tasks. Two main sets of AE data are considered in this work: (1) from a journal bearing in operation, and (2) from an Airbus A320 main landing gear subjected to fatigue testing.