Research on the Acoustic Emission Source Localization Methodology in Composite Materials based on Artificial Intelligence

TL;DR

The paper addresses the challenge of localizing acoustic emission sources in anisotropic composites where traditional time-of-arrival methods falter due to nonuniform wave propagation. It introduces AESLNet, a neural network that processes wavelet-derived scalograms and uses four parallel convolutional streams to account for sensor-position effects, with Bayesian optimization to tune hyperparameters. The approach achieves a mean localization error of $3.02$ mm and a 20 mm resolution, outperforming propagation-speed-based methods and standard CNNs, highlighting improved robustness for heterogeneous materials. This methodology has practical implications for structural health monitoring of composites and could extend to complex geometries and damage-detection applications.

Abstract

In this study, methodology of acoustic emission source localization in composite materials based on artificial intelligence was presented. Carbon fiber reinforced plastic was selected for specimen, and acoustic emission signal were measured using piezoelectric devices. The measured signal was wavelet-transformed to obtain scalograms, which were used as training data for the artificial intelligence model. AESLNet(acoustic emission source localization network), proposed in this study, was constructed convolutional layers in parallel due to anisotropy of the composited materials. It is regression model to detect the coordinates of acoustic emission source location. Hyper-parameter of network has been optimized by Bayesian optimization. It has been confirmed that network can detect location of acoustic emission source with an average error of 3.02mm and a resolution of 20mm.

Figures (9)

• Figure 1: Schematic of experiment
• Figure 2: Experimental Setup
• Figure 3: Signal Processing
• Figure 4: Acoustic emission signal
• Figure 5: Method to construct the database