返回
Lamb wave based automatic damage detection using matching pursuit and machine learning
DOI:10.1088/0964-1726/23/8/085012.png)
摘要
En 中文
In this study, matching pursuit (MP) has been tested with machine learning algorithms such as artificial neural networks (ANNs) and support vector machines (SVMs) to automate the process of damage detection in metallic plates. Here, damage detection is done using the Lamb wave response in a thin aluminium plate simulated using a finite element (FE) method. To reduce the complexity of the Lamb wave response, only the A(0) mode is excited and sensed. The procedure adopted for damage detection consists of three major steps, involving signal processing and machine learning (ML). In the first step, MP is used for de-noising and enhancing the sparsity of the database. In the existing literature, MP is used to decompose any signal into a linear combination of waveforms that are selected from a redundant dictionary. In this work, MP is deployed in two stages to make the database sparse as well as to de-noise it. After using MP on the database, it is then passed as input data for ML classifiers. ANN and SVM are used to detect the location of the potential damage from the reduced data. The study demonstrates that the SVM is a robust classifier in the presence of noise and is more efficient than the ANN. Out-of-sample data are used for the validation of the trained and tested classifier. Trained classifiers are found to be successful in the detection of damage with a detection rate of more than 95%.
Keyword:
Lamb wave
matching pursuit
SVM
ANN
damage detection
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.8
论文数:
8.5K
被引数:
2.5W
机构
引用论文
Lamb wave-based quantitative identification of delamination in CF/EP composite structures using artificial neural algorithm
COMPOSITE STRUCTURES
IF7.1
Interaction of Lamb mode (Ao) with structural discontinuity and generation of Turning modes'' in a T-joint
ULTRASONICS
IF4.1

