Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model

Composite laminates are widely used in aerospace, automotive, construction, and luxury industries, owing to their superior mechanical properties and design flexibility. However, detecting manufacturing defects and in-service damage remains a vital challenge for structural safety. While traditional u...

Full description

Saved in:
Bibliographic Details
Main Authors: Olivier Munyaneza, Jung Woo Sohn
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/15/2445
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405820151791616
author Olivier Munyaneza
Jung Woo Sohn
author_facet Olivier Munyaneza
Jung Woo Sohn
author_sort Olivier Munyaneza
collection DOAJ
description Composite laminates are widely used in aerospace, automotive, construction, and luxury industries, owing to their superior mechanical properties and design flexibility. However, detecting manufacturing defects and in-service damage remains a vital challenge for structural safety. While traditional unsupervised machine learning methods have been used in structural health monitoring (SHM), their high false positive rates limit their reliability in real-world applications. This issue is mostly inherited from their limited ability to capture small temporal variations in Lamb wave signals and their dependence on shallow architectures that suffer with complex signal distributions, causing the misclassification of damaged signals as healthy data. To address this, we suggested an unsupervised anomaly detection framework that integrates a self-attention autoencoder with a Gaussian mixture model (SAE-GMM). The model is solely trained on healthy Lamb wave signals, including high-quality synthetic data generated via a generative adversarial network (GAN). Damages are detected through reconstruction errors and probabilistic clustering in the latent space. The self-attention mechanism enhances feature representation by capturing subtle temporal dependencies, while the GMM enables a solid separation among signals. Experimental results demonstrated that the proposed model (SAE-GMM) achieves high detection accuracy, a low false positive rate, and strong generalization under varying noise conditions, outperforming traditional and deep learning baselines.
format Article
id doaj-art-69426417c24d4ce98ab0bb68b5719e7f
institution Kabale University
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-69426417c24d4ce98ab0bb68b5719e7f2025-08-20T03:36:34ZengMDPI AGMathematics2227-73902025-07-011315244510.3390/math13152445Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture ModelOlivier Munyaneza0Jung Woo Sohn1Department of Aeronautics, Mechanical and Electronic Convergence Engineering, Graduated School, Kumoh National Institute of Technology, Daehak-ro 61, Gumi 39177, Republic of KoreaSchool of Mechanical Engineering, Kumoh National Institute of Technology, Daehak-ro 61, Gumi 39177, Republic of KoreaComposite laminates are widely used in aerospace, automotive, construction, and luxury industries, owing to their superior mechanical properties and design flexibility. However, detecting manufacturing defects and in-service damage remains a vital challenge for structural safety. While traditional unsupervised machine learning methods have been used in structural health monitoring (SHM), their high false positive rates limit their reliability in real-world applications. This issue is mostly inherited from their limited ability to capture small temporal variations in Lamb wave signals and their dependence on shallow architectures that suffer with complex signal distributions, causing the misclassification of damaged signals as healthy data. To address this, we suggested an unsupervised anomaly detection framework that integrates a self-attention autoencoder with a Gaussian mixture model (SAE-GMM). The model is solely trained on healthy Lamb wave signals, including high-quality synthetic data generated via a generative adversarial network (GAN). Damages are detected through reconstruction errors and probabilistic clustering in the latent space. The self-attention mechanism enhances feature representation by capturing subtle temporal dependencies, while the GMM enables a solid separation among signals. Experimental results demonstrated that the proposed model (SAE-GMM) achieves high detection accuracy, a low false positive rate, and strong generalization under varying noise conditions, outperforming traditional and deep learning baselines.https://www.mdpi.com/2227-7390/13/15/2445composite laminatesunsupervised machine learningstructural healthy monitoringself-attentionGaussian mixture modelgenerative adversarial network
spellingShingle Olivier Munyaneza
Jung Woo Sohn
Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model
Mathematics
composite laminates
unsupervised machine learning
structural healthy monitoring
self-attention
Gaussian mixture model
generative adversarial network
title Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model
title_full Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model
title_fullStr Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model
title_full_unstemmed Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model
title_short Anomaly Detection on Laminated Composite Plate Using Self-Attention Autoencoder and Gaussian Mixture Model
title_sort anomaly detection on laminated composite plate using self attention autoencoder and gaussian mixture model
topic composite laminates
unsupervised machine learning
structural healthy monitoring
self-attention
Gaussian mixture model
generative adversarial network
url https://www.mdpi.com/2227-7390/13/15/2445
work_keys_str_mv AT oliviermunyaneza anomalydetectiononlaminatedcompositeplateusingselfattentionautoencoderandgaussianmixturemodel
AT jungwoosohn anomalydetectiononlaminatedcompositeplateusingselfattentionautoencoderandgaussianmixturemodel