Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation

The detection of acoustic emission events from various failing mechanisms, such as plastic deformations, is a critical element in the monitoring and timely detection of structural failures in infrastructures. This study focuses on the detection of such failures in metal gates at rivers’ lifting dams...

Full description

Saved in:
Bibliographic Details
Main Authors: Theocharis Tsenis, Vassilios Kappatos
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/2/38
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080488392228864
author Theocharis Tsenis
Vassilios Kappatos
author_facet Theocharis Tsenis
Vassilios Kappatos
author_sort Theocharis Tsenis
collection DOAJ
description The detection of acoustic emission events from various failing mechanisms, such as plastic deformations, is a critical element in the monitoring and timely detection of structural failures in infrastructures. This study focuses on the detection of such failures in metal gates at rivers’ lifting dams aiming to increase the reliability of river transport compared to the current situation, thereby, increasing the resilience of transport corridors. During our study, we used lifting dams in both France and Italy where river transport is thriving. A methodology was developed, processing corresponding acoustic emission recordings originating from lifting dams’ metal gates, using advanced denoising—preprocessing, various decompositions, and spectral embeddings associated with various latest nonlinear processing clustering techniques—thus providing a detailed cluster label morphology and profile of water gates’ normal operating area. Latest machine learning outlier detection algorithms, like One-Class Support Vector Machine, Variational Auto-Encoder, and others, were incorporated, producing a vector of confidence on upcoming out-of-the-normal gate operation and failure prediction, achieving detection contrast enhancement on out-of-the-normal operation points up to 400%.
format Article
id doaj-art-7d3d4bc56b374940ba165273086da209
institution DOAJ
issn 2412-3811
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-7d3d4bc56b374940ba165273086da2092025-08-20T02:44:56ZengMDPI AGInfrastructures2412-38112025-02-011023810.3390/infrastructures10020038Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal OperationTheocharis Tsenis0Vassilios Kappatos1Department C: Non-land Transport, Environmental and Economic Issues, Sector of Hellenic Institute of Transportation (HIT), Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceDepartment C: Non-land Transport, Environmental and Economic Issues, Sector of Hellenic Institute of Transportation (HIT), Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceThe detection of acoustic emission events from various failing mechanisms, such as plastic deformations, is a critical element in the monitoring and timely detection of structural failures in infrastructures. This study focuses on the detection of such failures in metal gates at rivers’ lifting dams aiming to increase the reliability of river transport compared to the current situation, thereby, increasing the resilience of transport corridors. During our study, we used lifting dams in both France and Italy where river transport is thriving. A methodology was developed, processing corresponding acoustic emission recordings originating from lifting dams’ metal gates, using advanced denoising—preprocessing, various decompositions, and spectral embeddings associated with various latest nonlinear processing clustering techniques—thus providing a detailed cluster label morphology and profile of water gates’ normal operating area. Latest machine learning outlier detection algorithms, like One-Class Support Vector Machine, Variational Auto-Encoder, and others, were incorporated, producing a vector of confidence on upcoming out-of-the-normal gate operation and failure prediction, achieving detection contrast enhancement on out-of-the-normal operation points up to 400%.https://www.mdpi.com/2412-3811/10/2/38acoustic emissioninfrastructuresupport vector machinevariational auto-encoderspectral clustering
spellingShingle Theocharis Tsenis
Vassilios Kappatos
Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation
Infrastructures
acoustic emission
infrastructure
support vector machine
variational auto-encoder
spectral clustering
title Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation
title_full Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation
title_fullStr Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation
title_full_unstemmed Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation
title_short Clustering and Vectorizing Acoustic Emission Events of Large Infrastructures’ Normal Operation
title_sort clustering and vectorizing acoustic emission events of large infrastructures normal operation
topic acoustic emission
infrastructure
support vector machine
variational auto-encoder
spectral clustering
url https://www.mdpi.com/2412-3811/10/2/38
work_keys_str_mv AT theocharistsenis clusteringandvectorizingacousticemissioneventsoflargeinfrastructuresnormaloperation
AT vassilioskappatos clusteringandvectorizingacousticemissioneventsoflargeinfrastructuresnormaloperation