Methods of artificial intelligence for acoustic emission diagnostics of fracture stages (a review) Part 1: algorithms of unsupervised and supervised machine learning

Based on the analysis of the latest studies, the possibilities of using unsupervised and supervised machine learning algorithms to automate the processing of acoustic emission signals to identify and localize their sources were considered. The accuracy of the results for different approaches was com...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Materials science (New York, N.Y.) Jg. 60; H. 3; S. 255 - 264
Hauptverfasser: Stankevych, O. M., Rebot, D. P.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.11.2024
Schlagworte:
Characterization and Evaluation of Materials
Chemistry and Materials Science
Materials Science
Solid Mechanics
Structural Materials
Acoustic emission
Identification of defects
Machine unsupervised and supervised learning
ISSN:1068-820X, 1573-885X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Based on the analysis of the latest studies, the possibilities of using unsupervised and supervised machine learning algorithms to automate the processing of acoustic emission signals to identify and localize their sources were considered. The accuracy of the results for different approaches was compared, and directions for improvement were described. The importance of further research regarding the adaptation and optimization of the latest techniques for various materials and structures was confirmed.
ISSN:1068-820X
1573-885X
DOI:10.1007/s11003-025-00880-4