Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments

This study outlines the development and optimization of a Long Short-Term Memory (LSTM) network designed to analyze and classify time-series data from tribological experiments, with a particular emphasis on identifying stationary phases. The process of fine-tuning key hyperparameters was systematica...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuxiao Zhao, Leyu Lin, Alois K. Schlarb
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Lubricants
Subjects:
Online Access:https://www.mdpi.com/2075-4442/12/12/423
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050055666401280
author Yuxiao Zhao
Leyu Lin
Alois K. Schlarb
author_facet Yuxiao Zhao
Leyu Lin
Alois K. Schlarb
author_sort Yuxiao Zhao
collection DOAJ
description This study outlines the development and optimization of a Long Short-Term Memory (LSTM) network designed to analyze and classify time-series data from tribological experiments, with a particular emphasis on identifying stationary phases. The process of fine-tuning key hyperparameters was systematically optimized through Bayesian optimization, coupled with K-fold cross-validation to minimize the inherent randomness associated with training neural networks. The refined LSTM network achieved a weighted average accuracy of 84%, demonstrating a high level of agreement between the network’s identified stationary phases and those manually determined by researchers. This result suggests that LSTM networks can reliably mimic manual identification processes in tribological data, providing a promising avenue for automating data analysis. The study underscores the potential of neural networks to transcend their traditional role in predictive modeling within tribology, opening up new possibilities for their application across a broader spectrum of tasks within the field.
format Article
id doaj-art-5335b01ba8f546d1a0af01b4500faa5f
institution DOAJ
issn 2075-4442
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Lubricants
spelling doaj-art-5335b01ba8f546d1a0af01b4500faa5f2025-08-20T02:53:34ZengMDPI AGLubricants2075-44422024-11-01121242310.3390/lubricants12120423Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological ExperimentsYuxiao Zhao0Leyu Lin1Alois K. Schlarb2Chair of Composite Engineering (CCe), Rheinland-Pfälzische Technische Universität (RPTU) Kaiserslautern-Landau, 67663 Kaiserslautern, GermanyChair of Composite Engineering (CCe), Rheinland-Pfälzische Technische Universität (RPTU) Kaiserslautern-Landau, 67663 Kaiserslautern, GermanyChair of Composite Engineering (CCe), Rheinland-Pfälzische Technische Universität (RPTU) Kaiserslautern-Landau, 67663 Kaiserslautern, GermanyThis study outlines the development and optimization of a Long Short-Term Memory (LSTM) network designed to analyze and classify time-series data from tribological experiments, with a particular emphasis on identifying stationary phases. The process of fine-tuning key hyperparameters was systematically optimized through Bayesian optimization, coupled with K-fold cross-validation to minimize the inherent randomness associated with training neural networks. The refined LSTM network achieved a weighted average accuracy of 84%, demonstrating a high level of agreement between the network’s identified stationary phases and those manually determined by researchers. This result suggests that LSTM networks can reliably mimic manual identification processes in tribological data, providing a promising avenue for automating data analysis. The study underscores the potential of neural networks to transcend their traditional role in predictive modeling within tribology, opening up new possibilities for their application across a broader spectrum of tasks within the field.https://www.mdpi.com/2075-4442/12/12/423artificial neural network (ANN)long short-term memory (LSTM)tribologypolymer-based composites
spellingShingle Yuxiao Zhao
Leyu Lin
Alois K. Schlarb
Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
Lubricants
artificial neural network (ANN)
long short-term memory (LSTM)
tribology
polymer-based composites
title Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
title_full Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
title_fullStr Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
title_full_unstemmed Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
title_short Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
title_sort long short term memory networks for the automated identification of the stationary phase in tribological experiments
topic artificial neural network (ANN)
long short-term memory (LSTM)
tribology
polymer-based composites
url https://www.mdpi.com/2075-4442/12/12/423
work_keys_str_mv AT yuxiaozhao longshorttermmemorynetworksfortheautomatedidentificationofthestationaryphaseintribologicalexperiments
AT leyulin longshorttermmemorynetworksfortheautomatedidentificationofthestationaryphaseintribologicalexperiments
AT aloiskschlarb longshorttermmemorynetworksfortheautomatedidentificationofthestationaryphaseintribologicalexperiments