A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm
Predicting remaining useful life (RUL) is crucial for tool condition monitoring (TCM) systems. Inaccurate predictions can lead to premature tool replacements or excessive usage, resulting in resource wastage and potential equipment failures. This study introduces a novel tool RUL prediction method t...
Published in: | Mathematics |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2024
|
Subjects: | |
Online Access: | https://doi.org/10.3390/math12152404 https://doaj.org/article/519265c0fdc3424297d2682ef13fde46 |
id |
ftdoajarticles:oai:doaj.org/article:519265c0fdc3424297d2682ef13fde46 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:519265c0fdc3424297d2682ef13fde46 2024-09-15T18:25:45+00:00 A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm Jianwei Wu Jiaqi Wang Huanguo Chen 2024-08-01T00:00:00Z https://doi.org/10.3390/math12152404 https://doaj.org/article/519265c0fdc3424297d2682ef13fde46 EN eng MDPI AG https://www.mdpi.com/2227-7390/12/15/2404 https://doaj.org/toc/2227-7390 doi:10.3390/math12152404 2227-7390 https://doaj.org/article/519265c0fdc3424297d2682ef13fde46 Mathematics, Vol 12, Iss 15, p 2404 (2024) bidirectional long short-term memory enhanced northern goshawk optimization remaining useful life prediction tool wear Mathematics QA1-939 article 2024 ftdoajarticles https://doi.org/10.3390/math12152404 2024-08-12T15:24:03Z Predicting remaining useful life (RUL) is crucial for tool condition monitoring (TCM) systems. Inaccurate predictions can lead to premature tool replacements or excessive usage, resulting in resource wastage and potential equipment failures. This study introduces a novel tool RUL prediction method that integrates the enhanced northern goshawk optimization (MSANGO) algorithm with a bidirectional long short-term memory (BiLSTM) network. Initially, key statistical features are extracted from collected signal data using multivariate variational mode decomposition. This is followed by effective feature reduction, facilitated by the uniform information coefficient and Mann–Kendall trend tests. The RUL predictions are subsequently refined through a BiLSTM network, with the MSANGO algorithm optimizing the network parameters. Comparative evaluations with BiLSTM, BiGRU, and NGO-BiLSTM models, as well as tests on real-world datasets, demonstrate this method’s superior accuracy and generalizability in RUL prediction, enhancing the efficacy of tool management systems. Article in Journal/Newspaper Northern Goshawk Directory of Open Access Journals: DOAJ Articles Mathematics 12 15 2404 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
bidirectional long short-term memory enhanced northern goshawk optimization remaining useful life prediction tool wear Mathematics QA1-939 |
spellingShingle |
bidirectional long short-term memory enhanced northern goshawk optimization remaining useful life prediction tool wear Mathematics QA1-939 Jianwei Wu Jiaqi Wang Huanguo Chen A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm |
topic_facet |
bidirectional long short-term memory enhanced northern goshawk optimization remaining useful life prediction tool wear Mathematics QA1-939 |
description |
Predicting remaining useful life (RUL) is crucial for tool condition monitoring (TCM) systems. Inaccurate predictions can lead to premature tool replacements or excessive usage, resulting in resource wastage and potential equipment failures. This study introduces a novel tool RUL prediction method that integrates the enhanced northern goshawk optimization (MSANGO) algorithm with a bidirectional long short-term memory (BiLSTM) network. Initially, key statistical features are extracted from collected signal data using multivariate variational mode decomposition. This is followed by effective feature reduction, facilitated by the uniform information coefficient and Mann–Kendall trend tests. The RUL predictions are subsequently refined through a BiLSTM network, with the MSANGO algorithm optimizing the network parameters. Comparative evaluations with BiLSTM, BiGRU, and NGO-BiLSTM models, as well as tests on real-world datasets, demonstrate this method’s superior accuracy and generalizability in RUL prediction, enhancing the efficacy of tool management systems. |
format |
Article in Journal/Newspaper |
author |
Jianwei Wu Jiaqi Wang Huanguo Chen |
author_facet |
Jianwei Wu Jiaqi Wang Huanguo Chen |
author_sort |
Jianwei Wu |
title |
A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm |
title_short |
A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm |
title_full |
A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm |
title_fullStr |
A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm |
title_full_unstemmed |
A Method for Predicting Tool Remaining Useful Life: Utilizing BiLSTM Optimized by an Enhanced NGO Algorithm |
title_sort |
method for predicting tool remaining useful life: utilizing bilstm optimized by an enhanced ngo algorithm |
publisher |
MDPI AG |
publishDate |
2024 |
url |
https://doi.org/10.3390/math12152404 https://doaj.org/article/519265c0fdc3424297d2682ef13fde46 |
genre |
Northern Goshawk |
genre_facet |
Northern Goshawk |
op_source |
Mathematics, Vol 12, Iss 15, p 2404 (2024) |
op_relation |
https://www.mdpi.com/2227-7390/12/15/2404 https://doaj.org/toc/2227-7390 doi:10.3390/math12152404 2227-7390 https://doaj.org/article/519265c0fdc3424297d2682ef13fde46 |
op_doi |
https://doi.org/10.3390/math12152404 |
container_title |
Mathematics |
container_volume |
12 |
container_issue |
15 |
container_start_page |
2404 |
_version_ |
1810466227517128704 |