An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks

To address the issue of rolling bearing fault diagnosis, this paper proposes a novel model combining the Improved Gorilla Troop Optimization (IGTO) algorithm, Variational Mode Decomposition (VMD), Permutation Entropy (PE), and Long Short-Term Memory (LSTM) networks. The IGTO algorithm is used to opt...

Full description

Saved in:
Bibliographic Details
Main Authors: Xianglong Luo, Fengrong Yu, Jing Qian, Biao An, Nengpeng Duan
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4338
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144588697698304
author Xianglong Luo
Fengrong Yu
Jing Qian
Biao An
Nengpeng Duan
author_facet Xianglong Luo
Fengrong Yu
Jing Qian
Biao An
Nengpeng Duan
author_sort Xianglong Luo
collection DOAJ
description To address the issue of rolling bearing fault diagnosis, this paper proposes a novel model combining the Improved Gorilla Troop Optimization (IGTO) algorithm, Variational Mode Decomposition (VMD), Permutation Entropy (PE), and Long Short-Term Memory (LSTM) networks. The IGTO algorithm is used to optimize the parameters of VMD and LSTM, enhancing signal decomposition and feature extraction. The proposed model achieves fault classification accuracies of 96.67% and 98.96% in the testing and training phases, respectively, on the Case Western Reserve University dataset, with minimal accuracy fluctuations. Furthermore, on the Jiangnan University dataset, the model reaches an average testing accuracy of 98.85%, with the highest accuracy reaching 99.48%. The results also demonstrate high stability, as indicated by low standard deviations (1.2148 and 1.3217) and narrow 95% confidence intervals ([95.75%, 97.58%] and [96.73%, 97.49%]). Despite a longer average runtime of 13.88 s per sample, the model’s superior accuracy justifies the computational cost. These results demonstrate the model’s excellent diagnostic performance, adaptability to different datasets, and practical applicability for rolling bearing fault diagnosis. This approach provides a valuable reference for predictive maintenance and fault detection systems in industrial applications.
format Article
id doaj-art-b173316fc9dc43b49b298df4a238aee6
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-b173316fc9dc43b49b298df4a238aee62025-08-20T02:28:19ZengMDPI AGApplied Sciences2076-34172025-04-01158433810.3390/app15084338An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM NetworksXianglong Luo0Fengrong Yu1Jing Qian2Biao An3Nengpeng Duan4School of Metallurgy and Energy Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaSchool of Metallurgy and Energy Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaSchool of Metallurgy and Energy Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaSchool of Metallurgy and Energy Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaSchool of Metallurgy and Energy Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaTo address the issue of rolling bearing fault diagnosis, this paper proposes a novel model combining the Improved Gorilla Troop Optimization (IGTO) algorithm, Variational Mode Decomposition (VMD), Permutation Entropy (PE), and Long Short-Term Memory (LSTM) networks. The IGTO algorithm is used to optimize the parameters of VMD and LSTM, enhancing signal decomposition and feature extraction. The proposed model achieves fault classification accuracies of 96.67% and 98.96% in the testing and training phases, respectively, on the Case Western Reserve University dataset, with minimal accuracy fluctuations. Furthermore, on the Jiangnan University dataset, the model reaches an average testing accuracy of 98.85%, with the highest accuracy reaching 99.48%. The results also demonstrate high stability, as indicated by low standard deviations (1.2148 and 1.3217) and narrow 95% confidence intervals ([95.75%, 97.58%] and [96.73%, 97.49%]). Despite a longer average runtime of 13.88 s per sample, the model’s superior accuracy justifies the computational cost. These results demonstrate the model’s excellent diagnostic performance, adaptability to different datasets, and practical applicability for rolling bearing fault diagnosis. This approach provides a valuable reference for predictive maintenance and fault detection systems in industrial applications.https://www.mdpi.com/2076-3417/15/8/4338rolling bearingfault diagnosisimproved gorilla troops optimizationvariational mode decompositionlong-term memory network
spellingShingle Xianglong Luo
Fengrong Yu
Jing Qian
Biao An
Nengpeng Duan
An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks
Applied Sciences
rolling bearing
fault diagnosis
improved gorilla troops optimization
variational mode decomposition
long-term memory network
title An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks
title_full An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks
title_fullStr An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks
title_full_unstemmed An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks
title_short An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks
title_sort intelligent fault diagnosis model for rolling bearings based on igto optimized vmd and lstm networks
topic rolling bearing
fault diagnosis
improved gorilla troops optimization
variational mode decomposition
long-term memory network
url https://www.mdpi.com/2076-3417/15/8/4338
work_keys_str_mv AT xianglongluo anintelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT fengrongyu anintelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT jingqian anintelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT biaoan anintelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT nengpengduan anintelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT xianglongluo intelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT fengrongyu intelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT jingqian intelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT biaoan intelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks
AT nengpengduan intelligentfaultdiagnosismodelforrollingbearingsbasedonigtooptimizedvmdandlstmnetworks