{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:01:07Z","timestamp":1790618467934,"version":"4.1.0"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2025TSGCCZZB0911"],"award-info":[{"award-number":["2025TSGCCZZB0911"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Bearing fault diagnosis for rotating machinery remains challenging due to strong background noise and variable operating conditions in harsh industrial environments. To address these issues, this paper proposes a robust and lightweight bearing fault diagnosis framework, termed Multi-scale and Dual-scale Wavelet Mamba (MDW-Mamba), for noisy and non-stationary industrial applications. The proposed method employs a multi-stage \u201cnoise-feature decoupling\u201d strategy, comprising a statistically guided three-channel input, a Multi-scale Omni-kernel Convolutions (MOM-Conv) backbone, and a Dual-Scale Wavelet Mamba (DSW-Mamba) module. This architecture explicitly separates fault components from broadband noise while enabling efficient long-term dependency modeling. Experimental results on three public datasets under variable-speed conditions demonstrate that MDW-Mamba consistently outperforms state-of-the-art methods. It achieves an average classification accuracy exceeding 87% even at a signal-to-noise ratio of \u22126 dB, showing exceptional robustness against strong interference. Furthermore, the model maintains an ultra-lightweight footprint of 0.26 M parameters and a fast inference time of 1.285 ms, indicating strong potential for real-time, on-board deployment in resource-constrained industrial edge devices.<\/jats:p>","DOI":"10.1371\/journal.pone.0358759","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:31:58Z","timestamp":1790616718000},"page":"e0358759","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust bearing fault diagnosis for rotating machinery under noisy and variable operating conditions using a Wavelet-Mamba Network"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3909-1929","authenticated-orcid":true,"given":"Dayou","family":"Cui","sequence":"first","affiliation":[{"name":"School of Railway Transportation, Shandong Jiaotong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4284-8540","authenticated-orcid":true,"given":"Zhaoyan","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Railway Transportation, Shandong Jiaotong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixue","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Railway Transportation, Shandong Jiaotong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Railway Transportation, Shandong Jiaotong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangxuan","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Railway Transportation, Shandong Jiaotong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"pone.0358759.ref001","doi-asserted-by":"crossref","first-page":"110924","DOI":"10.1016\/j.ress.2025.110924","article-title":"Health evaluation techniques towards rotating machinery: a systematic literature review and implementation guideline","volume":"260","author":"W Jiang","year":"2025","journal-title":"Reliabil Eng System Safety"},{"issue":"1","key":"pone.0358759.ref002","doi-asserted-by":"crossref","first-page":"58","DOI":"10.3390\/s26010058","article-title":"Condition monitoring system for planetary journal bearings in wind turbines based on surface acoustic wave measurements\u2014validation on a system level","volume":"26","author":"TM Decker","year":"2026","journal-title":"Sensors"},{"key":"pone.0358759.ref003","doi-asserted-by":"crossref","first-page":"151","DOI":"10.24874\/ti.1749.09.24.12","article-title":"Comparative analysis of machine learning techniques for fault diagnosis of rolling element bearing with wear defects","volume":"7","author":"D Sahu","year":"2025","journal-title":"Tribol Ind"},{"key":"pone.0358759.ref004","doi-asserted-by":"crossref","first-page":"110596","DOI":"10.1016\/j.ress.2024.110596","article-title":"Explicit speed-integrated LSTM network for non-stationary gearbox vibration representation and fault detection under varying speed conditions","volume":"254","author":"Y Chen","year":"2025","journal-title":"Reliabil Eng Syst Saf"},{"key":"pone.0358759.ref005","first-page":"1","article-title":"Deep transfer learning for bearing fault diagnosis: a systematic review since 2016","volume":"72","author":"X Chen","year":"2023","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0358759.ref006","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/j.ymssp.2017.06.022","article-title":"A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load","volume":"100","author":"W Zhang","year":"2018","journal-title":"Mech Syst Signal Process"},{"key":"pone.0358759.ref007","doi-asserted-by":"crossref","first-page":"106587","DOI":"10.1016\/j.ymssp.2019.106587","article-title":"Applications of machine learning to machine fault diagnosis: a review and roadmap","volume":"138","author":"Y Lei","year":"2020","journal-title":"Mech Syst Signal Process"},{"issue":"2","key":"pone.0358759.ref008","doi-asserted-by":"crossref","first-page":"425","DOI":"10.3390\/s17020425","article-title":"A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals","volume":"17","author":"W Zhang","year":"2017","journal-title":"Sensors (Basel)"},{"key":"pone.0358759.ref009","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"pone.0358759.ref010","doi-asserted-by":"crossref","first-page":"3196","DOI":"10.1109\/TIE.2018.2844805","article-title":"Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox","volume":"66","author":"G Jiang","year":"2019","journal-title":"IEEE Transac Indus Electron"},{"key":"pone.0358759.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2023.3288742","article-title":"CNN-TransNet: a hybrid CNN-transformer network with differential feature enhancement for cloud detection","volume":"20","author":"N Ma","year":"2023","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"pone.0358759.ref012","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.energy.2019.05.230","article-title":"Predicting residential energy consumption using CNN-LSTM neural networks","volume":"182","author":"T-Y Kim","year":"2019","journal-title":"Energy"},{"key":"pone.0358759.ref013","doi-asserted-by":"crossref","first-page":"110242","DOI":"10.1016\/j.measurement.2021.110242","article-title":"Fault diagnosis for small samples based on attention mechanism","volume":"187","author":"X Zhang","year":"2022","journal-title":"Measurement"},{"issue":"4","key":"pone.0358759.ref014","doi-asserted-by":"crossref","first-page":"6356","DOI":"10.1109\/TII.2023.3345449","article-title":"Cross-domain class incremental broad network for continuous diagnosis of rotating machinery faults under variable operating conditions","volume":"20","author":"M Shi","year":"2024","journal-title":"IEEE Trans Ind Inf"},{"key":"pone.0358759.ref015","doi-asserted-by":"crossref","first-page":"110172","DOI":"10.1016\/j.knosys.2022.110172","article-title":"Deep hypergraph autoencoder embedding: an efficient intelligent approach for rotating machinery fault diagnosis","volume":"260","author":"M Shi","year":"2023","journal-title":"Knowledge-Based Syst"},{"issue":"7","key":"pone.0358759.ref016","doi-asserted-by":"crossref","first-page":"075108","DOI":"10.1088\/1361-6501\/acc885","article-title":"Bearing fault diagnosis method using the joint feature extraction of transformer and ResNet","volume":"34","author":"S Hou","year":"2023","journal-title":"Meas Sci Technol"},{"key":"pone.0358759.ref017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Advances in neural information processing systems. 2017. 5998\u20136008."},{"key":"pone.0358759.ref018","unstructured":"Gu A, Dao T. Mamba: linear-time sequence modeling with selective state spaces. 2024."},{"key":"pone.0358759.ref019","first-page":"1","article-title":"FDMamba: frequency-driven dual-branch mamba network for road extraction from remote sensing images","volume":"63","author":"Z Wang","year":"2025","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0358759.ref020","first-page":"1","article-title":"Rep-mamba: re-parameterization in vision mamba for lightweight remote sensing image super-resolution","volume":"63","author":"K Jiang","year":"2025","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0358759.ref021","doi-asserted-by":"crossref","first-page":"102589","DOI":"10.1016\/j.inffus.2024.102589","article-title":"MixMamba: Time series modeling with adaptive expertise","volume":"112","author":"K Alkilane","year":"2024","journal-title":"Inform Fusion"},{"key":"pone.0358759.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3381688","article-title":"FFT-trans: enhancing robustness in mechanical fault diagnosis with fourier transform-based transformer under noisy conditions","volume":"73","author":"X Luo","year":"2024","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0358759.ref023","first-page":"1","article-title":"Multiscale Noise Reduction Attention Network for Aeroengine Bearing Fault Diagnosis","volume":"72","author":"X Wang","year":"2023","journal-title":"IEEE Trans Instrum Meas"},{"issue":"7","key":"pone.0358759.ref024","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/34.192463","article-title":"A theory for multiresolution signal decomposition: the wavelet representation","volume":"11","author":"SG Mallat","year":"1989","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"pone.0358759.ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2024.3506034","article-title":"WaveMamba: spatial-spectral wavelet mamba for hyperspectral image classification","volume":"22","author":"M Ahmad","year":"2025","journal-title":"IEEE Geosci Remote Sensing Lett"},{"key":"pone.0358759.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2025.3584385","article-title":"IRSRMamba: infrared image super-resolution via mamba-based wavelet transform feature modulation model","volume":"63","author":"Y Huang","year":"2025","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0358759.ref027","first-page":"1","article-title":"Small-sample mechanical fault diagnosis based on multi-scale dilatable convolution and DMWT-Mamba","volume":"46","author":"JY Yang","year":"2025","journal-title":"Noise and Vibration Control"},{"issue":"21","key":"pone.0358759.ref028","doi-asserted-by":"crossref","first-page":"6652","DOI":"10.3390\/s25216652","article-title":"Fault diagnosis of rolling bearings using denoising multi-channel mixture of CNN and mamba-enhanced adaptive self-attention LSTM","volume":"25","author":"S Lai","year":"2025","journal-title":"Sensors (Basel)"},{"key":"pone.0358759.ref029","doi-asserted-by":"crossref","first-page":"110536","DOI":"10.1016\/j.engappai.2025.110536","article-title":"Dual-branch crack segmentation network with multi-shape kernel based on convolutional neural network and Mamba","volume":"150","author":"J Zhang","year":"2025","journal-title":"Eng Appl Artif Intel"},{"key":"pone.0358759.ref030","doi-asserted-by":"crossref","first-page":"125518","DOI":"10.1016\/j.eswa.2024.125518","article-title":"Selective and multi-scale fusion Mamba for medical image segmentation","volume":"261","author":"G Li","year":"2025","journal-title":"Expert Syst Appl"},{"key":"pone.0358759.ref031","doi-asserted-by":"crossref","first-page":"131092","DOI":"10.1016\/j.neucom.2025.131092","article-title":"Bearing fault diagnosis under heavy noise: a multi-scale dilated convolution and dense temporal convolutional network","volume":"652","author":"X Si","year":"2025","journal-title":"Neurocomputing"},{"key":"pone.0358759.ref032","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Yang J. Selective kernel networks. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 2019. 510\u20139. https:\/\/doi.org\/10.1109\/cvpr.2019.00060","DOI":"10.1109\/CVPR.2019.00060"},{"key":"pone.0358759.ref033","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. 2018. 7132\u201341. https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"8","key":"pone.0358759.ref034","doi-asserted-by":"crossref","first-page":"5856","DOI":"10.1016\/j.jksuci.2021.07.012","article-title":"A Hybrid robust watermarking system based on discrete cosine transform, discrete wavelet transform, and singular value decomposition","volume":"34","author":"M Begum","year":"2022","journal-title":"J King Saud Univ - Comp Inform Sci"},{"key":"pone.0358759.ref035","unstructured":"Loshchilov I, Hutter F. Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representations (ICLR), 2017."},{"key":"pone.0358759.ref036","doi-asserted-by":"crossref","unstructured":"D\u2019Angelo F, Andriushchenko M, Varre A, Flammarion N. Why do we need weight decay in modern deep learning?. In: Advances in neural information processing systems 37, 2024. 23191\u2013223. https:\/\/doi.org\/10.52202\/079017-0730","DOI":"10.52202\/079017-0730"},{"key":"pone.0358759.ref037","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1016\/j.dib.2018.11.019","article-title":"Bearing vibration data collected under time-varying rotational speed conditions","volume":"21","author":"H Huang","year":"2018","journal-title":"Data Brief"},{"key":"pone.0358759.ref038","doi-asserted-by":"crossref","first-page":"109327","DOI":"10.1016\/j.dib.2023.109327","article-title":"University of Ottawa constant load and speed rolling-element bearing vibration and acoustic fault signature datasets","volume":"49","author":"M Sehri","year":"2023","journal-title":"Data Brief"},{"issue":"1","key":"pone.0358759.ref039","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/TR.2018.2882682","article-title":"A hybrid prognostics approach for estimating remaining useful life of rolling element bearings","volume":"69","author":"B Wang","year":"2020","journal-title":"IEEE Trans Rel"},{"issue":"16","key":"pone.0358759.ref040","first-page":"1","article-title":"XJTU-SY rolling element bearing accelerated life test datasets: a tutorial","volume":"55","author":"Y Lei","year":"2019","journal-title":"J Mech Eng"},{"key":"pone.0358759.ref041","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.isatra.2020.08.010","article-title":"Deep learning algorithms for rotating machinery intelligent diagnosis: an open source benchmark study","volume":"107","author":"Z Zhao","year":"2020","journal-title":"ISA Trans"},{"issue":"1","key":"pone.0358759.ref042","first-page":"8","article-title":"A small sample fault diagnosis method for bearings and gears based on triplet network","volume":"39","author":"Y Xie","year":"2022","journal-title":"J Mech Electrical Eng"},{"key":"pone.0358759.ref043","doi-asserted-by":"crossref","first-page":"111935","DOI":"10.1016\/j.ress.2025.111935","article-title":"Explainable artificial intelligence based intelligent fault diagnosis: a systematic review from applications to insights","volume":"267","author":"T Li","year":"2026","journal-title":"Reliability Eng System Safety"},{"issue":"3","key":"pone.0358759.ref044","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.1109\/TSMC.2025.3647102","article-title":"A Kolmogorov\u2013Arnold-informed interpretable graph wavelet activation network for machine fault diagnosis","volume":"56","author":"T Li","year":"2026","journal-title":"IEEE Trans Syst Man Cybern, Syst"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:32:11Z","timestamp":1790616731000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358759"}},"subtitle":[],"editor":[{"given":"Zhibin","family":"Zhao","sequence":"first","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":44,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358759","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]}}}