{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T18:09:26Z","timestamp":1790014166097,"version":"4.0.1"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To address the significant decline in the accuracy of rolling bearing fault diagnosis under variable working conditions and strong noise, which is caused by feature distribution shift and fault feature submersion, this paper proposes a bearing fault diagnosis method based on the Dual Attention Multi-Scale Convolutional Neural Network (DAMSCNN). First, a parallel multi-scale convolution module with multiple kernel sizes extracts fault features under different receptive fields, overcoming the limitation of fixed receptive fields in single-scale convolution. Second, a cascaded channel-spatial dual attention mechanism is designed following a progressive weighting strategy. A residual connection is embedded in the channel attention branch to highlight fault-sensitive channels and suppress redundant ones. The spatial attention branch fuses global average pooling and max pooling to strengthen fault impulse regions and suppress interference from working condition fluctuations and background noise. Finally, the weighted features are classified by a Softmax classifier. Experiments on the CWRU bearing dataset demonstrate that DAMSCNN achieves a peak diagnostic accuracy of 99.69% in cross-condition tasks and maintains accuracy above 92% under \u22125 dB SNR, outperforming BiTCN-Transformer, MTFC-T, and CTCA in accuracy, recall, and F1-score, while also offering lower computational cost and faster inference speed.<\/jats:p>","DOI":"10.1371\/journal.pone.0358253","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:29:57Z","timestamp":1790011797000},"page":"e0358253","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Rolling bearing fault diagnosis method based on dual attention multi-scale convolutional network"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1550-8506","authenticated-orcid":true,"given":"Yamei","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Intelligent Science and Engineering, Xi\u2019an Peihua University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohu","family":"Liu","sequence":"additional","affiliation":[{"name":"Trine Engineering Institute, Shaanxi University of Technology","place":["Hanzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"issue":"4","key":"pone.0358253.ref001","first-page":"571","article-title":"Fault diagnosis of rolling bearing based on channel attention mechanism and multi-scale subtraction lightweight neural network","volume":"45","author":"L Zhang","year":"2025","journal-title":"Journal of Chinese Society of Power Engineering"},{"issue":"3","key":"pone.0358253.ref002","first-page":"118","article-title":"Cable fault-automation positioning technology based on CNN and BiLSTM","volume":"40","author":"L Hao","year":"2025","journal-title":"Automation and Instrumentation"},{"issue":"6","key":"pone.0358253.ref003","first-page":"267","article-title":"Fault diagnosis of wind turbine high-speed bearings based on time-frequency dual-domain fusion","volume":"47","author":"J Liu","year":"2026","journal-title":"Acta Energiae Solaris Sinica"},{"issue":"12","key":"pone.0358253.ref004","first-page":"258","article-title":"Fault diagnosis method for shaft bearing of mine hoist under strong background noise based on VMD-MOMEDA-CNN","volume":"39","author":"J Shen","year":"2025","journal-title":"J Electronic Measur Instrumentation"},{"issue":"12","key":"pone.0358253.ref005","doi-asserted-by":"crossref","first-page":"452","DOI":"10.3390\/lubricants12120452","article-title":"A Rolling Bearing Fault Diagnosis Method Combining MSSSA-VMD with the Parallel Network of GASF-CNN and BiLSTM","volume":"12","author":"Y Du","year":"2024","journal-title":"Lubricants"},{"issue":"12","key":"pone.0358253.ref006","first-page":"135","article-title":"Shearer cutting section rolling bearing fault diagnosis based on VMD-Transformer-BiGRU","volume":"49","author":"L Wang","year":"2026","journal-title":"Modern Electronic Technique"},{"issue":"8","key":"pone.0358253.ref007","first-page":"2992","article-title":"Information fusion diagnosis of switching tube open-circuit fault in V2G charging piles based on multi-scale convolutional neural network and dual-attention mechanism","volume":"45","author":"Y Xu","year":"2025","journal-title":"Proceedings of the CSEE"},{"issue":"8","key":"pone.0358253.ref008","first-page":"1405","article-title":"Bearing fault diagnosis of mining drilling rig with time-frequency-fused deep network","volume":"35","author":"X Zou","year":"2024","journal-title":"China Mechanical Eng"},{"issue":"5","key":"pone.0358253.ref009","first-page":"134","article-title":"Composite fault diagnosis of rolling bearing based on attention mechanism and CNN convolution network","volume":"52","author":"i Chen Q","year":"2023","journal-title":"Machine Building and Automation"},{"issue":"2","key":"pone.0358253.ref010","first-page":"113","article-title":"Fault diagnosis of rolling bearings based on denoising multi-branch CNN and attention mechanism","volume":"64","author":"J Liu","year":"2023","journal-title":"Modular Machine Tool and Automatic Manufacturing Technique"},{"issue":"1","key":"pone.0358253.ref011","doi-asserted-by":"crossref","first-page":"100226","DOI":"10.1016\/j.geits.2024.100226","article-title":"State of charge estimation of lithium-ion battery based on state of temperature estimation using weight clustered-convolutional neural network-long short-term memory","volume":"4","author":"C Li","year":"2025","journal-title":"Green Energy and Intelligent Transportation"},{"issue":"3","key":"pone.0358253.ref012","doi-asserted-by":"crossref","first-page":"100337","DOI":"10.1016\/j.geits.2025.100337","article-title":"Dynamic range compression dual-domain attention network for tunnel extreme exposure image enhancement in transportation visual systems","volume":"5","author":"B Xu","year":"2026","journal-title":"Green Energy and Intelligent Transportation"},{"issue":"9","key":"pone.0358253.ref013","first-page":"37","article-title":"Bearing fault diagnosis based on multi-scale convolutional neural network and self-attention feature fusion mechanism","volume":"12","author":"Y Huang","year":"2022","journal-title":"Intelligent Computer and Applications"},{"issue":"2","key":"pone.0358253.ref014","first-page":"66","article-title":"Improved CNN bearing fault diagnosis under variable working conditions with attention mechanism","volume":"42","author":"J Zhang","year":"2022","journal-title":"Journal of Anhui University of Science and Technology (Natural Science)"},{"key":"pone.0358253.ref015","unstructured":"Kong L. Research on bearing fault diagnosis method under complex working conditions based on convolutional neural network. Tianjin University, 2022."},{"key":"pone.0358253.ref016","author":"J Su","year":"2021"},{"issue":"2","key":"pone.0358253.ref017","article-title":"A weighted DJP-MMD based deep transfer metric learning for the fault diagnosis of bearing under variable working conditions","volume":"20","author":"Z Xu","year":"2025","journal-title":"Front Mech Eng"},{"issue":"1","key":"pone.0358253.ref018","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1108\/IJSI-02-2025-0043","article-title":"Simulation knowledge transfer: a new approach for intelligent fault diagnosis of rolling bearings using simulation-reality domain mixup adaptation","volume":"17","author":"F Jia","year":"2026","journal-title":"Int J Structural Integrity"},{"issue":"1","key":"pone.0358253.ref019","first-page":"10","article-title":"Bearing fault diagnosis based on multi-scale transfer learning","volume":"46","author":"H Yin","year":"2025","journal-title":"Machinery Design and Manufacture"},{"issue":"3","key":"pone.0358253.ref020","first-page":"35","article-title":"Fault diagnosis of rolling bearings based on improved CEEMDAN and CNN-BiGRU","volume":"33","author":"W Zheng","year":"2026","journal-title":"J Lanzhou Instit Technoly"},{"issue":"7","key":"pone.0358253.ref021","first-page":"65","article-title":"Rolling bearing fault diagnosis with multi-scale multi-task attention convolutional neural network","volume":"28","author":"Z Wang","year":"2024","journal-title":"Electric Machines and Control"},{"issue":"6","key":"pone.0358253.ref022","first-page":"68","article-title":"Fault diagnosis of wind turbine rolling bearings based on SSA optimization of VME and SMHD","volume":"53","author":"J Yu","year":"2025","journal-title":"Small and Special Electrical Machines"},{"issue":"5","key":"pone.0358253.ref023","first-page":"159","article-title":"Rolling bearing fault diagnosis method based on wavelet packet transform and CEEMDAN","volume":"39","author":"X Luan","year":"2024","journal-title":"J Aerospace Power"},{"issue":"5","key":"pone.0358253.ref024","first-page":"48","article-title":"Research on bearing fault diagnosis method based on an improved CNN-Transformer architecture","volume":"39","author":"H Xu","year":"2026","journal-title":"Industrial Control Computer"},{"issue":"2","key":"pone.0358253.ref025","first-page":"32","article-title":"Rolling Bearing fault diagnosis based on attention mechanism and lightweight adaptive CNN model","volume":"45","author":"J Tang","year":"2026","journal-title":"Ordnance Industry Automation"},{"issue":"2","key":"pone.0358253.ref026","first-page":"267","article-title":"Operating condition domain generalization fault diagnosis method for bearings based on a multiscale convolutional neural network and the two-stage attention mechanism","volume":"44","author":"H Qiao","year":"2025","journal-title":"Journal of Vibration and Shock"},{"issue":"9","key":"pone.0358253.ref027","first-page":"84","article-title":"Rolling bearing fault diagnosis method based on a multi-scale and improved gated recurrent neural network with dual attention","volume":"45","author":"M Wang","year":"2024","journal-title":"J Vibration and Shock"},{"issue":"9","key":"pone.0358253.ref028","first-page":"120","article-title":"Attention mechanism and multi-source information fusion-based method for bearing fault diagnosis under variable operating conditions","volume":"45","author":"H Qiao","year":"2024","journal-title":"Chinese J Scientific Instrument"},{"issue":"5","key":"pone.0358253.ref029","first-page":"105","article-title":"Fault diagnosis of motor rolling bearings based on dual-channel information fusion and VCC-FuseNet","volume":"48","author":"Y He","year":"2026","journal-title":"Journal of Mechanical Strength"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:30:06Z","timestamp":1790011806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358253"}},"subtitle":[],"editor":[{"given":"Lei","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":29,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358253","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]}}}