{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T01:08:20Z","timestamp":1776301700488,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T00:00:00Z","timestamp":1723248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"2022 Open Research Project of the National Key Laboratory for Special Vehicle Design and Manufacturing Integration Technology","award":["2022.F.FQ. Process-0492"],"award-info":[{"award-number":["2022.F.FQ. Process-0492"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>To address the issues of inadequate feature extraction for rolling bearings, inaccurate fault diagnosis, and overfitting in complex operating conditions, this paper proposes a rolling bearing diagnosis method based on multi-scale feature fusion and transfer adversarial learning. Firstly, a multi-scale convolutional fusion layer is designed to effectively extract fault features from the original vibration signals at multiple time scales. Through a feature encoding fusion module based on the multi-head attention mechanism, feature fusion extraction is performed, which can model long-distance contextual information and significantly improve diagnostic accuracy and anti-noise capability. Secondly, based on the domain adaptation (DA) cross-domain feature adversarial learning strategy of transfer learning methods, the extraction of optimal domain-invariant features is achieved by reducing the gap in data distribution between the target domain and the source domain, addressing the call for research on fault diagnosis across operating conditions, equipment, and virtual\u2013real migrations. Finally, experiments were conducted to verify and optimize the effectiveness of the feature extraction and fusion network. A public bearing dataset was used as the source domain data, and special vehicle bearing data were selected as the target domain data for comparative experiments on the effect of network transfer learning. The experimental results demonstrate that the proposed method exhibits an exceptional performance in cross-domain and variable load environments. In multiple bearing cross-domain transfer learning tasks, the method achieves an average migration fault diagnosis accuracy rate of up to 98.65%. When compared with existing methods, the proposed method significantly enhances the ability of data feature extraction, thereby achieving a more robust diagnostic performance.<\/jats:p>","DOI":"10.3390\/s24165181","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T11:23:46Z","timestamp":1723461826000},"page":"5181","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Fault Diagnosis Method of Special Vehicle Bearing Based on Multi-Scale Feature Fusion and Transfer Adversarial Learning"],"prefix":"10.3390","volume":"24","author":[{"given":"Zhiguo","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100811, China"},{"name":"College of Computer Science and Technology, Changchun University, Changchun 130022, China"},{"name":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou City 014030, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongni","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100811, China"},{"name":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou City 014030, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunguang","family":"Yang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou City 014030, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou City 014030, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"107036","DOI":"10.1016\/j.measurement.2019.107036","article-title":"Fault diagnosis of rolling bearings using weighted horizontal visibility graph and graph Fourier transform","volume":"149","author":"Gao","year":"2020","journal-title":"Measurement"},{"key":"ref_2","first-page":"13","article-title":"Deep learning technology and its application analysis and outlook in fault diagnosis","volume":"54","author":"Zhang","year":"2020","journal-title":"J. Xi\u2019an Jiaotong Univ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","article-title":"Deep learning and its applications to machine health monitoring","volume":"115","author":"Rui","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_4","first-page":"351","article-title":"Knock edge diagnosis of gasoline engine based on wavelet transform and Hilbert transform","volume":"37","author":"Lin","year":"2019","journal-title":"Trans. CSICE"},{"key":"ref_5","first-page":"4508","article-title":"Feature extraction and abnormal state diagnosis of on-load tap-changer based on complementary ensemble empirical mode decomposition and local outlier factor","volume":"34","author":"Zhang","year":"2019","journal-title":"Trans. China Electrotech. Soc."},{"key":"ref_6","first-page":"81","article-title":"Application of improved empirical wavelet transform and minimum entropy deconvolution in railway bearing fault diagnosis","volume":"40","author":"Qiao","year":"2021","journal-title":"J. Vib. Shock"},{"key":"ref_7","first-page":"85","article-title":"Fault Diagnosis of Rolling Bearings Based on GSA-VMD and Adaptive CNN","volume":"60","author":"Wang","year":"2022","journal-title":"Modul. Mach. Tool Autom. Manuf. Tech."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8628","DOI":"10.1109\/TII.2024.3366993","article-title":"Transparent operator network: A fully interpretable network incorporating learnable wavelet operator for intelligent fault diagnosis","volume":"20","author":"Li","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110688","DOI":"10.1016\/j.ymssp.2023.110688","article-title":"Dynamic weighted federated remaining useful life prediction approach for rotating machinery","volume":"202","author":"Qin","year":"2023","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_10","unstructured":"Zhang, J. (2022). Research on Fault Diagnosis Method and Application of Rolling Bearings Based on Sparse Representation. [Ph.D. Thesis, Xi\u2019an University of Technology]."},{"key":"ref_11","first-page":"41","article-title":"Fault diagnosis method of bearings based on G-DPSO algorithm and decision tree","volume":"24","author":"Zhang","year":"2021","journal-title":"Ind. Eng. J."},{"key":"ref_12","first-page":"172","article-title":"Research on fault diagnosis system of motor bearings based on improved Bayesian classification","volume":"48","author":"Yang","year":"2020","journal-title":"Mach. Tool Hydraul."},{"key":"ref_13","first-page":"221","article-title":"Bearing fault diagnosis based on multi-scale permutation entropy and parameter-optimized support vector machine","volume":"41","author":"Wang","year":"2022","journal-title":"J. Vib. Shock"},{"key":"ref_14","first-page":"180","article-title":"Fault diagnosis of rolling bearings for mine belt conveyors based on artificial neural network technology","volume":"42","author":"Zhang","year":"2014","journal-title":"Mach. Tool Hydraul."},{"key":"ref_15","first-page":"53","article-title":"Fault diagnosis of variable load rolling bearings based on improved DenseNet and transfer learning","volume":"41","author":"Lv","year":"2023","journal-title":"Light Ind. Mach."},{"key":"ref_16","first-page":"58","article-title":"Intelligent fault diagnosis of mechanical equipment based on feature knowledge transfer under unlabeled data","volume":"40","author":"Guo","year":"2019","journal-title":"Chin. J. Sci. Instrum."},{"key":"ref_17","first-page":"45","article-title":"Research review on fault diagnosis of bearings with small samples","volume":"59","author":"Si","year":"2023","journal-title":"Comput. Eng. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.1016\/j.isatra.2014.06.002","article-title":"Bi-spectrum based-EMD applied to the non-stationary vibration signals for bearing faults diagnosis","volume":"53","author":"Saidi","year":"2015","journal-title":"ISA Trans."},{"key":"ref_19","first-page":"184","article-title":"New fault diagnosis approach for bearings based on parameter optimized VMD and genetic algorithm","volume":"40","author":"He","year":"2021","journal-title":"J. Vib. Shock"},{"key":"ref_20","first-page":"7","article-title":"Research on fault diagnosis method of train axle box bearings based on improved multi-scale permutation entropy","volume":"42","author":"Li","year":"2020","journal-title":"J. China Railw. Soc."},{"key":"ref_21","first-page":"121","article-title":"Bearing fault diagnosis based on parallel network multi-scale feature fusion","volume":"42","author":"Jiang","year":"2023","journal-title":"Transducer Microsyst. Technol."},{"key":"ref_22","first-page":"151","article-title":"Fault diagnosis method of rolling bearings based on MTF-CNN","volume":"41","author":"Lei","year":"2022","journal-title":"J. Vib. Shock."},{"key":"ref_23","first-page":"258","article-title":"A new fault diagnosis method of reducer bearings based on DSCNN-GRU structure","volume":"39","author":"Wang","year":"2020","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_24","first-page":"361","article-title":"Fault diagnosis of bearings in different source domains based on balanced adaptation transfer","volume":"40","author":"Zhu","year":"2023","journal-title":"Mech. Electr. Eng. Mag."},{"key":"ref_25","first-page":"21","article-title":"Fault diagnosis of rolling bearings across domains based on DCGAN and DANN networks","volume":"41","author":"Hu","year":"2022","journal-title":"J. Vib. Shock"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"57023","DOI":"10.1109\/ACCESS.2019.2912072","article-title":"Lightweight deep residual CNN for fault diagnosis of rotating machinery based on depthwise separable convolutions","volume":"7","author":"Ma","year":"2019","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3127641","article-title":"A novel multiscale lightweight fault diagnosis model based on the idea of adversarial learning","volume":"70","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_28","unstructured":"Ganin, Y., and Lempitsky, V. (2015, January 7\u20139). Unsupervised domain adaptation by backpropagation. Proceedings of the International Conference on Machine Learning PMLR 2015, Lille, France."},{"key":"ref_29","unstructured":"Vaswani, A., Shazeer, N., and Parmar, N. (2017). Attention is all you need. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_31","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.advengsoft.2016.01.008","article-title":"The Whale Optimization Algorithm","volume":"95","author":"Seyedali","year":"2016","journal-title":"Adv. Eng. Software."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"115504","DOI":"10.1016\/j.apenergy.2020.115504","article-title":"State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis","volume":"277","author":"Li","year":"2020","journal-title":"Appl. Energy"},{"key":"ref_34","first-page":"255","article-title":"Deep Domain Confusion: Maximizing for Domain Invariance","volume":"88","author":"Tzeng","year":"2014","journal-title":"Comput. Sci."},{"key":"ref_35","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume":"9","author":"Long","year":"2015","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref_36","unstructured":"Long, M., Zhu, H., and Wang, J. (2017, January 6\u201311). Deep Transfer Learning with Joint Adaptation Networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia. PMLR."},{"key":"ref_37","first-page":"310","article-title":"Research on Fault Diagnosis Method of Wind Turbine Generator Bearings Based on Domain Adaptation","volume":"44","author":"Tian","year":"2023","journal-title":"Acta Energiae Solaris Sin."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"103548","DOI":"10.1016\/j.bspc.2022.103548","article-title":"Deep adaptation network for subject-specific sleep stage classification based on a single-lead ECG","volume":"75","author":"Tang","year":"2022","journal-title":"Bi-Omedical Signal Process. Control"},{"key":"ref_39","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1007\/s10845-020-01600-2","article-title":"Bearing fault diagnosis base on multi-scale CNN and LSTM model","volume":"32","author":"Chen","year":"2021","journal-title":"J. Intell. Manuf."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/16\/5181\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:34:44Z","timestamp":1760110484000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/16\/5181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,10]]},"references-count":40,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["s24165181"],"URL":"https:\/\/doi.org\/10.3390\/s24165181","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,10]]}}}