{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T15:31:19Z","timestamp":1787585479427,"version":"build-2736575974"},"reference-count":39,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010857","name":"Science and Technology Project of the Jiangxi Provincial Department of Education","doi-asserted-by":"publisher","award":["GJJ2200626"],"award-info":[{"award-number":["GJJ2200626"]}],"id":[{"id":"10.13039\/501100010857","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Cross-domain distribution shifts severely degrade the diagnostic performance of rolling bearing models under unseen variable operating scenarios. Single-source domain generalization (SDG) builds fault diagnosis models using only single-source vibration data, which fits the practical limitations of industrial data collection. Existing contrastive learning methods adopt uniform spectral perturbations for data augmentation, which easily corrupt fault harmonic characteristics and require massive, labeled training samples. To tackle these drawbacks, this paper proposes an unsupervised contrastive learning framework named FDACL. An adaptive frequency-domain augmentation (AFA) module equipped with learnable weights is designed to separate fault-critical frequency bands from noise components. Differentiated amplitude perturbations are applied to two categories of spectral signals to generate diverse pseudo-samples while retaining intrinsic fault information. A shared encoder is trained with combined InfoNCE contrast loss and classification loss to learn domain-invariant fault representations. Validations are carried out on three datasets, namely Case Western Reserve University (CWRU), Paderborn University (PU), and the industrial CRRC Qingdao Sifang railway wheelset bearing dataset acquired from physical test benches. FDACL achieves average cross-speed diagnostic accuracies of 92.68% and 77.85% on CWRU and PU, respectively, and maintains competitive performance on the Qingdao Sifang industrial dataset. It outperforms state-of-the-art baselines by 4.23\u20138.71% across all SDG transfer tasks. Ablation experiments and hyperparameter analysis verify the efficacy of the AFA module and contrastive learning scheme, providing an unsupervised diagnostic approach for railway bearings under unknown working conditions.<\/jats:p>","DOI":"10.3390\/s26175349","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T14:49:34Z","timestamp":1787582974000},"page":"5349","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bearing Single-Source Domain Generalization Fault Diagnosis Method Based on Adaptive Frequency-Domain Augmentation and Unsupervised Contrastive Learning"],"prefix":"10.3390","volume":"26","author":[{"given":"Kaisheng","family":"Deng","sequence":"first","affiliation":[{"name":"School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Mechatronics and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"104405","DOI":"10.1016\/j.aei.2026.104405","article-title":"DG-LDM: A Dual-Guided Latent Diffusion Model for Data Augmentation in Imbalanced Fault Diagnosis","volume":"71","author":"Yue","year":"2026","journal-title":"Adv. Eng. Inform."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"116344","DOI":"10.1016\/j.knosys.2026.116344","article-title":"Universal Attack Based Focal Enhancement for Bearing Fault Diagnosis","volume":"348","author":"Jia","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"ref_3","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":"Lei","year":"2020","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1177\/1475921720980718","article-title":"Simulation Data Driven Weakly Supervised Adversarial Domain Adaptation Approach for Intelligent Cross-Machine Fault Diagnosis","volume":"20","author":"Yu","year":"2021","journal-title":"Struct. Health Monit."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107961","DOI":"10.1016\/j.ress.2021.107961","article-title":"Fusing Physics-Based and Deep Learning Models for Prognostics","volume":"217","author":"Kulkarni","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, H., Xiao, Q., Zhao, L., Hu, Y., Liu, H., and Qiao, Y. (2022). Numerical Model Driving Multi-Domain Information Transfer Method for Bearing Fault Diagnosis. Sensors, 22.","DOI":"10.3390\/s22249759"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, C., Huang, C., Zhang, L., Xiang, Z., Xiao, Y., Qian, T., and Liu, J. (2024). Denoising Diffusion Implicit Model Combined with TransNet for Rolling Bearing Fault Diagnosis Under Imbalanced Data. Sensors, 24.","DOI":"10.3390\/s24248009"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1109\/TII.2023.3268750","article-title":"Gaussian Mixture Variational-Based Transformer Domain Adaptation Fault Diagnosis Method and Its Application in Bearing Fault Diagnosis","volume":"20","author":"An","year":"2024","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"114109","DOI":"10.1016\/j.knosys.2025.114109","article-title":"A Comprehensive Survey on Domain Adaptation for Intelligent Fault Diagnosis","volume":"327","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"113655","DOI":"10.1016\/j.engappai.2025.113655","article-title":"Dual-Stage Interpretable Domain Generalization Fault Diagnosis: Integrating Prior Knowledge and Gradient-Weighted Class Activation Mapping","volume":"166","author":"Peng","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103063","DOI":"10.1016\/j.aei.2024.103063","article-title":"Domain Generalization for Rotating Machinery Fault Diagnosis: A Survey","volume":"64","author":"Xiao","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103955","DOI":"10.1016\/j.aei.2025.103955","article-title":"Physics-Guided Counterfactual Causal Learning for Explainable Single-Source Domain Generalization Cross-Machine Bearing Fault Diagnosis","volume":"69","author":"Deng","year":"2026","journal-title":"Adv. Eng. Inform."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"108672","DOI":"10.1016\/j.ress.2022.108672","article-title":"Adaptive Open Set Domain Generalization Network: Learning to Diagnose Unknown Faults under Unknown Working Conditions","volume":"226","author":"Zhao","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"109463","DOI":"10.1016\/j.ress.2023.109463","article-title":"A Novel Domain Generalization Network with Multidomain Specific Auxiliary Classifiers for Machinery Fault Diagnosis under Unseen Working Conditions","volume":"238","author":"Wang","year":"2023","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102262","DOI":"10.1016\/j.aei.2023.102262","article-title":"Imbalanced Domain Generalization via Semantic-Discriminative Augmentation for Intelligent Fault Diagnosis","volume":"59","author":"Zhao","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"109964","DOI":"10.1016\/j.ress.2024.109964","article-title":"Domain Generalization for Cross-Domain Fault Diagnosis: An Application-Oriented Perspective and a Benchmark Study","volume":"245","author":"Zhao","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2909","DOI":"10.1109\/TII.2022.3175018","article-title":"Adversarial Mutual Information-Guided Single Domain Generalization Network for Intelligent Fault Diagnosis","volume":"19","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"122455","DOI":"10.1016\/j.eswa.2023.122455","article-title":"Single Domain Generalizable and Physically Interpretable Bearing Fault Diagnosis for Unseen Working Conditions","volume":"241","author":"Kim","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"109879","DOI":"10.1016\/j.ress.2023.109879","article-title":"Multi-Scale Style Generative and Adversarial Contrastive Networks for Single Domain Generalization Fault Diagnosis","volume":"243","author":"Wang","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"113286","DOI":"10.1016\/j.ymssp.2025.113286","article-title":"Discrete Wavelet Convolutional Network with Cross-Contrast Perturbation for Single Domain Generalization in Fault Diagnosis","volume":"239","author":"Wei","year":"2025","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104227","DOI":"10.1016\/j.aei.2025.104227","article-title":"Causal Feature-Aware Dynamic Graph Neural Network for Open-Set Domain Generalization Diagnosis in Multi-Sensor Systems","volume":"70","author":"Zhang","year":"2026","journal-title":"Adv. Eng. Inform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"7641","DOI":"10.1109\/TII.2024.3359409","article-title":"Debiased Contrastive Learning for Time-Series Representation Learning and Fault Detection","volume":"20","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"15604","DOI":"10.1109\/TPAMI.2023.3308189","article-title":"Self-Supervised Contrastive Representation Learning for Semi-Supervised Time-Series Classification","volume":"45","author":"Eldele","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8980","DOI":"10.1609\/aaai.v36i8.20881","article-title":"TS2Vec: Towards Universal Representation of Time Series","volume":"Volume 36","author":"Yue","year":"2022","journal-title":"Proceedings of the 36th AAAI Conference on Artificial Intelligence"},{"key":"ref_25","unstructured":"Tonekaboni, S., Eytan, D., and Goldenberg, A. (2021). Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9153","DOI":"10.1609\/aaai.v37i8.26098","article-title":"MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series","volume":"Volume 37","author":"Meng","year":"2023","journal-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107043","DOI":"10.1016\/j.ymssp.2020.107043","article-title":"A Multi-Stage Semi-Supervised Learning Approach for Intelligent Fault Diagnosis of Rolling Bearing Using Data Augmentation and Metric Learning","volume":"146","author":"Yu","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2031","DOI":"10.1214\/19-AOS1876","article-title":"Empirical Risk Minimization and Complexity of Dynamical Models","volume":"48","author":"McGoff","year":"2020","journal-title":"Ann. Stat."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6785","DOI":"10.1109\/TMM.2024.3355651","article-title":"Improving Deepfake Detection Generalization by Invariant Risk Minimization","volume":"26","author":"Yin","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"43255","DOI":"10.1038\/srep43255","article-title":"Evidence for Risk Extrapolation in Decision Making by Tadpoles","volume":"7","author":"Crane","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2022.3154000","article-title":"Conditional Contrastive Domain Generalization for Fault Diagnosis","volume":"71","author":"Ragab","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1109\/TMM.2023.3294002","article-title":"Style-Agnostic Representation Learning for Visible-Infrared Person Re-Identification","volume":"26","author":"Wu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"276105","DOI":"10.1088\/1361-6501\/ae804c","article-title":"Deep Imbalanced Adversarial Domain Adaptation Network for Cross Domain Fault Diagnosis","volume":"37","author":"Zhong","year":"2026","journal-title":"Meas. Sci. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1016\/j.measurement.2006.10.010","article-title":"A Fault Diagnosis Approach for Roller Bearing Based on IMF Envelope Spectrum and SVM","volume":"40","author":"Yang","year":"2007","journal-title":"Measurement"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1109\/TR.2026.3691333","article-title":"Targeted Augmentation Domain-Mixed Network for Single-Source Domain Generalization Fault Diagnosis","volume":"75","author":"Ren","year":"2026","journal-title":"IEEE Trans. Reliab."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"276004","DOI":"10.1088\/1361-6501\/ae80f1","article-title":"Attention-Guided Wavelet Packet Energy Autoencoder with Distribution Consistency for Single-Source Domain Generalization Fault Diagnosis","volume":"37","author":"Feng","year":"2026","journal-title":"Meas. Sci. Technol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"104169","DOI":"10.1016\/j.compind.2024.104169","article-title":"Prior Knowledge Embedding Convolutional Autoencoder: A Single-Source Domain Generalized Fault Diagnosis Framework under Small Samples","volume":"164","author":"Lu","year":"2025","journal-title":"Comput. Ind."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"25447","DOI":"10.1038\/s41598-024-75088-8","article-title":"A Domain Generalization Network for Imbalanced Machinery Fault Diagnosis","volume":"14","author":"Guo","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"045264","DOI":"10.1088\/2631-8695\/ad9fd3","article-title":"Dynamic Feature Separation Domain Generalization for Bearing Fault Diagnosis","volume":"6","author":"Cai","year":"2024","journal-title":"Eng. Res. Express"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5349\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T14:52:22Z","timestamp":1787583142000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5349"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":39,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26175349"],"URL":"https:\/\/doi.org\/10.3390\/s26175349","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]}}}