{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:22:53Z","timestamp":1780525373187,"version":"3.54.1"},"reference-count":28,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Shaanxi Province","award":["2019JM-310"],"award-info":[{"award-number":["2019JM-310"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Bearings, as widely employed supporting components, frequently work in challenging working conditions, leading to diverse fault types. Traditional methods for diagnosing bearing faults primarily center on time\u2013frequency analysis, but this often requires expert experience for accurate fault identification. Conversely, intelligent fault recognition and classification methods frequently lack interpretability. To address this challenge, this paper introduces a convolutional neural network with an attention mechanism method, denoted as CBAM-CNN, for bearing fault diagnosis. This approach incorporates an attention mechanism, creating a Convolutional Block Attention Module (CBAM), to enhance the fault feature extraction capability of the network in the time\u2013frequency domain. In addition, the proposed method integrates a weight visualization module known as the Gradient-Weighted Class Activation Map (Grad-CAM), enhancing the interpretability of the convolutional neural network by generating visual heatmaps on fault time\u2013frequency graphs. The experimental results demonstrate that utilizing the dataset employed in this study, the CBAM-CNN achieves an accuracy of 99.81%, outperforming the Base-CNN with enhanced convergence speed. Furthermore, the analysis of attention weights reveals that this method exhibits distinct focus of attention under various fault types and degrees. The interpretability experiments indicate that the CBAM module balances the weight allocation, emphasizing signal frequency distribution rather than amplitude distribution. Consequently, this mitigates the impact of the signal amplitude on the diagnostic model to some extent.<\/jats:p>","DOI":"10.3390\/s24061831","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T03:46:31Z","timestamp":1710301591000},"page":"1831","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Convolutional Neural Network with Attention Mechanism and Visual Vibration Signal Analysis for Bearing Fault Diagnosis"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9861-1173","authenticated-orcid":false,"given":"Qing","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Instrument Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenggang","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110511","DOI":"10.1016\/j.measurement.2021.110511","article-title":"Multiscale inverted residual convolutional neural network for intelligent diagnosis of bearings under variable load condition","volume":"188","author":"Zhao","year":"2022","journal-title":"Measurement"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107050","DOI":"10.1016\/j.ress.2020.107050","article-title":"Multi-scale deep intra-class transfer learning for bearing fault diagnosis","volume":"202","author":"Wang","year":"2020","journal-title":"Reliab. Eng. Syst. Safe."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.isatra.2022.05.042","article-title":"Variational multi-harmonic mode extraction for characterising impulse envelope of bearing failures","volume":"132","author":"Jiang","year":"2023","journal-title":"ISA Trans."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, W., Yang, W., Jin, G., Chen, J., Li, J., Huang, R., and Chen, Z. (2022). Clustering Federated Learning for Bearing Fault Diagnosis in Aerospace Applications with a Self-Attention Mechanism. Aerospace, 9.","DOI":"10.3390\/aerospace9090516"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.engfailanal.2014.05.014","article-title":"Diesel engine crankshaft journal bearings failures: Case study","volume":"44","author":"Aleksandar","year":"2014","journal-title":"Eng. Fail. Anal."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107518","DOI":"10.1016\/j.engfailanal.2023.107518","article-title":"A review of bearing failure Modes, mechanisms and causes","volume":"152","author":"Xu","year":"2023","journal-title":"Eng. Fail. Anal."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107951","DOI":"10.1016\/j.engfailanal.2023.107951","article-title":"Fatigue Failure of High Precision Spindle Bearing under Extreme Service Conditions","volume":"158","author":"Hu","year":"2023","journal-title":"Eng. Fail. Anal."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1016\/S0888-3270(03)00077-3","article-title":"Bearing fault diagnosis based on wavelet transform and fuzzy inference","volume":"18","author":"Lou","year":"2004","journal-title":"Mech. Syst. Signal. Pr."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zheng, X., Lei, Z., Feng, Z., and Chen, L. (2024). Legendre Multiwavelet Transform and Its Application in Bearing Fault Detection. Appl. Sci., 14.","DOI":"10.3390\/app14010219"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.jsv.2017.02.041","article-title":"A New Time\u2013Frequency Method for Identification and Classification of Ball Bearing Faults","volume":"397","author":"Attoui","year":"2017","journal-title":"J. Sound. Vib."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jiang, X., Wu, L., and Ge, M. (2017). A Novel Faults Diagnosis Method for Rolling Element Bearings Based on EWT and Ambiguity Correlation Classifiers. Entropy, 19.","DOI":"10.3390\/e19050231"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.measurement.2017.08.036","article-title":"Early Fault Diagnosis of Bearing and Stator Faults of the Single-Phase Induction Motor Using Acoustic Signals","volume":"113","author":"Glowacz","year":"2018","journal-title":"Measurement"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1018","DOI":"10.1007\/s11668-019-00723-w","article-title":"Rolling Element Bearing Fault Diagnosis Based on Adaptive Local Iterative Filtering Decomposition and Teager\u2013Kaiser Energy Operator","volume":"19","author":"Zhao","year":"2019","journal-title":"J. Fail. Anal. Prev."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1687814018816751","DOI":"10.1177\/1687814018816751","article-title":"Reviews of bearing vibration measurement using fast Fourier transform and enhanced fast Fourier transform algorithms","volume":"11","author":"Lin","year":"2019","journal-title":"Adv. Mech. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Guo, J., Li, Y., and Xiang, J. (2021, January 11\u201313). An improved cepstrum analysis method to diagnose faults in bearings. Proceedings of the 7th International Conference on Condition Monitoring of Machinery in Non-Stationary Operations (CMMNO), Guangzhou, China.","DOI":"10.1109\/CMMNO53328.2021.9467663"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Qin, Y.-F., Fu, X., Li, X.-K., and Li, H.-J. (2024). ADAMS Simulation and HHT Feature Extraction Method for Bearing Faults of Coal Shearer. Processes, 12.","DOI":"10.3390\/pr12010164"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hejazi, S.Z., Packianather, M., and Liu, Y. (2024). A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset. Machines, 12.","DOI":"10.3390\/machines12010044"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lu, L., Wang, W., Kong, D., Zhu, J., and Chen, D. (2023). Fault Diagnosis of Rotating Machinery Using Kernel Neighborhood Preserving Embedding and a Modified Sparse Bayesian Classification Model. Entropy, 25.","DOI":"10.3390\/e25111549"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Liu, H., Mao, W., Xie, X., and Cui, Y. (2023). Rolling Bearing Fault Diagnosis across Operating Conditions Based on Unsupervised Domain Adaptation. Lubricants, 11.","DOI":"10.3390\/lubricants11090383"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, W., Peng, G., Li, C., Chen, Y., and Zhang, Z. (2017). A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals. Sensors, 17.","DOI":"10.20944\/preprints201701.0132.v1"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"92743","DOI":"10.1109\/ACCESS.2020.2995198","article-title":"A Novel Method of Bearing Fault Diagnosis in Time-Frequency Graphs Using InceptionResnet and Deformable Convolution Networks","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"\u0141uczak, D., Brock, S., and Siembab, K. (2023). Cloud Based Fault Diagnosis by Convolutional Neural Network as Time\u2013Frequency RGB Image Recognition of Industrial Machine Vibration with Internet of Things Connectivity. Sensors, 23.","DOI":"10.3390\/s23073755"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"\u0141uczak, D. (2024). Machine Fault Diagnosis through Vibration Analysis: Continuous Wavelet Transform with Complex Morlet Wavelet and Time\u2013Frequency RGB Image Recognition via Convolutional Neural Network. Electronics, 13.","DOI":"10.3390\/electronics13020452"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8807","DOI":"10.1109\/TII.2022.3147828","article-title":"Deep Learning-Based Explainable Fault Diagnosis Model with an Individually Grouped 1-D Convolution for Three-Axis Vibration Signals","volume":"18","author":"Kim","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1109\/TIM.2019.2956332","article-title":"New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN","volume":"69","author":"Wang","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.sigpro.2019.03.019","article-title":"Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism","volume":"161","author":"Li","year":"2019","journal-title":"Signal Process."},{"key":"ref_27","first-page":"108","article-title":"Improved CNN-Based Fault Diagnosis Method for Rolling Bearings under Variable Working Conditions","volume":"55","author":"Zhao","year":"2021","journal-title":"J. Xi\u2019an Jiaotong Univ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"055005","DOI":"10.1088\/1361-6501\/ac41a5","article-title":"Interpretability of deep convolutional neural networks on rolling bearing fault diagnosis","volume":"33","author":"Yang","year":"2022","journal-title":"Meas. Sci. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/6\/1831\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:12:43Z","timestamp":1760105563000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/6\/1831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,13]]},"references-count":28,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["s24061831"],"URL":"https:\/\/doi.org\/10.3390\/s24061831","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,13]]}}}