{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T05:19:38Z","timestamp":1793683178658,"version":"4.5.1"},"reference-count":29,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:00:00Z","timestamp":1789171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Bearing fault diagnosis increasingly relies on multiple sensors, since compound or multi-location faults can produce signatures that are only partially captured by a single sensor. The decision-level fusion (DLF) of independently trained models offers a practical way to combine such complementary information, yet systematic comparisons across DLF techniques remain scarce, particularly for measurements from different sensor locations. This paper benchmarks six DLF strategies, i.e, Max, Average, Majority Voting, Weighted Sum, Dempster\u2013Shafer, and Stacking, on a dual-branch one-dimensional convolutional neural network (1D-CNN) with each branch trained end-to-end on vibration signals from a distinct bearing location. On a two-sensor test bench covering seven health conditions, all methods exceed 99.7% accuracy on clean signals, while Dempster\u2013Shafer fusion proves markedly more robust under noise, retaining up to 84% accuracy at a 5 dB signal-to-noise ratio (SNR). A conflict-coefficient analysis further provides an interpretable account of when fusion succeeds, linking performance to the confidence complementarity between branches.<\/jats:p>","DOI":"10.3390\/e28091020","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:10:23Z","timestamp":1789373423000},"page":"1020","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparative Study of Decision-Level Fusion Strategies for Multi-Sensor CNN-Based Bearing Fault Diagnosis"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9803-1977","authenticated-orcid":false,"given":"Iman","family":"Makrouf","sequence":"first","affiliation":[{"name":"Digital Engineering for Leading Technology and Automation, National Higher School of Arts and Crafts Casablanca, Hassan II University of Casablanca, Casablanca 20670, Morocco"},{"name":"Complex Systems and Interactions, Ecole Centrale Casablanca, Bouskoura 27182, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0820-8933","authenticated-orcid":false,"given":"Mourad","family":"Zegrari","sequence":"additional","affiliation":[{"name":"Digital Engineering for Leading Technology and Automation, National Higher School of Arts and Crafts Casablanca, Hassan II University of Casablanca, Casablanca 20670, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1651-0668","authenticated-orcid":false,"given":"Khalid","family":"Dahi","sequence":"additional","affiliation":[{"name":"Complex Systems and Interactions, Ecole Centrale Casablanca, Bouskoura 27182, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4421-6175","authenticated-orcid":false,"given":"Demba","family":"Diallo","sequence":"additional","affiliation":[{"name":"GeePs, CNRS, CentraleSup\u00e9lec, Universit\u00e9 Paris-Saclay, 91190 Gif-sur-Yvette, France"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Meryem","family":"Abtane","sequence":"additional","affiliation":[{"name":"Complex Systems and Interactions, Ecole Centrale Casablanca, Bouskoura 27182, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Ilias","family":"Ouachtouk","sequence":"additional","affiliation":[{"name":"Digital Engineering for Leading Technology and Automation, National Higher School of Arts and Crafts Casablanca, Hassan II University of Casablanca, Casablanca 20670, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103405","DOI":"10.1016\/j.aei.2025.103405","article-title":"Bearing fault diagnosis method based on multi-level information fusion","volume":"66","author":"Wang","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_2","first-page":"512","article-title":"Advanced Model of Squirrel Cage Induction Machine for Broken Rotor Bars Fault Using Multi Indicators","volume":"14","author":"Ouachtouk","year":"2016","journal-title":"Adv. Electr. Electron. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Dahi, K., Elhani, S., Guedira, S., Sadiki, L., and Ouachtouk, I. (2015, January 25\u201327). High-resolution spectral analysis method to identify rotor faults in WRIM using Neutral Voltage. Proceedings of the 2015 International Conference on Electrical and Information Technologies (ICEIT), Marrakech, Morocco.","DOI":"10.1109\/EITech.2015.7162988"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"106908","DOI":"10.1016\/j.ymssp.2020.106908","article-title":"Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review","volume":"144","author":"Gangsar","year":"2020","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1177\/14759217221095067","article-title":"A novel spectral coherence-based envelope spectrum for railway axle-box bearing damage identification","volume":"22","author":"Chen","year":"2023","journal-title":"Struct. Health Monit."},{"key":"ref_6","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_7","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, X., Song, D., Zheng, Z., and Li, W. (2025). A Novel Bearing Fault Diagnosis Method Based on Improved Convolutional Neural Network and Multi-Sensor Fusion. Machines, 13.","DOI":"10.3390\/machines13030216"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"117755","DOI":"10.1016\/j.measurement.2025.117755","article-title":"A novel method for untrained detection of compound fault in rolling bearing via fast Fourier Transform-Transformer model","volume":"253","author":"Tang","year":"2025","journal-title":"Measurement"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4711","DOI":"10.1007\/s10462-022-10243-z","article-title":"A scoping review on multi-fault diagnosis of industrial rotating machines using multi-sensor data fusion","volume":"56","author":"Gawde","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"114457","DOI":"10.1016\/j.solener.2026.114457","article-title":"A comprehensive review of fusion-based methods applied to photovoltaic fault diagnosis","volume":"309","author":"Lu","year":"2026","journal-title":"Sol. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"110664","DOI":"10.1016\/j.ymssp.2023.110664","article-title":"Machinery multi-sensor fault diagnosis based on adaptive multivariate feature mode decomposition and multi-attention fusion residual convolutional neural network","volume":"202","author":"Yan","year":"2023","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"101025","DOI":"10.1016\/j.prime.2025.101025","article-title":"A novel framework for multi-sensor data fusion in bearing fault diagnosis using continuous wavelet transform and transfer learning","volume":"13","author":"Makrouf","year":"2025","journal-title":"e-Prime-Adv. Electr. Eng. Electron. Energy"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104000","DOI":"10.1016\/j.inffus.2025.104000","article-title":"MSIF-Convformer: A novel end-to-end fault diagnosis framework with multi-source sensors under strong noise","volume":"129","author":"Li","year":"2026","journal-title":"Inf. Fusion"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"125214","DOI":"10.1016\/j.eswa.2024.125214","article-title":"MRCFN: A multi-sensor residual convolutional fusion network for intelligent fault diagnosis of bearings in noisy and small sample scenarios","volume":"259","author":"Ye","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_15","first-page":"100854","article-title":"Collaborative and trustworthy fault diagnosis for mechanical systems based on probabilistic neural network with decision-level information fusion","volume":"46","author":"Xu","year":"2025","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1007\/s11431-021-1904-7","article-title":"Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals","volume":"65","author":"Chao","year":"2021","journal-title":"Sci. China Technol. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"34766","DOI":"10.1109\/JSEN.2024.3416958","article-title":"A Novel Collaborative Bearing Fault Diagnosis Method Based on Multisignal Decision-Level Dynamically Enhanced Fusion","volume":"24","author":"Xu","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"122472","DOI":"10.1016\/j.engstruct.2026.122472","article-title":"Multi-channel convolutional neural network and decision-level fusion for multi-part cover fault diagnosis","volume":"357","author":"Chen","year":"2026","journal-title":"Eng. Struct."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, L., Zhang, X., Wang, P., Chen, C., Ma, T., and Gao, S. (2025). A Bearing Fault Diagnosis Method for Multi-Sensors Using Cloud Model and Dempster\u2013Shafer Evidence Fusion. Appl. Sci., 15.","DOI":"10.3390\/app152111302"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"015324","DOI":"10.1088\/2631-8695\/ada86f","article-title":"Fault diagnosis of rolling bearing based on improved stacking ensemble learning","volume":"7","author":"Wang","year":"2025","journal-title":"Eng. Res. Express"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/s42417-024-01405-0","article-title":"Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis","volume":"12","author":"Alhams","year":"2024","journal-title":"J. Vib. Eng. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"118807","DOI":"10.1016\/j.oceaneng.2024.118807","article-title":"A confidence-guided DS fault diagnosis method for tidal stream turbines blade","volume":"311","author":"Xu","year":"2024","journal-title":"Ocean. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"144747","DOI":"10.1109\/ACCESS.2023.3344776","article-title":"Graph Regularization Methods in Soft Detector Fusion","volume":"11","author":"Salazar","year":"2023","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102218","DOI":"10.1016\/j.inffus.2023.102218","article-title":"Multimodal Emotion Recognition with Deep Learning: Advancements, challenges, and future directions","volume":"105","author":"Geetha","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"10693","DOI":"10.1038\/s41598-025-93857-x","article-title":"Investigation on coaxial pseudo-fault characteristics induced by the outer ring defect in the single-sided axle-box bearing of wheelset in urban rail vehicles","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"144082","DOI":"10.1109\/ACCESS.2024.3433513","article-title":"State-of-the-Art in 1D Convolutional Neural Networks: A Survey","volume":"12","author":"Ige","year":"2024","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"114658","DOI":"10.1016\/j.measurement.2024.114658","article-title":"Multi-Sensor data fusion in intelligent fault diagnosis of rotating machines: A comprehensive review","volume":"232","author":"Kibrete","year":"2024","journal-title":"Measurement"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3044","DOI":"10.1109\/TII.2025.3642387","article-title":"Multimodal Fault Diagnosis of Rotating Machinery Using Dynamic Fusion and Improved DS Theory","volume":"22","author":"Yang","year":"2026","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"112889","DOI":"10.1016\/j.asoc.2025.112889","article-title":"An ensemble deep learning network based on 2D convolutional neural network and 1D LSTM with self-attention for bearing fault diagnosis","volume":"172","author":"Wang","year":"2025","journal-title":"Appl. Soft Comput."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/9\/1020\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:11:07Z","timestamp":1789373467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/9\/1020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,12]]},"references-count":29,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["e28091020"],"URL":"https:\/\/doi.org\/10.3390\/e28091020","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,12]]}}}