{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T04:43:04Z","timestamp":1777264984664,"version":"3.51.4"},"reference-count":37,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Talent Program of Chengdu Technological University","award":["2025RC048"],"award-info":[{"award-number":["2025RC048"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Accurate classification of spindle rotational errors is critical for ensuring machining precision and operational reliability of CNC machine tools. However, existing methods face challenges in extracting discriminative feature information from vibration signals due to small inter-class differences and complex electromechanical interference. This paper proposes a novel deep learning model, MFAFENet, based on multi-sensor collaboration and multi-scale feature information adaptive fusion. Vibration signals from three mounting positions are transformed into time-frequency information representations via Short-time Fourier Transform. The proposed network adaptively fuses multi-scale feature information from parallel branches with different kernel sizes through a branch attention mechanism. An efficient channel attention module is then incorporated to recalibrate channel-wise feature responses. The cross-entropy loss function is employed to optimize the network parameters during training. Experiments on a spindle reliability test bench demonstrate that MFAFENet achieves 93.37% average test accuracy, outperforming other comparative methods. Ablation and comparative studies confirm the effectiveness of each module and the clear advantage of adaptive fusion over fixed-weight multi-scale methods. Multi-sensor fusion further improves accuracy by 7.23% over the best single-sensor setup. The proposed method establishes an effective end-to-end mapping between vibration signals and rotational errors, providing a promising solution for high-precision spindle condition monitoring.<\/jats:p>","DOI":"10.3390\/e28040475","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:53:23Z","timestamp":1776696803000},"page":"475","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MFAFENet: A Multi-Sensor Collaborative and Multi-Scale Feature Information Adaptive Fusion Network for Spindle Rotational Error Classification in CNC Machine Tools"],"prefix":"10.3390","volume":"28","author":[{"given":"Fei","family":"Wang","sequence":"first","affiliation":[{"name":"School of Low-Altitude Technology and Transportation, Chengdu Technological University, Yibin 644012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Song","sequence":"additional","affiliation":[{"name":"School of Low-Altitude Technology and Transportation, Chengdu Technological University, Yibin 644012, China"},{"name":"School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Chengdu Technological University, Chengdu 611730, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Low-Altitude Technology and Transportation, Chengdu Technological University, Yibin 644012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Low-Altitude Technology and Transportation, Chengdu Technological University, Yibin 644012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"045415","DOI":"10.1088\/2631-8695\/ad8ac1","article-title":"Positioning errors and accuracy of CNC machine tools","volume":"6","author":"Younes","year":"2024","journal-title":"Eng. Res. Express"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1016\/j.measurement.2018.05.011","article-title":"Analysis of tool deflection errors in precision CNC end milling of aerospace Aluminum 6061-T6 alloy","volume":"125","author":"Nghiep","year":"2018","journal-title":"Measurement"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"022021","DOI":"10.1088\/1757-899X\/569\/2\/022021","article-title":"Structural Design and CNC Machining of Integral Impeller for Automotive Turbocharger","volume":"569","author":"Guo","year":"2019","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.measurement.2015.09.052","article-title":"Optimisation of parameters affecting surface roughness of Co28Cr6Mo medical material during CNC lathe machining by using the Taguchi and RSM methods","volume":"78","author":"Ince","year":"2016","journal-title":"Measurement"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Song, L., and Tan, J. (2024). Rotation error prediction of CNC spindle based on short-time Fourier transform of vibration sensor signals and improved weighted residual network. Sensors, 24.","DOI":"10.3390\/s24134244"},{"key":"ref_6","first-page":"15","article-title":"Measurementand research oftheelectric spindlerotation error","volume":"31","author":"Jia","year":"2015","journal-title":"J. Shanxi Univ. Technol. (Nat. Sci. Ed.)"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1016\/j.measurement.2007.06.002","article-title":"A method for evaluating spindle rotation errors of machine tools using a laser interferometer","volume":"41","author":"Castro","year":"2008","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s12206-016-1210-6","article-title":"Multiscale singular value manifold for rotating machinery fault diagnosis","volume":"31","author":"Feng","year":"2017","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_9","unstructured":"Jiang, G., Liu, H., Kang, H., Hu, C., Zhou, Y., Cao, Z., Ouyang, Z., Li, W., Duan, L., and Zeng, H. (2024). Study on Detection Method of Spindle Rotation Error Considering System Vibration. J. Vib. Meas. Diagn., 44."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"240","DOI":"10.3901\/JME.2020.17.240","article-title":"Dynamic prediction method for machine tool spindle rotational accuracy under cutting condition","volume":"56","author":"Kang","year":"2020","journal-title":"J. Mech. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TMECH.2020.3002342","article-title":"Four-point method in the measurement and separation of spindle rotation error","volume":"26","author":"Liu","year":"2020","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"109470","DOI":"10.1016\/j.measurement.2021.109470","article-title":"Sparsity adaptive matching pursuit and spectrum line interpolation method for measuring radial and axial error motions of spindle rotation","volume":"182","author":"Kong","year":"2021","journal-title":"Measurement"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"108233","DOI":"10.1016\/j.measurement.2020.108233","article-title":"Rotation error modeling and compensation of spindle based on Clarke transformation in straightness error measurement of regular hexagon section shaft","volume":"166","author":"Kong","year":"2020","journal-title":"Measurement"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zheng, J., Yu, H., Zhao, R., Shi, W., and Wang, J. (2021). Rotation accuracy analysis of aerostatic spindle considering shaft\u2019s roundness and cylindricity. Appl. Sci., 11.","DOI":"10.3390\/app11177912"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zheng, J., Yu, H., Chen, T., Zhang, K., and Dou, G. (2022). Evaluation of the influence of shaft shape errors on the rotation accuracy of aerostatic spindle\u2014Part 1: Modeling. Electronics, 11.","DOI":"10.3390\/electronics11091304"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1177\/1077546319845429","article-title":"Analysis of aerostatic spindle radial vibration error based on microscale nonlinear dynamic characteristics","volume":"25","author":"Chen","year":"2019","journal-title":"J. Vib. Control"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103694","DOI":"10.1016\/j.aei.2025.103694","article-title":"Multiscale calibration networks with pseudo label for bearing fault diagnosis under class-imbalanced data and multi-rate sampling scenarios","volume":"68","author":"Liu","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, C., Lian, Y., and Luo, B. (2025). Research on Bearing Fault Diagnosis Based on VMD-RCMWPE Feature Extraction and WOA-SVM-Optimized Multidataset Fusion. Sensors, 25.","DOI":"10.3390\/s25165139"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ymssp.2016.04.017","article-title":"Normalization of vibration signals generated under highly varying speed and load with application to signal separation","volume":"82","author":"Urbanek","year":"2017","journal-title":"Mech. Syst. Signal Proc."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108490","DOI":"10.1016\/j.measurement.2020.108490","article-title":"A novel denoising method for vibration signal of hob spindle based on EEMD and grey theory","volume":"169","author":"Jia","year":"2021","journal-title":"Measurement"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Song, L., Wu, J., Wang, L., Chen, G., Shi, Y., and Liu, Z. (2023). Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network. Entropy, 25.","DOI":"10.3390\/e25050798"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ren, J., Jin, W., Wu, Y., Sun, Z., and Li, L. (2023). Research on performance degradation estimation of key components of high-speed train bogie based on multi-task learning. Entropy, 25.","DOI":"10.3390\/e25040696"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1360\/SST-2019-0363","article-title":"A method for predicting spindle rotation accuracy using vibration","volume":"50","author":"Chen","year":"2020","journal-title":"Sci. Sin. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Song, L., Wang, L.P., Wu, J., Liang, J.H., and Liu, Z.G. (2021). Integrating physics and data driven cyber-physical system for condition monitoring of critical transmission components in smart production line. Appl. Sci., 11.","DOI":"10.3390\/app11198967"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"021102","DOI":"10.1115\/1.4064642","article-title":"Indirect prediction of spindle rotation error through vibration signal based on supervised local mean decomposition filter fusion and Bi-LSTM classification network","volume":"10","author":"Liang","year":"2024","journal-title":"ASCE-ASME J. Risk Uncertain. Eng. Syst. Part B Mech. Eng."},{"key":"ref_26","first-page":"439","article-title":"Reliability analysis based on cyber-physical system and digital twin","volume":"52","author":"Song","year":"2022","journal-title":"J. Jilin Univ. (Eng. Technol. Ed.)"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4949","DOI":"10.1109\/TII.2020.2967557","article-title":"Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition","volume":"16","author":"Peng","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Song, L., Zhao, Y., He, J., Wang, S., Zhong, B., and Wang, F. (2025). MAJATNet: A Lightweight Multi-Scale Attention Joint Adaptive Adversarial Transfer Network for Bearing Unsupervised Cross-Domain Fault Diagnosis. Entropy, 27.","DOI":"10.3390\/e27101011"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"111782","DOI":"10.1016\/j.measurement.2022.111782","article-title":"A remaining useful life prediction method based on time\u2013frequency images of the mechanical vibration signals","volume":"202","author":"Du","year":"2022","journal-title":"Measurement"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., and Yang, J. (2020). Selective Kernel Networks. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_33","first-page":"1107","article-title":"Load spectrum compilation for machining center spindles based on S-shaped specimens","volume":"58","author":"Chen","year":"2018","journal-title":"J. Tsinghua Univ. (Sci. Technol.)"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.isatra.2020.08.010","article-title":"Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study","volume":"107","author":"Zhao","year":"2020","journal-title":"ISA Trans."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"121338","DOI":"10.1016\/j.eswa.2023.121338","article-title":"LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention","volume":"237","author":"Yan","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/475\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T04:11:59Z","timestamp":1777263119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/475"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":37,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["e28040475"],"URL":"https:\/\/doi.org\/10.3390\/e28040475","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]}}}