{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T06:05:12Z","timestamp":1790057112784,"version":"4.0.1"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Predicting the Remaining Useful Life (RUL) of rolling bearings is essential in predictive maintenance. High-frequency vibration signals present a dual-domain challenge, since impulses are most visible in the time domain while harmonics are most visible in time-frequency analysis. Existing approaches are limited by vanishing gradients in LSTM networks and by the quadratic O(L\n                      <jats:sup>2<\/jats:sup>\n                      ) cost of transformer models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We introduce DST-SGR, a Mamba-inspired dual-stream spectro-temporal network in which selective temporal modeling is realized through optimized gated recurrent (GRU-based) state interactions with linear O(L) computational cost in a fully cross-platform PyTorch implementation. A temporal branch detects impulses from raw time-series data while a spectral branch learns harmonic signatures from an STFT spectrogram, and three Spectro-Temporal Interaction Blocks (STIBs) couple the streams through bidirectional cross-gated fusion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the NASA IMS bearing dataset, under a leakage-free, file-level evaluation protocol with piecewise RUL labels, DST-SGR attains a test-set MAE of 0.152 and RMSE of 0.191, with a five-fold file-level cross-validation MAE of 0.128 \u00b1 0.004, and generalizes to IMS Tests 2 and 3 under changed fault locations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The model contains 131,137 trainable parameters and trains in approximately 0.97 h on an NVIDIA RTX 4060 GPU, showing that competitive prognostic accuracy is achievable with modest computational resources.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1857281","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T05:40:04Z","timestamp":1790055604000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DST-SGR: a Mamba-inspired dual-stream spectro-temporal network for remaining useful life prediction of rotating machinery"],"prefix":"10.3389","volume":"9","author":[{"given":"A. S.","family":"Gaurish Kumar","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Madhavan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Dhanalakshmi","sequence":"additional","affiliation":[{"name":"Centre for Cyber Physical Systems, School of Computer Science and Engineering, Vellore Institute of Technology, Chennai","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.ymssp.2004.09.001","article-title":"The spectral kurtosis: a useful tool for characterising non-stationary signals","volume":"20","author":"Antoni","year":"2006","journal-title":"Mech. Syst. Signal Process"},{"key":"B2","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.ymssp.2004.09.002","article-title":"The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines","volume":"20","author":"Antoni","year":"2006","journal-title":"Mech. Syst. Signal Process"},{"key":"B3","author":"Ba","year":"2016","journal-title":"Layer normalization. arXiv"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.3115\/v1\/D14-1179","article-title":"\u201cLearning phrase representations using RNN encoder\u2013decoder for statistical machine translation,\u201d","author":"Cho","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B5","author":"Chung","year":"2014","journal-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv"},{"key":"B6","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.ymssp.2013.01.017","article-title":"Recent advances in time\u2013frequency analysis methods for machinery fault diagnosis: a review with application examples","volume":"38","author":"Feng","year":"2013","journal-title":"Mech. Syst. Signal Process"},{"key":"B7","author":"Gu","year":"2023","journal-title":"Mamba: linear-time sequence modeling with selective state spaces. arXiv"},{"key":"B8","article-title":"\u201cEfficiently modeling long sequences with structured state spaces,\u201d","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR 2022)","author":"Gu","year":"2022"},{"key":"B9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.neucom.2017.02.045","article-title":"A recurrent neural network based health indicator for remaining useful life prediction of bearings","volume":"240","author":"Guo","year":"2017","journal-title":"Neurocomputing"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/PHM.2008.4711422","article-title":"\u201cRecurrent neural networks for remaining useful life estimation,\u201d","author":"Heimes","year":"2008","journal-title":"Proceedings of the IEEE International Conference on Prognostics and Health Management"},{"key":"B11","author":"Hendrycks","year":"2016","journal-title":"Gaussian error linear units (GELUs). arXiv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","article-title":"Robust estimation of a location parameter","volume":"35","author":"Huber","year":"1964","journal-title":"Ann. Math. Stat"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1016\/j.ymssp.2005.09.012","article-title":"A review on machinery diagnostics and prognostics implementing condition-based maintenance","volume":"20","author":"Jardine","year":"2006","journal-title":"Mech. Syst. Signal Process"},{"key":"B15","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1016\/j.ymssp.2017.11.016","article-title":"Machinery health prognostics: a systematic review from data acquisition to RUL prediction","volume":"104","author":"Lei","year":"2018","journal-title":"Mech. Syst. Signal Process"},{"key":"B16","doi-asserted-by":"publisher","first-page":"7762","DOI":"10.1109\/TIE.2015.2455055","article-title":"An improved exponential model for predicting remaining useful life of rolling element bearings","volume":"62","author":"Li","year":"2015","journal-title":"IEEE Trans. Ind. Electron"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ress.2017.11.021","article-title":"Remaining useful life estimation in prognostics using deep convolution neural networks","volume":"172","author":"Li","year":"2018","journal-title":"Reliab. Eng. Syst. Saf"},{"key":"B18","doi-asserted-by":"publisher","first-page":"5761","DOI":"10.1109\/TIP.2025.3607615","article-title":"MambaDiff: mamba-enhanced diffusion model for 3D medical image segmentation","volume":"34","author":"Liu","year":"2025","journal-title":"IEEE Trans. Image Process"},{"key":"B19","article-title":"\u201cDecoupled weight decay regularization,\u201d","author":"Loshchilov","year":"2019","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR 2019"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1007\/s10845-021-01750-x","article-title":"Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit","volume":"32","author":"Mo","year":"2021","journal-title":"J. Intell. Manuf"},{"key":"B21","first-page":"1","article-title":"\u201cPRONOSTIA: an experimental platform for bearings accelerated degradation tests,\u201d","volume-title":"Proceedings of the IEEE International Conference on Prognostics and Health Management","author":"Nectoux","year":"2012"},{"key":"B22","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/S0888-3270(03)00075-X","article-title":"Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography","volume":"18","author":"Peng","year":"2004","journal-title":"Mech. Syst. Signal Process"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1016\/j.jsv.2005.03.007","article-title":"Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics","volume":"289","author":"Qiu","year":"2006","journal-title":"J. Sound Vib"},{"key":"B24","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.ymssp.2010.07.017","article-title":"Rolling element bearing diagnostics\u2014a tutorial","volume":"25","author":"Randall","year":"2011","journal-title":"Mech. Syst. Signal Process"},{"key":"B25","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-319-32025-0_14","article-title":"\u201cDeep convolutional neural network based regression approach for estimation of remaining useful life,\u201d","author":"Sateesh Babu","year":"2016","journal-title":"Database Systems for Advanced Applications (DASFAA 2016)"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/PHM.2008.4711414","article-title":"\u201cDamage propagation modeling for aircraft engine run-to-failure simulation,\u201d","author":"Saxena","year":"2008","journal-title":"Proceedings of the IEEE International Conference on Prognostics and Health Management"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICPHM.2012.6299548","article-title":"\u201cEstimation of remaining useful life of ball bearings using data driven methodologies,\u201d","author":"Sutrisno","year":"2012","journal-title":"Proceedings of the IEEE International Conference on Prognostics and Health Management"},{"key":"B28","first-page":"5998","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Proceding of Advances in Neural Information Processing Systems"},{"key":"B29","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1109\/TR.2018.2882682","article-title":"A hybrid prognostics approach for estimating remaining useful life of rolling element bearings","volume":"69","author":"Wang","year":"2020","journal-title":"IEEE Trans. Reliab"},{"key":"B30","doi-asserted-by":"publisher","first-page":"3591","DOI":"10.1109\/TCE.2025.3572477","article-title":"A collaborative network of Mamba and CNN for lightweight image super-resolution","volume":"71","author":"Wang","year":"2025","journal-title":"IEEE Trans. Consum. Electron"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3572167","article-title":"Integrating Kolmogorov\u2013Arnold network and UNet architecture for reconstruction of 3-D electrical impedance tomography to assess the efficacy of tumor treating fields","volume":"74","author":"Xiao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B32","doi-asserted-by":"publisher","first-page":"8045","DOI":"10.1109\/TCE.2025.3593784","article-title":"HCMNet: a hybrid CNN-Mamba network for breast ultrasound segmentation for consumer assisted diagnosis","volume":"71","author":"Xiong","year":"2025","journal-title":"IEEE Trans. Consum. Electron"},{"key":"B33","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.jmsy.2018.05.011","article-title":"Long short-term memory for machine remaining life prediction","volume":"48","author":"Zhang","year":"2018","journal-title":"J. Manuf. Syst"},{"key":"B34","doi-asserted-by":"publisher","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":"Zhao","year":"2019","journal-title":"Mech. Syst. Signal Process"},{"key":"B35","doi-asserted-by":"crossref","DOI":"10.1109\/ICPHM.2017.7998311","article-title":"\u201cLong short-term memory network for remaining useful life estimation,\u201d","volume-title":"Proceedings of the IEEE International Conference on Prognostics and Health Management","author":"Zheng","year":"2017"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3551581","article-title":"Visually stabilized mamba U-shaped network with strong inductive bias for 3-D brain tumor segmentation","volume":"74","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Instrum. Meas"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1857281\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T05:40:06Z","timestamp":1790055606000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1857281\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":36,"alternative-id":["10.3389\/frai.2026.1857281"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1857281","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"article-number":"1857281"}}