{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:56:13Z","timestamp":1792803373323,"version":"4.5.0"},"reference-count":66,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018950","name":"\u0110\u1ea1i h\u1ecdc T\u00f4n \u0110\u1ee9c Th\u1eafng","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is critical for safe, reliable Battery Health Management in diverse operating conditions. Existing RUL models often fail to generalize when test data diverge from the training distribution. To address this, we introduce HybridoNet-Adapt, a domain-adaptive RUL prediction framework that explicitly bridges the gap between labeled source and unlabeled target domains. During training, we minimize the Maximum Mean Discrepancy (MMD) between feature distributions to learn domain-invariant representations. Simultaneously, we employ two parallel predictors\u2014one tailored to the source domain and one to the target domain\u2014and balance their outputs via two learnable trade-off parameters, enabling the model to dynamically weight domain-specific insights. Our architecture couples this adaptation strategy with LSTM, multi-head attention, and Neural ODE blocks for deep temporal feature extraction, but its core novelty lies in the MMD-based alignment and hybrid prediction mechanism. On two large, publicly available battery datasets, HybridoNet-Adapt consistently outperforms non-adaptive baselines (Structural Pruning, Multi-Time Scale Feature Extraction Hybrid model, XGBoost, Elastic Net), archiving an RMSE reduction of up to 152 cycles under domain shifts. These results demonstrate that incorporating domain adaptation into RUL modeling substantially enhances robustness and real-world applicability.<\/jats:p>","DOI":"10.1371\/journal.pone.0335066","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:41:55Z","timestamp":1761932515000},"page":"e0335066","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["HybridoNet-Adapt: A domain-adapted framework for accurate lithium-ion battery RUL prediction"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0969-1807","authenticated-orcid":true,"given":"Khoa","family":"Tran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bao","family":"Huynh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tri","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lam","family":"Pham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vy-Rin","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duong","family":"Tran Anh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2172-8231","authenticated-orcid":true,"given":"Hung-Cuong","family":"Trinh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"issue":"4","key":"pone.0335066.ref001","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1021\/ja3091438","article-title":"The Li-ion rechargeable battery: a perspective","volume":"135","author":"JB Goodenough","year":"2013","journal-title":"J Am Chem Soc"},{"key":"pone.0335066.ref002","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1016\/j.jechem.2024.01.055","article-title":"Managing the surge: a comprehensive review of the entire disposal framework for retired lithium-ion batteries from electric vehicles","volume":"92","author":"R Guo","year":"2024","journal-title":"Journal of Energy Chemistry"},{"issue":"6058","key":"pone.0335066.ref003","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1126\/science.1212741","article-title":"Electrical energy storage for the grid: a battery of choices","volume":"334","author":"B Dunn","year":"2011","journal-title":"Science"},{"key":"pone.0335066.ref004","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.jechem.2023.08.037","article-title":"Patent-based technological developments and surfactants application of lithium-ion batteries fire-extinguishing agent","volume":"88","author":"J Zhang","year":"2024","journal-title":"Journal of Energy Chemistry"},{"issue":"1","key":"pone.0335066.ref005","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1038\/nchem.2085","article-title":"Towards greener and more sustainable batteries for electrical energy storage","volume":"7","author":"D Larcher","year":"2015","journal-title":"Nat Chem"},{"key":"pone.0335066.ref006","unstructured":"Pillot C. The rechargeable battery market and main trends 2018 \u20132030. In: 36th annual international battery seminar & exhibit. 2019. p. 35."},{"issue":"1","key":"pone.0335066.ref007","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1002\/er.1956","article-title":"Thermal management of lithium-ion batteries for electric vehicles","volume":"37","author":"G Karimi","year":"2012","journal-title":"Int J Energy Res"},{"key":"pone.0335066.ref008","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.jechem.2023.08.040","article-title":"Research on the impact of high-temperature aging on the thermal safety of lithium-ion batteries","volume":"87","author":"G Zhang","year":"2023","journal-title":"Journal of Energy Chemistry"},{"key":"pone.0335066.ref009","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1016\/j.jechem.2024.04.005","article-title":"Exploring impedance spectrum for lithium-ion batteries diagnosis and prognosis: a comprehensive review","volume":"95","author":"X Du","year":"2024","journal-title":"Journal of Energy Chemistry"},{"key":"pone.0335066.ref010","doi-asserted-by":"crossref","first-page":"102440","DOI":"10.1016\/j.est.2021.102440","article-title":"State of charge and state of energy estimation for lithium-ion batteries based on a long short-term memory neural network","volume":"37","author":"L Ma","year":"2021","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref011","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.est.2016.03.003","article-title":"Accuracy improvement of SOC estimation in lithium-ion batteries","volume":"6","author":"MA Awadallah","year":"2016","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref012","doi-asserted-by":"crossref","first-page":"101459","DOI":"10.1016\/j.est.2020.101459","article-title":"Online joint-prediction of multi-forward-step battery SOC using LSTM neural networks and multiple linear regression for real-world electric vehicles","volume":"30","author":"J Hong","year":"2020","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref013","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.jechem.2022.06.049","article-title":"A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries","volume":"74","author":"K Luo","year":"2022","journal-title":"Journal of Energy Chemistry"},{"key":"pone.0335066.ref014","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.jechem.2023.03.026","article-title":"The development of machine learning-based remaining useful life prediction for lithium-ion batteries","volume":"82","author":"X Li","year":"2023","journal-title":"Journal of Energy Chemistry"},{"key":"pone.0335066.ref015","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1016\/j.jechem.2023.12.043","article-title":"Accurate and efficient remaining useful life prediction of batteries enabled by physics-informed machine learning","volume":"91","author":"L Ma","year":"2024","journal-title":"Journal of Energy Chemistry"},{"issue":"5","key":"pone.0335066.ref016","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1038\/s41560-019-0356-8","article-title":"Data-driven prediction of battery cycle life before capacity degradation","volume":"4","author":"KA Severson","year":"2019","journal-title":"Nat Energy"},{"key":"pone.0335066.ref017","doi-asserted-by":"crossref","first-page":"232477","DOI":"10.1016\/j.jpowsour.2022.232477","article-title":"Capacity and internal resistance of lithium-ion batteries: full degradation curve prediction from Voltage response at constant Current at discharge","volume":"556","author":"R Ibraheem","year":"2023","journal-title":"Journal of Power Sources"},{"issue":"6","key":"pone.0335066.ref018","article-title":"Early prediction of remaining useful life for grid-scale battery energy storage system","volume":"147","author":"D Lin","year":"2021","journal-title":"J Energy Eng"},{"key":"pone.0335066.ref019","doi-asserted-by":"crossref","first-page":"104901","DOI":"10.1016\/j.est.2022.104901","article-title":"Lithium-ion battery capacity and remaining useful life prediction using board learning system and long short-term memory neural network","volume":"52","author":"S Zhao","year":"2022","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref020","doi-asserted-by":"crossref","first-page":"110012","DOI":"10.1016\/j.knosys.2022.110012","article-title":"A two-stage integrated method for early prediction of remaining useful life of lithium-ion batteries","volume":"259","author":"G Ma","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"pone.0335066.ref021","doi-asserted-by":"crossref","first-page":"106457","DOI":"10.1016\/j.est.2022.106457","article-title":"Lithium-ion battery remaining useful life prediction using a two-phase degradation model with a dynamic change point","volume":"59","author":"R Wang","year":"2023","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref022","doi-asserted-by":"crossref","first-page":"121043","DOI":"10.1016\/j.apenergy.2023.121043","article-title":"Joint nonlinear-drift-driven Wiener process-Markov chain degradation switching model for adaptive online predicting lithium-ion battery remaining useful life","volume":"341","author":"Y Zhang","year":"2023","journal-title":"Applied Energy"},{"key":"pone.0335066.ref023","doi-asserted-by":"crossref","first-page":"108427","DOI":"10.1016\/j.est.2023.108427","article-title":"Historical data-independent remaining useful life prediction method based on dual-input deep learning neural network","volume":"72","author":"J Xia","year":"2023","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref024","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: a survey","volume":"151","author":"S Kiranyaz","year":"2021","journal-title":"Mechanical Systems and Signal Processing"},{"key":"pone.0335066.ref025","doi-asserted-by":"crossref","unstructured":"Javid AM, Das S, Skoglund M, Chatterjee S. A ReLU dense layer to improve the performance of neural networks. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2021. p. 2810\u20134. https:\/\/doi.org\/10.1109\/icassp39728.2021.9414269","DOI":"10.1109\/ICASSP39728.2021.9414269"},{"key":"pone.0335066.ref026","doi-asserted-by":"crossref","unstructured":"Graves A, Graves A. Long short-term memory. Supervised sequence labelling with recurrent neural networks. 2012. p. 37\u201345.","DOI":"10.1007\/978-3-642-24797-2_4"},{"issue":"9","key":"pone.0335066.ref027","doi-asserted-by":"crossref","first-page":"2330","DOI":"10.4249\/scholarpedia.2330","article-title":"Echo state network","volume":"2","author":"H Jaeger","year":"2007","journal-title":"Scholarpedia"},{"key":"pone.0335066.ref028","doi-asserted-by":"crossref","first-page":"123563","DOI":"10.1016\/j.eswa.2024.123563","article-title":"A hybrid approach based on deep neural network and double exponential model for remaining useful life prediction","volume":"249","author":"J Liang","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"10","key":"pone.0335066.ref029","doi-asserted-by":"crossref","first-page":"4083","DOI":"10.1039\/D2EE01676A","article-title":"Real-time personalized health status prediction of lithium-ion batteries using deep transfer learning","volume":"15","author":"G Ma","year":"2022","journal-title":"Energy Environ Sci"},{"issue":"1","key":"pone.0335066.ref030","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1038\/s41467-022-29837-w","article-title":"Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation","volume":"13","author":"J Zhu","year":"2022","journal-title":"Nat Commun"},{"key":"pone.0335066.ref031","doi-asserted-by":"crossref","first-page":"230975","DOI":"10.1016\/j.jpowsour.2022.230975","article-title":"A transferable lithium-ion battery remaining useful life prediction method from cycle-consistency of degradation trend","volume":"521","author":"F Wang","year":"2022","journal-title":"Journal of Power Sources"},{"issue":"7795","key":"pone.0335066.ref032","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1038\/s41586-020-1994-5","article-title":"Closed-loop optimization of fast-charging protocols for batteries with machine learning","volume":"578","author":"PM Attia","year":"2020","journal-title":"Nature"},{"key":"pone.0335066.ref033","doi-asserted-by":"crossref","first-page":"87178","DOI":"10.1109\/ACCESS.2019.2925468","article-title":"A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery","volume":"7","author":"J Qu","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0335066.ref034","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.microrel.2016.07.151","article-title":"Lithium-ion batteries remaining useful life prediction based on a mixture of empirical mode decomposition and ARIMA model","volume":"65","author":"Y Zhou","year":"2016","journal-title":"Microelectronics Reliability"},{"key":"pone.0335066.ref035","unstructured":"Saha B, Goebel K. Battery data set. NASA AMES prognostics data repository. 2007."},{"key":"pone.0335066.ref036","doi-asserted-by":"crossref","first-page":"122555","DOI":"10.1016\/j.apenergy.2023.122555","article-title":"A hybrid deep learning approach for remaining useful life prediction of lithium-ion batteries based on discharging fragments","volume":"358","author":"Y Liu","year":"2024","journal-title":"Applied Energy"},{"key":"pone.0335066.ref037","doi-asserted-by":"crossref","first-page":"39","DOI":"10.2741\/S357","volume":"5","author":"ASS Vasan","year":"2013","journal-title":"Frontiers in bioscience"},{"key":"pone.0335066.ref038","doi-asserted-by":"crossref","first-page":"128984","DOI":"10.1016\/j.energy.2023.128984","article-title":"Remaining useful life prediction method of lithium-ion batteries is based on variational modal decomposition and deep learning integrated approach","volume":"282","author":"S Wang","year":"2023","journal-title":"Energy"},{"issue":"1","key":"pone.0335066.ref039","doi-asserted-by":"crossref","DOI":"10.36001\/phmconf.2014.v6i1.2490","article-title":"Adaptation of an electrochemistry-based li-ion battery model to account for deterioration observed under randomized use","volume":"6","author":"B Bole","year":"2014","journal-title":"PHM_CONF"},{"key":"pone.0335066.ref040","doi-asserted-by":"crossref","first-page":"109198","DOI":"10.1016\/j.est.2023.109198","article-title":"Optimized data-driven approach for remaining useful life prediction of Lithium-ion batteries based on sliding window and systematic sampling","volume":"73","author":"S Ansari","year":"2023","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref041","unstructured":"NASA. Li-ion Battery Aging Datasets. https:\/\/data.nasa.gov\/dataset\/Li-ion-Battery-Aging-Datasets\/uj5r-zjdb\/about_data"},{"key":"pone.0335066.ref042","doi-asserted-by":"crossref","first-page":"116024","DOI":"10.1016\/j.est.2025.116024","article-title":"Multi-time scale feature extraction for early prediction of battery RUL and knee point using a hybrid deep learning approach","volume":"117","author":"Q Yu","year":"2025","journal-title":"Journal of Energy Storage"},{"key":"pone.0335066.ref043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3055791","article-title":"Remaining useful life estimation for LFP cells in second-life applications","volume":"70","author":"I Sanz-Gorrachategui","year":"2021","journal-title":"IEEE Trans Instrum Meas"},{"issue":"59","key":"pone.0335066.ref044","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Y Ganin","year":"2016","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"pone.0335066.ref045","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1109\/TPEL.2021.3117788","article-title":"State-of-health estimation for lithium-ion batteries using domain adversarial transfer learning","volume":"37","author":"Z Ye","year":"2022","journal-title":"IEEE Trans Power Electron"},{"key":"pone.0335066.ref046","article-title":"Generative adversarial nets","volume":"27","author":"I Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0335066.ref047","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0335066.ref048","doi-asserted-by":"crossref","unstructured":"Justusson B. Median filtering: statistical properties. Two-dimensional digital signal processing II: transforms and median filters. 2006. p. 161\u201396.","DOI":"10.1007\/BFb0057597"},{"issue":"4","key":"pone.0335066.ref049","doi-asserted-by":"crossref","first-page":"4450","DOI":"10.1016\/j.eswa.2010.09.116","article-title":"Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm","volume":"38","author":"M Elangovan","year":"2011","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"pone.0335066.ref050","doi-asserted-by":"crossref","first-page":"4088","DOI":"10.1016\/j.eswa.2010.09.072","article-title":"Effect of number of features on classification of roller bearing faults using SVM and PSVM","volume":"38","author":"V Sugumaran","year":"2011","journal-title":"Expert Systems with Applications"},{"key":"pone.0335066.ref051","article-title":"Layer normalization","author":"JL Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"pone.0335066.ref052","article-title":"Understanding dropout","volume":"26","author":"P Baldi","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"pone.0335066.ref053","article-title":"An equivalence of fully connected layer and convolutional layer","author":"W Ma","year":"2017","journal-title":"arXiv preprint"},{"key":"pone.0335066.ref054","article-title":"Deep learning using rectified linear units (relu)","author":"AF Agarap","year":"2018","journal-title":"arXiv preprint"},{"issue":"3","key":"pone.0335066.ref055","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1093\/aob\/mcg029","article-title":"A flexible sigmoid function of determinate growth","volume":"91","author":"X Yin","year":"2003","journal-title":"Ann Bot"},{"key":"pone.0335066.ref056","article-title":"Understanding batch normalization","volume":"31","author":"N Bjorck","year":"2018","journal-title":"Advances in neural information processing systems"},{"issue":"14","key":"pone.0335066.ref057","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btl242","article-title":"Integrating structured biological data by Kernel Maximum Mean Discrepancy","volume":"22","author":"KM Borgwardt","year":"2006","journal-title":"Bioinformatics"},{"key":"pone.0335066.ref058","author":"I Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"pone.0335066.ref059","unstructured":"Ganin Y, Lempitsky V. In: International conference on machine learning, 2015. 1180\u20139."},{"key":"pone.0335066.ref060","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3354\/cr030079","article-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance","volume":"30","author":"C Willmott","year":"2005","journal-title":"Clim Res"},{"issue":"2","key":"pone.0335066.ref061","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/S0304-4076(96)01818-0","article-title":"An R-squared measure of goodness of fit for some common nonlinear regression models","volume":"77","author":"A Colin Cameron","year":"1997","journal-title":"Journal of Econometrics"},{"key":"pone.0335066.ref062","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neucom.2015.12.114","article-title":"Mean absolute percentage error for regression models","volume":"192","author":"A de Myttenaere","year":"2016","journal-title":"Neurocomputing"},{"key":"pone.0335066.ref063","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining; 2016. p. 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"issue":"7825","key":"pone.0335066.ref064","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"issue":"3","key":"pone.0335066.ref065","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"P Virtanen","year":"2020","journal-title":"Nat Methods"},{"key":"pone.0335066.ref066","doi-asserted-by":"crossref","first-page":"111396","DOI":"10.1016\/j.est.2024.111396","article-title":"A structural pruning method for lithium-ion batteries remaining useful life prediction model with multi-head attention mechanism","volume":"86","author":"Y Ge","year":"2024","journal-title":"Journal of Energy Storage"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:42:05Z","timestamp":1761932525000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335066"}},"subtitle":[],"editor":[{"given":"Zhibin","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":66,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0335066","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,31]]}}}