{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T11:04:02Z","timestamp":1789383842861,"version":"build-2803163510"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004728","name":"VIT University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004728","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Reliable estimation of battery state of charge (SOC) and state of energy (SOE) under real world dynamic driving conditions is essential for battery management systems. However, traditional physics-based models and purely data-driven models struggle to adapt and generalize. This work proposes Closed-Loop Hybrid Digital Twin (CL-HDT) that synergizes adaptive physics twin, recurrent residual learning, physics guided optimization, and recursive state feedback for joint SOC-SOE estimation. Adaptive physics twin generates physically consistent reference estimate and residual from closed-loop recurrent model recursively corrects it. The proposed CL-HDT was developed with a dataset containing 30 real-world electric cycle driving trips, split with leakage-safe strategy into training, validation, and locked holdout test set. To analyze generalizability, leave-one-trip-out cross-validation (LOTO-CV) was applied within training set. The proposed architecture was benchmarked against five baselines including Extended Kalman Filter (EKF), Gated Recurrent Unit (GRU), Feature-Fusion Recurrent estimator (FFR), Residual-Guided Hybrid estimator (RGH), and Adaptive Physics Twin (APT). All the baselines and CL-HDT were trained and evaluated under identical pipeline to ensure fair comparison. CL-HDT attained strongest generalization in LOTO-CV with mean RMSE values of 0.7078% and 0.6883% for SOC and SOE respectively, while maintaining competitive performance in locked holdout test. Apart from aggregate metrics, CL-HDT was further evaluated using residual correction analysis, tracking curves, drift curves, component-wise ablation, error distribution, and ambient condition analysis to demonstrate its robustness and ability to mitigate accumulation of error over longer real-world trips. This approach offers a physically consistent solution for next-generation battery management systems under realistic driving conditions to support safety and battery life.<\/jats:p>","DOI":"10.3389\/frai.2026.1816237","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:27:38Z","timestamp":1789381658000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of a hybrid battery digital twin for joint SOC\u2013SOE estimation under real driving conditions"],"prefix":"10.3389","volume":"9","author":[{"given":"Sushil","family":"Krishnan","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yokesh Babu","family":"Sundaresan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"69950","DOI":"10.1109\/ACCESS.2025.3560065","article-title":"On equivalent circuit model-based state-of-charge estimation for Lithium-Ion batteries in electric vehicles","volume":"13","author":"Ahmed","year":"2025","journal-title":"IEEE Access"},{"key":"B2","doi-asserted-by":"publisher","first-page":"136134","DOI":"10.1016\/j.energy.2025.136134","article-title":"A highly effective and robust structure-based LSTM with feature-vector tuning framework for high-accuracy SOC estimation in EV","volume":"325","author":"Ahn","year":"2025","journal-title":"Energy"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TVT.2025.3565907","article-title":"Advancing electric vehicle battery management: a data-driven digital twin approach for real-time monitoring and performance enhancement","volume":"74","author":"Alamin","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"2504023","DOI":"10.26877\/asset.v7i4.2613","article-title":"Physics-informed neural network with thevenin equivalent circuit for accurate SOC Li-ion battery estimation","volume":"7","author":"Apribowo","year":"2025","journal-title":"Adv. Sustain. Sci. Eng. Technol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"12472","DOI":"10.1109\/TTE.2025.3590916","article-title":"State-of-charge and state-of-energy estimation for Lithium-Ion batteries based on meta-learning and square-root unscented Kalman filter","volume":"11","author":"Chen","year":"2025","journal-title":"IEEE Trans. Transp.Electrif."},{"key":"B6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.3390\/batteries11030107","article-title":"Exploiting artificial neural networks for the state of charge estimation in EV\/HV battery systems: a review","volume":"11","author":"Dini","year":"2025","journal-title":"Batteries"},{"key":"B7","doi-asserted-by":"publisher","first-page":"116690","DOI":"10.1016\/j.est.2025.116690","article-title":"A novel SOC estimation method for lithium-ion batteries using the fusion of deep neural network and physical information model","volume":"122","author":"Fan","year":"2025","journal-title":"J. Energy Storage"},{"key":"B8","doi-asserted-by":"publisher","first-page":"100638","DOI":"10.1016\/j.array.2025.100638","article-title":"Real-time adaptive neural network-based state of charge prediction of battery pack in a digital twin framework","volume":"29","author":"Farooq","year":"2026","journal-title":"Array"},{"key":"B9","doi-asserted-by":"publisher","first-page":"8164","DOI":"10.3390\/app15158164","article-title":"A unified machine learning framework for Li-Ion battery state estimation and prediction","volume":"15","author":"Fouka","year":"2025","journal-title":"Appl. Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.trpro.2025.03.104","article-title":"Enhanced state-of-charge estimation for lithium-ion batteries using a fractional-order sliding mode observer","volume":"84","author":"Gaufan","year":"2025","journal-title":"Transp. Res. Proc."},{"key":"B11","doi-asserted-by":"publisher","first-page":"37990","DOI":"10.1109\/ACCESS.2025.3539792","article-title":"Ensemble learning for precise state-of-charge estimation in electric vehicles lithium-ion batteries considering uncertainty","volume":"13","author":"Haraz","year":"2025","journal-title":"IEEE Access"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-02709-1","article-title":"SOC estimation for a lithium-ion pouch cell using machine learning under different load profiles","author":"Harinarayanan","year":"2025","journal-title":"Sci. Rep."},{"key":"B13","doi-asserted-by":"publisher","first-page":"6192","DOI":"10.3390\/en18236192","article-title":"Enhanced lithium-ion battery state-of-charge estimation via Akima\u2013Savitzky\u2013Golay OCV-SOC mapping reconstruction and Bayesian-optimized adaptive extended Kalman filter","volume":"18","author":"Isa","year":"2025","journal-title":"Energies"},{"key":"B14","doi-asserted-by":"publisher","first-page":"124685","DOI":"10.1109\/ACCESS.2022.3225093","article-title":"Prediction of the battery state using the digital twin framework based on the battery management system","volume":"10","author":"Jafari","year":"2022","journal-title":"IEEE Access"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.21203\/rs.3.rs-6806872\/v1","article-title":"Physics-informed neural SOH estimation method for lithium-ion battery under partial observability and sparse sensor data","volume":"32","author":"Jin","year":"2025","journal-title":"Ionics."},{"key":"B16","doi-asserted-by":"publisher","first-page":"10613","DOI":"10.3390\/app151910613","article-title":"Domain-driven teacher\u2013student machine learning framework for predicting slope stability under dry conditions","volume":"15","author":"Kassa","year":"2025","journal-title":"Appl. Sci."},{"key":"B17","doi-asserted-by":"publisher","first-page":"137539","DOI":"10.1016\/j.energy.2025.137539","article-title":"State of charge estimation for lithium-ion battery using a multi-feature Mamba network and UKF under mixed operating conditions","volume":"335","author":"Li","year":"2025","journal-title":"Energy"},{"key":"B18","doi-asserted-by":"publisher","first-page":"116023","DOI":"10.1016\/j.est.2025.116023","article-title":"An adaptive hybrid approach for online battery state of charge estimation","volume":"115","author":"Lin","year":"2025","journal-title":"J. Energy Storage"},{"key":"B19","author":"Manivannan","year":"2026","journal-title":"A Real-World Dataset for SOC and SOE Estimation of Electric Cycle Lithium-Ion Batteries on Indian National Highways"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.3390\/en18051188","article-title":"Analysis of state-of-charge estimation methods for Li-Ion batteries considering wide temperature range","volume":"18","author":"Miao","year":"2025","journal-title":"Energies"},{"key":"B21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3390\/batteries12010033","article-title":"Advanced battery modeling framework for enhanced power and energy state estimation with experimental validation","volume":"12","author":"Mi\u0161ljenovi\u0107","year":"2026","journal-title":"Batteries"},{"key":"B22","doi-asserted-by":"publisher","first-page":"120194","DOI":"10.1016\/j.est.2025.120194","article-title":"Digital twin-based prediction of battery parameters from limited initial data using an optimised time-series multi-layer perceptron","volume":"148","author":"Najafi-Shad","year":"2026","journal-title":"J. Energy Storage"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/s43926-025-00148-y","article-title":"Deep learning based state of charge estimation of lithium ion battery for electric vehicle application","author":"Pande","year":"2025","journal-title":"Discov. Internet Things"},{"key":"B24","doi-asserted-by":"publisher","first-page":"100528","DOI":"10.1016\/j.etran.2025.100528","article-title":"Real-time AI-enabled digital twin for battery health estimation and fast charging using partial-discharge data","volume":"27","author":"Qasem","year":"2026","journal-title":"eTransportation"},{"key":"B25","doi-asserted-by":"publisher","first-page":"92","DOI":"10.3390\/automation6040092","article-title":"Multi-physics digital twin models for predicting thermal runaway and safety failures in EV batteries","volume":"6","author":"Ramesh Babu","year":"2025","journal-title":"Automation"},{"key":"B26","doi-asserted-by":"publisher","first-page":"76","DOI":"10.3390\/ECSA-12-26513","article-title":"SOC estimation-based battery management system for electric bicycles: design and implementation","volume":"118","author":"Reddy","year":"2025","journal-title":"Eng. Proc."},{"key":"B27","doi-asserted-by":"publisher","first-page":"109905","DOI":"10.1016\/j.epsr.2023.109905","article-title":"Validation of EKF based SoC estimation using vehicle dynamic modelling for range prediction","volume":"226","author":"Sangeetha","year":"2024","journal-title":"Electr. Power Syst. Res."},{"key":"B28","doi-asserted-by":"publisher","first-page":"3542","DOI":"10.3390\/en18133542","article-title":"From empirical measurements to AI Fusion\u2014a holistic review of SOH estimation techniques for lithium-ion batteries in electric and hybrid vehicles","volume":"18","author":"Shan","year":"2025","journal-title":"Energies"},{"key":"B29","doi-asserted-by":"publisher","first-page":"100514","DOI":"10.1016\/j.nxener.2026.100514","article-title":"Predicting electric vehicle performance metrics using a convolution neural network-gated recurrent unit-attention based deep learning architecture","volume":"11","author":"Sharma","year":"2026","journal-title":"Next Energy"},{"key":"B30","doi-asserted-by":"publisher","first-page":"105498","DOI":"10.1016\/j.trc.2025.105498","article-title":"Iterative physics-enhanced residual learning for context-aware traffic assignment under biased inputs","volume":"183","author":"Shi","year":"2026","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"106049","DOI":"10.1016\/j.est.2022.106049","article-title":"Comprehensive co-estimation of lithium-ion battery state of charge, state of energy, state of power, maximum available capacity, and maximum available energy","volume":"56","author":"Shrivastava","year":"2022","journal-title":"J. Energy Storage"},{"key":"B32","doi-asserted-by":"publisher","first-page":"16543","DOI":"10.1038\/s41598-023-43858-5","article-title":"Prediction of lithium-ion battery SOC based on the fusion of MHA and ConvolGRU","volume":"13","author":"Tang","year":"2023","journal-title":"Sci. Rep."},{"key":"B33","doi-asserted-by":"publisher","first-page":"137215","DOI":"10.1016\/j.energy.2025.137215","article-title":"A generic physics-informed neural network framework for lithium-ion batteries state of health estimation","volume":"332","author":"Tian","year":"2025","journal-title":"Energy"},{"key":"B34","doi-asserted-by":"publisher","first-page":"116001","DOI":"10.1016\/j.est.2025.116001","article-title":"Joint state of charge and state of energy estimation of special aircraft lithium-ion batteries by optimized genetic marginalization-extended particle filtering","volume":"115","author":"Wang","year":"","journal-title":"J. Energy Storage"},{"key":"B35","doi-asserted-by":"publisher","first-page":"7821","DOI":"10.1007\/s11581-025-06424-9","article-title":"Joint estimation of state of charge and state of energy for lithium-ion batteries based on the iTransformer deep learning network","volume":"31","author":"Wang","year":"","journal-title":"Ionics"},{"key":"B36","doi-asserted-by":"publisher","first-page":"165663","DOI":"10.1109\/ACCESS.2024.3490655","article-title":"Digital twin model for lithium-ion battery SOC estimation in battery swapping station","volume":"12","author":"Wu","year":"2024","journal-title":"IEEE Access"},{"key":"B37","doi-asserted-by":"publisher","first-page":"126427","DOI":"10.1016\/j.apenergy.2025.126427","article-title":"Physics-informed neural network for co-estimation of state of health, remaining useful life, and short-term degradation path in lithium-ion batteries","volume":"398","author":"Yang","year":"2025","journal-title":"Appl. Energy"},{"key":"B38","doi-asserted-by":"publisher","first-page":"33035","DOI":"10.2139\/ssrn.4736082","article-title":"A transformer-based model for state of charge estimation of electrical vehicle batteries","volume":"13","author":"Yilmaz","year":"2025","journal-title":"IEEE Access."},{"key":"B39","doi-asserted-by":"publisher","first-page":"372","DOI":"10.3390\/batteries11100372","article-title":"Multi-timescale estimation of SOE and SOH for lithium-ion batteries with a fractional-order model and multi-innovation filter framework","volume":"11","author":"Yu","year":"2025","journal-title":"Batteries"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3628427","article-title":"A physics-informed dual-branch architecture for lithium-ion battery modeling and prognostics","volume":"74","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"B41","doi-asserted-by":"publisher","first-page":"135639","DOI":"10.1016\/j.energy.2025.135639","article-title":"A high-speed recurrent state network with noise reduction for multi-temperature state of energy estimation of electric vehicles lithium-ion batteries","volume":"322","author":"Zou","year":"2025","journal-title":"Energy"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1816237\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:27:39Z","timestamp":1789381659000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1816237\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":41,"alternative-id":["10.3389\/frai.2026.1816237"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1816237","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"article-number":"1816237"}}