{"paper":{"title":"A Hybrid Tucker-LSTM Tensor Network Model for SOC Prediction in Electric Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Tucker tensor decomposition combined with LSTM networks improves SOC prediction accuracy for electric vehicles by preserving temporal structure in compressed data.","cross_cats":["cs.ET"],"primary_cat":"cs.LG","authors_text":"Bing Wang, Han Wang, Ying Wang","submitted_at":"2026-05-13T08:54:17Z","abstract_excerpt":"Accurate state of charge estimation is critical for the success of electric vehicle battery management strategies, but it is well known that conventional estimators suffer from two fundamental shortcomings: cumulative errors that grow over time and reliance on simplified battery models that do not reflect real world dynamics. Therefore, this paper presents a novel hybrid approach combining Tucker tensor decomposition with LSTM networks, using full - lifecycle EV field data for SOC prediction. The inputs are charge status, mileage, voltage, current, cell differentials, and temporal features. Tu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Tucker-LSTM outperforms the baseline on all metrics, with MSE dropping 70.5% (from 21.07 to 6.22), MAE improving 48.7% (from 3.37% to 1.73%), RMSE falling from 4.59% to 2.49%, and R² rising from 0.918 to 0.976.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Tucker decomposition reduces dimensionality while fully preserving the temporal structure and predictive information needed for accurate SOC forecasting on real EV data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Tucker-LSTM hybrid reduces MSE by 70.5% for EV battery SOC prediction versus standard LSTM on full-lifecycle field data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Tucker tensor decomposition combined with LSTM networks improves SOC prediction accuracy for electric vehicles by preserving temporal structure in compressed data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3c9b891339a8371aa820101c100a2606a07e0923369c9005801c9f93954c35df"},"source":{"id":"2605.13200","kind":"arxiv","version":1},"verdict":{"id":"3e165083-b22c-4c1f-87bf-223e677a0a52","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:27:50.208407Z","strongest_claim":"Tucker-LSTM outperforms the baseline on all metrics, with MSE dropping 70.5% (from 21.07 to 6.22), MAE improving 48.7% (from 3.37% to 1.73%), RMSE falling from 4.59% to 2.49%, and R² rising from 0.918 to 0.976.","one_line_summary":"Tucker-LSTM hybrid reduces MSE by 70.5% for EV battery SOC prediction versus standard LSTM on full-lifecycle field data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Tucker decomposition reduces dimensionality while fully preserving the temporal structure and predictive information needed for accurate SOC forecasting on real EV data.","pith_extraction_headline":"Tucker tensor decomposition combined with LSTM networks improves SOC prediction accuracy for electric vehicles by preserving temporal structure in compressed data."},"references":{"count":98,"sample":[{"doi":"","year":2024,"title":"A lithium-ion battery remaining useful life prediction model based on ceemdan data preprocessing and hssa-lstm-tcn,","work_id":"25072e36-3a59-4d61-bcbc-b42538329569","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Mechanistically guided residual learning for battery state monitoring throughout life,","work_id":"d8a5838d-c21e-4696-8336-8fe63342c92e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Analysis of state-of-charge estimation methods for li-ion batteries considering wide temperature range,","work_id":"574211fe-ec7e-4fce-95e7-3775d0ed8263","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"A critical review of the state estimation methods of power batteries for electric vehicles,","work_id":"c486948b-e9ce-4cae-bc7b-47a2792b3a46","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Explainable real-time data driven method for battery electric model reconstruction via tensor train decomposition,","work_id":"1b1cddba-1402-4422-98c4-8f35f824850e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":98,"snapshot_sha256":"98d4e4cce38e1697bd7b81cc657f4e43184409b4cbdc70358203701eff03e245","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}