{"id":"W4393971547","doi":"10.1016/j.est.2024.111524","title":"A self-attention-based CNN-Bi-LSTM model for accurate state-of-charge estimation of lithium-ion batteries","year":2024,"lang":"en","type":"article","venue":"Journal of Energy Storage","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec; Mila - Quebec Artificial Intelligence Institute; Polytechnique Montréal; Université du Québec à Montréal","funders":"","keywords":"Lithium (medication); State of charge; Ion; State (computer science); Charge (physics); Computer science; Estimation; Artificial intelligence; Pattern recognition (psychology); Physics; Algorithm; Engineering; Battery (electricity); Psychology; Quantum mechanics; Power (physics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002634577,0.0001490501,0.0002910872,0.0004865535,0.00002976249,0.00003263729,0.000227289,0.00008513984,0.00001637555],"category_scores_gemma":[0.00009434117,0.0001323959,0.0001522492,0.0002739,0.00004718875,0.0004537844,0.00002987491,0.000216376,0.000001394812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001630857,"about_ca_system_score_gemma":0.00009079599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002374006,"about_ca_topic_score_gemma":0.000002525689,"domain_scores_codex":[0.9987744,0.00002077039,0.0005775383,0.0001119443,0.0003018263,0.0002134854],"domain_scores_gemma":[0.999172,0.000195737,0.0001875676,0.0001833237,0.0002137567,0.00004757927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005460004,0.00003754677,0.00001223296,0.0006627238,0.0001019359,0.00001627873,0.00009102203,0.9423817,0.04459991,0.0004998803,0.000751409,0.01079081],"study_design_scores_gemma":[0.0002711371,0.000155444,0.00002428829,0.0002148257,0.00002403609,0.000007178236,0.00001771296,0.899954,0.0964391,0.00161225,0.001176186,0.0001038069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1941078,0.000598334,0.804511,0.0001407159,0.0003260089,0.00007366308,0.00005280013,0.0001295158,0.00006016401],"genre_scores_gemma":[0.9706423,0.0001725171,0.02886695,0.00001136504,0.00004141527,0.00001727194,0.0000110847,0.00004397674,0.0001931594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7765344,"threshold_uncertainty_score":0.539895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01829718610191178,"score_gpt":0.2787327988063442,"score_spread":0.2604356127044324,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}