{"id":"W4413142757","doi":"10.1016/j.est.2025.118043","title":"Data-driven methods for early warning of battery thermal runaway: A review of multi-signal fusion and machine learning approaches","year":2025,"lang":"en","type":"article","venue":"Journal of Energy Storage","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Higher Education Discipline Innovation Project; China Scholarship Council; Ministry of Education of the People's Republic of China","keywords":"Thermal runaway; Battery (electricity); Warning system; Computer science; Sensor fusion; Fusion; SIGNAL (programming language); Artificial intelligence; Machine learning; Engineering; Telecommunications; 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":[0.001029783,0.0001403333,0.0005188657,0.0003057958,0.00004350421,0.00000968672,0.0004623402,0.00008667734,0.00001498886],"category_scores_gemma":[0.0004219342,0.0001154124,0.00008888321,0.0002328844,0.00007600177,0.0002410412,0.0003018667,0.0004274612,4.82306e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004460596,"about_ca_system_score_gemma":0.00003373882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006390416,"about_ca_topic_score_gemma":0.000002000064,"domain_scores_codex":[0.9987949,0.000155133,0.0005647664,0.000139309,0.0001622037,0.000183654],"domain_scores_gemma":[0.9988376,0.0004266528,0.0003066005,0.0002717363,0.0001194931,0.00003788578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001050453,0.000073954,0.001594217,0.00529936,0.0004120657,0.00001623155,0.0001022373,0.1684304,0.1139228,0.0001848257,0.000204266,0.7096546],"study_design_scores_gemma":[0.001525517,0.0004641077,0.002012868,0.006551292,0.0001758216,0.0000338425,0.0001356059,0.9200537,0.03560507,0.0001254478,0.03302034,0.0002963775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02271811,0.04857806,0.9282174,0.0001023446,0.00008429248,0.00009946398,0.00002005767,0.00003402301,0.0001463004],"genre_scores_gemma":[0.647525,0.01420998,0.3379476,0.00004210235,0.00005309219,0.00001169032,0.00002130492,0.00004577668,0.0001434915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7516233,"threshold_uncertainty_score":0.470638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08978071440432223,"score_gpt":0.3487632640259096,"score_spread":0.2589825496215873,"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."}}