{"id":"W4409487892","doi":"10.1016/j.apenergy.2025.125923","title":"Battery state-of-health estimation using CNNs with transfer learning and multi-modal fusion of partial voltage profiles and histogram data","year":2025,"lang":"en","type":"article","venue":"Applied Energy","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Battery (electricity); Modal; Histogram; Transfer of learning; Computer science; Artificial intelligence; Fusion; State (computer science); Voltage; Pattern recognition (psychology); State of health; Sensor fusion; Engineering; Chemistry; Algorithm; Electrical engineering; Image (mathematics); 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":[0.0001112606,0.0001097568,0.0002077545,0.0001464737,0.00005888417,0.000009252367,0.0001102117,0.00005022585,0.00000258396],"category_scores_gemma":[0.00001071641,0.0001018785,0.000006211349,0.0001792714,0.0001114138,0.00009087452,0.0001216427,0.0001356607,7.625484e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003442234,"about_ca_system_score_gemma":0.00002907063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001346908,"about_ca_topic_score_gemma":0.0000396609,"domain_scores_codex":[0.9992664,0.00001419605,0.000216962,0.0002075235,0.0001058889,0.0001890583],"domain_scores_gemma":[0.9996617,0.0000522058,0.00003010294,0.0002156977,0.00001611,0.00002413507],"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":[0.00004537713,0.00002971953,0.001100312,0.0004467419,0.0000352174,0.00000110029,0.0001296168,0.2828782,0.1606355,0.0007452045,0.000007978126,0.5539451],"study_design_scores_gemma":[0.0006392347,0.00007436441,0.00111304,0.000111217,0.00001294172,0.000001680866,0.0001613279,0.9014946,0.0955493,0.0001750702,0.0005261297,0.0001411264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4196139,0.0002158022,0.5799405,0.00001155089,0.00001126423,0.00008299771,0.000008654553,0.00007941998,0.00003589025],"genre_scores_gemma":[0.9708137,0.0001931904,0.02889694,0.00000587112,0.000003252259,0.00001622924,0.00004085909,0.00001861886,0.00001132844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6186163,"threshold_uncertainty_score":0.4154485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0245635584185667,"score_gpt":0.2871359318006677,"score_spread":0.2625723733821009,"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."}}