{"id":"W3195109032","doi":"10.1016/j.energy.2021.121857","title":"State of health prognostics for series battery packs: A universal deep learning method","year":2021,"lang":"en","type":"article","venue":"Energy","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":116,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Battery (electricity); Prognostics; Reliability (semiconductor); State of health; State (computer science); Feature (linguistics); Reliability engineering; Series (stratigraphy); Computer science; Deep learning; Artificial intelligence; Engineering; Algorithm; 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":[0.00013359,0.00009561893,0.0002009769,0.00008428404,0.00004981359,0.00001097181,0.0001113489,0.00004228621,0.00001671408],"category_scores_gemma":[0.0002141941,0.0001041414,0.0000382197,0.0002344207,0.00003869453,0.0000983513,0.0000851359,0.000140425,0.00000100006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007970924,"about_ca_system_score_gemma":0.00004457715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001124859,"about_ca_topic_score_gemma":0.00005396262,"domain_scores_codex":[0.9991955,0.0000633637,0.0001795995,0.0001437107,0.0001088401,0.0003090113],"domain_scores_gemma":[0.9994428,0.0002269494,0.00003894987,0.0001711981,0.00008572027,0.00003443556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001384985,0.00001649268,0.0001546551,0.000220996,0.00006777921,0.0000216216,0.0002122897,0.4375452,0.009318686,0.002196831,0.0003236023,0.549908],"study_design_scores_gemma":[0.0008692924,0.0005746792,0.0004629217,0.0001461686,0.00001438188,0.00004361622,0.002809356,0.1718475,0.5212798,0.009733955,0.2916936,0.0005247965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005882262,0.0009809795,0.9920743,0.0003358165,0.00009052327,0.00006008,0.00001343519,0.0003169243,0.0002456992],"genre_scores_gemma":[0.5398192,0.001782594,0.4558875,0.00007963573,0.00004615402,0.0000658308,0.00009815308,0.0001000609,0.00212081],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5493832,"threshold_uncertainty_score":0.4246764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01794461205611868,"score_gpt":0.2838534580980284,"score_spread":0.2659088460419097,"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."}}