{"id":"W4327709671","doi":"10.1016/j.enconman.2023.116921","title":"Energy management strategy for fuel cell vehicles via soft actor-critic-based deep reinforcement learning considering powertrain thermal and durability characteristics","year":2023,"lang":"en","type":"article","venue":"Energy Conversion and Management","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":86,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Powertrain; Durability; Automotive engineering; Proton exchange membrane fuel cell; Battery (electricity); Stack (abstract data type); State of health; Reinforcement learning; Engineering; Computer science; Simulation; Power (physics); Torque; Fuel cells; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002020598,0.0002526651,0.0002333066,0.0001578063,0.0001621884,0.00009491662,0.00008512702,0.00009944713,0.00009312729],"category_scores_gemma":[0.000002498663,0.0002478196,0.00005627015,0.00009598433,0.00005703047,0.00008230385,0.0001310489,0.00006897763,0.000006662258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004674279,"about_ca_system_score_gemma":0.000004564496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002480944,"about_ca_topic_score_gemma":0.000003883866,"domain_scores_codex":[0.998814,0.00003528706,0.0003036951,0.000313067,0.000154331,0.000379549],"domain_scores_gemma":[0.9995664,0.00006904564,0.00005294463,0.0001648345,0.00002424467,0.0001224711],"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":[0.000395911,0.0001516223,0.0001811084,0.03340458,0.0008830847,0.0004304031,0.0006229247,0.8333842,0.03380365,0.007522868,0.002850643,0.08636907],"study_design_scores_gemma":[0.002391625,0.0001601288,0.0005200115,0.0001142773,0.0001457341,0.000001872354,0.0006424179,0.7924566,0.007882792,0.0002939703,0.1948236,0.0005668955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5352129,0.01120493,0.3260698,0.001674469,0.008069626,0.003802853,0.00007444032,0.005570971,0.10832],"genre_scores_gemma":[0.9888325,0.008786845,0.0002575586,0.000176143,0.00003731057,0.00006623883,0.0001225007,0.00004338256,0.001677472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4536196,"threshold_uncertainty_score":0.9999974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008274694417114368,"score_gpt":0.1898814195785575,"score_spread":0.1816067251614432,"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."}}