{"id":"W4200520486","doi":"10.1016/j.est.2021.103660","title":"Estimating battery state of charge using recurrent and non-recurrent neural networks","year":2021,"lang":"en","type":"article","venue":"Journal of Energy Storage","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Battery (electricity); Recurrent neural network; Artificial neural network; Computer science; Estimator; State of charge; Feedforward neural network; Microprocessor; State (computer science); Artificial intelligence; Algorithm; Power (physics); Computer hardware; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001703961,0.0001494315,0.0003309355,0.0001823205,0.00004066309,0.00002921763,0.0001628485,0.00005592779,0.00002256456],"category_scores_gemma":[0.00008379892,0.0001406744,0.00007413371,0.0002457998,0.00005225912,0.0002376392,0.0001310331,0.0004446654,2.032107e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001088987,"about_ca_system_score_gemma":0.00002751694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002304899,"about_ca_topic_score_gemma":0.000003801034,"domain_scores_codex":[0.9988323,0.0000375163,0.0004786189,0.0001154896,0.0002458056,0.0002902108],"domain_scores_gemma":[0.9993012,0.00009111628,0.0002035437,0.0001698492,0.0001478583,0.00008641781],"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":[0.00001343458,0.00002578289,0.0003371535,0.0000700141,0.0000524634,0.0002008109,0.00003929955,0.8408874,0.01295124,0.000007577883,0.0001559003,0.1452589],"study_design_scores_gemma":[0.0002783495,0.00009404313,0.000539889,0.0002152518,0.00001320642,0.0001717911,0.00002377795,0.9877962,0.01033333,0.00006165139,0.0003400272,0.0001324187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7319748,0.002824229,0.264228,0.00003555323,0.000858073,0.00001980352,0.000004840197,0.00002375896,0.00003091495],"genre_scores_gemma":[0.9889947,0.0004798445,0.0103019,0.00001549842,0.0001587065,0.000001246574,0.000002156659,0.00003014361,0.00001582011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2570199,"threshold_uncertainty_score":0.5736535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02015420789818803,"score_gpt":0.2744588461515624,"score_spread":0.2543046382533743,"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."}}