{"id":"W4390628459","doi":"10.1016/j.apenergy.2023.122555","title":"A hybrid deep learning approach for remaining useful life prediction of lithium-ion batteries based on discharging fragments","year":2024,"lang":"en","type":"article","venue":"Applied Energy","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Hilbert–Huang transform; Degradation (telecommunications); Robustness (evolution); Convolutional neural network; Trajectory; Computer science; Battery capacity; Battery (electricity); Lithium-ion battery; Deep learning; Artificial intelligence; Algorithm; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002444217,0.0006290558,0.0006909973,0.0006233901,0.0002699737,0.0005230032,0.001228276,0.0007280951,0.001554785],"category_scores_gemma":[0.0005158304,0.0002483184,0.0005315086,0.0005065007,0.000203621,0.000837777,0.000494615,0.0006792128,0.0003392043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005947497,"about_ca_system_score_gemma":0.000670005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01051013,"about_ca_topic_score_gemma":0.009850294,"domain_scores_codex":[0.9999143,0.000008168204,0.000005295471,0.00002376545,0.00002598793,0.00002249608],"domain_scores_gemma":[0.9998078,0.00006695173,0.00001974563,0.00001287068,0.00007580138,0.00001682669],"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":[0.0002756393,0.0002234781,0.0037647,0.00008790347,0.00007201159,0.0001313335,0.00003025979,0.7814363,0.006184511,0.001958648,0.002684963,0.2031502],"study_design_scores_gemma":[0.000001303692,0.000006949889,0.0001057031,0.000001608385,0.000003239337,0.000003825264,0.000001457685,0.9990531,0.0003768883,0.0003648603,0.00007967484,0.000001473186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2658318,0.002251936,0.7234629,0.000451936,0.0001510967,0.0000684304,0.0009610708,0.002070766,0.004749925],"genre_scores_gemma":[0.9633491,0.0003706322,0.03039841,0.0001244293,0.00005780653,0.00006012023,0.0008573356,0.00004874571,0.004733476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01051013,"threshold_uncertainty_score":0.02089787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01538237495393101,"score_gpt":0.229731382036245,"score_spread":0.214349007082314,"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."}}