{"id":"W4412991508","doi":"10.1016/j.conengprac.2025.106513","title":"Systematic framework for deep learning-based predictive injection control with Bayesian hyperparameter optimization for a hydrogen/diesel dual-fuel engine","year":2025,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Advanced Combustion Engine Technologies","field":"Chemical Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Deutsche Forschungsgemeinschaft","keywords":"Hyperparameter; Dual (grammatical number); Bayesian optimization; Diesel fuel; Bayesian probability; Machine learning; Computer science; Automotive engineering; Artificial intelligence; Engineering","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005151246,0.0004899331,0.0007670742,0.0004205485,0.0001469379,0.00007833204,0.0002371592,0.0003802314,0.000005772396],"category_scores_gemma":[0.02381305,0.0004706867,0.0001887981,0.0006128994,0.00004105188,0.0005030306,0.00002308586,0.0007044637,0.000002375706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003542652,"about_ca_system_score_gemma":0.00005818494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002611332,"about_ca_topic_score_gemma":4.98496e-7,"domain_scores_codex":[0.9979575,0.00006168454,0.0006141941,0.0005418106,0.0002473282,0.0005774787],"domain_scores_gemma":[0.9903129,0.008268265,0.0003292875,0.0004231758,0.0005716779,0.00009463084],"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":[0.0009251882,0.00007965165,0.000005013029,0.00471435,0.000772572,0.000003608988,0.00006184058,0.9886239,0.0003496601,0.004221928,0.000007119354,0.0002352314],"study_design_scores_gemma":[0.005061664,0.0005247713,0.000003323345,0.001718079,0.001085469,0.00002037585,0.000185609,0.9895962,0.0006799587,0.0002476246,0.0004313274,0.0004456373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005850165,0.0009896079,0.9926338,0.0007308989,0.0002594747,0.00313048,0.00002974442,0.002124222,0.00004323347],"genre_scores_gemma":[0.7074603,0.00001135437,0.2884113,0.0001669211,0.00008804454,0.003663416,0.00002353303,0.0001075947,0.00006753749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7074018,"threshold_uncertainty_score":0.9997745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00416942781926794,"score_gpt":0.2327056382441287,"score_spread":0.2285362104248608,"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."}}