{"id":"W4407632315","doi":"10.18154/rwth-2025-01751","title":"Safe Reinforcement Learning-based Control for Hydrogen Diesel Dual-Fuel Engines","year":2025,"lang":"en","type":"preprint","venue":"RWTH Publications (RWTH Aachen)","topic":"Advanced Combustion Engine Technologies","field":"Chemical Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Mitacs","keywords":"Diesel fuel; Dual (grammatical number); Reinforcement learning; Automotive engineering; Reinforcement; Control (management); Environmental science; Computer science; Engineering; Artificial intelligence; Structural engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004214226,0.0007868068,0.0008428913,0.0009971519,0.0002562699,0.0001234627,0.001204552,0.0008591136,0.000154169],"category_scores_gemma":[0.004229089,0.0008577146,0.0004804215,0.0008335033,0.0001377944,0.000241944,0.0005097,0.001687028,0.00006048871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006478881,"about_ca_system_score_gemma":0.0004486679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001509092,"about_ca_topic_score_gemma":0.000004554487,"domain_scores_codex":[0.9965156,0.00005122317,0.00105854,0.001059152,0.0004456269,0.000869865],"domain_scores_gemma":[0.9957192,0.0009031895,0.0005229689,0.001828757,0.0008178371,0.000208047],"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":[0.00003022341,0.0000973487,0.00006146913,0.0007061677,0.0003078668,6.053401e-7,0.00005637739,0.9693424,0.000247214,0.02443842,0.002057025,0.002654898],"study_design_scores_gemma":[0.001419004,0.00004948368,0.00003346423,0.0001654907,0.000216163,0.000001389261,0.00003751524,0.819486,0.002242243,0.002380968,0.1732441,0.0007241435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003488867,0.001095696,0.9778553,0.007428542,0.0003805785,0.002247927,0.0003788879,0.004820654,0.005443583],"genre_scores_gemma":[0.920472,0.0001411682,0.03975463,0.0003973041,0.0003413409,0.00981578,0.003220624,0.0001667247,0.02569048],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9381006,"threshold_uncertainty_score":0.9993874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01864760181716811,"score_gpt":0.2726239438558856,"score_spread":0.2539763420387175,"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."}}