{"id":"W4405766477","doi":"10.1002/qre.3714","title":"Joint Optimization of Condition‐Based Maintenance and Production Rate Using Reinforcement Learning Algorithms","year":2024,"lang":"en","type":"article","venue":"Quality and Reliability Engineering International","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Kermanshah University of Technology","keywords":"Reinforcement learning; Markov decision process; Production (economics); Computer science; Time horizon; Production planning; Scheduling (production processes); Mathematical optimization; Q-learning; Production control; Hyperparameter; Preventive maintenance; Dynamic programming; Industrial engineering; Operations research; Markov process; Engineering; Algorithm; Reliability engineering; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.000905789,0.0001554555,0.0001881401,0.0001589877,0.00004913268,0.00006569369,0.00005283034,0.00009167391,0.00003167419],"category_scores_gemma":[0.0004619336,0.0001536681,0.00005331122,0.0001645207,0.00007877269,0.0003422311,0.0000274698,0.0002135412,8.400407e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001543859,"about_ca_system_score_gemma":0.00002449018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002871254,"about_ca_topic_score_gemma":5.515976e-7,"domain_scores_codex":[0.9988707,0.00004184783,0.0004834321,0.0002775858,0.0001776339,0.0001487613],"domain_scores_gemma":[0.9995133,0.00009610646,0.00005276077,0.0001258073,0.0001641134,0.00004794301],"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":[0.00001105542,0.00001260382,0.0001009873,0.0007522997,0.00003229757,7.085758e-7,0.0001441167,0.9926322,0.00387113,0.001773387,0.00002275221,0.0006464697],"study_design_scores_gemma":[0.000176349,0.00002679504,0.0009979272,0.0003281723,0.00001729195,0.000006927778,0.00004081337,0.9940454,0.003296632,0.000226408,0.0006724427,0.0001648507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1217923,0.0001782395,0.8758781,0.0004328706,0.001079821,0.0002152498,0.00001202818,0.0002823319,0.0001290768],"genre_scores_gemma":[0.9694773,0.0003900976,0.02984158,0.00001851361,0.00009519923,0.00002036428,0.00006514084,0.00002438604,0.00006740978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.847685,"threshold_uncertainty_score":0.6266401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174909545892994,"score_gpt":0.2587951566424163,"score_spread":0.2413042020531169,"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."}}