{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002541343,0.0008468041,0.001507815,0.0006560151,0.0003149585,0.0009237336,0.001083085,0.001250869,0.001728219],"category_scores_gemma":[0.006221552,0.0005691132,0.0005193913,0.0003852452,0.001089343,0.0009541434,0.0007282812,0.001309233,0.000200614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350026,"about_ca_system_score_gemma":0.0017539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008753279,"about_ca_topic_score_gemma":0.004438716,"domain_scores_codex":[0.9992254,0.0003319547,0.00003715496,0.0001440186,0.0001398957,0.0001216575],"domain_scores_gemma":[0.9954151,0.003409434,0.0004579784,0.0001189703,0.0004529768,0.0001455967],"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":[0.00002719143,0.00003778156,0.0002701764,0.00001436061,0.00001202659,0.00001192268,0.000008193113,0.9930177,0.0002325721,0.001218791,0.0001283196,0.005020956],"study_design_scores_gemma":[0.000005104276,0.00001092504,0.00003400598,0.000001424003,0.000001791595,0.000001499354,7.944199e-7,0.9994496,0.00005893626,0.0004130099,0.00002177719,0.000001175657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0667375,0.0003097569,0.9290148,0.0003705447,0.0000375315,0.00009875333,0.0000448416,0.0003578325,0.003028333],"genre_scores_gemma":[0.9610838,0.00008664651,0.03736478,0.00006167193,0.00001746911,0.0001028947,0.00004395397,0.00002648612,0.001212384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008753279,"threshold_uncertainty_score":0.01740462,"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."}}