{"id":"W2903255379","doi":"10.1002/qre.2428","title":"Optimal Bayesian maintenance policy for a gearbox subject to two dependent failure modes","year":2018,"lang":"en","type":"article","venue":"Quality and Reliability Engineering International","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Qinglan Project of Jiangsu Province of China; China Scholarship Council; Nanjing Institute of Technology; Nanjing University of Aeronautics and Astronautics; University of Toronto; National Natural Science Foundation of China","keywords":"Unobservable; Control chart; Bayesian probability; Residual; Hidden Markov model; Failure mode and effects analysis; Computer science; Fault (geology); Preventive maintenance; Condition-based maintenance; Bayesian inference; Process (computing); Markov process; Engineering; Reliability engineering; Artificial intelligence; Econometrics; Mathematics; Statistics; Algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007668904,0.0002508324,0.0002636337,0.000185892,0.0000904466,0.0001022669,0.000267501,0.0001265934,0.00002982795],"category_scores_gemma":[0.001015868,0.0002480643,0.0001033318,0.000202056,0.00007865184,0.0002003563,0.00007654588,0.0001807116,0.00001077422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002993594,"about_ca_system_score_gemma":0.00004309503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001593086,"about_ca_topic_score_gemma":0.00007487799,"domain_scores_codex":[0.9984194,0.00002674718,0.0004677757,0.0004284936,0.0002484091,0.0004091621],"domain_scores_gemma":[0.9989722,0.0001651311,0.00003990268,0.000322258,0.0003200367,0.0001804402],"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":[0.0001006973,0.00004333441,0.0002978581,0.0001747933,0.00005232777,6.555001e-7,0.0005160923,0.9739447,0.003575578,0.01933202,0.0004007393,0.001561163],"study_design_scores_gemma":[0.0008545112,0.0001200295,0.002560971,0.00008981991,0.00001222845,0.00001163931,0.0001132492,0.9783539,0.003945834,0.001534807,0.01197376,0.0004293188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2105657,0.00001793158,0.7843408,0.002821874,0.0006179768,0.0004796798,0.000111502,0.0003473694,0.0006971447],"genre_scores_gemma":[0.9125409,0.00002933999,0.08621355,0.0001836037,0.0006361724,0.0001336541,0.00003100945,0.00003924082,0.0001925425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7019752,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00982033292679253,"score_gpt":0.2760010790639216,"score_spread":0.2661807461371291,"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."}}