{"id":"W3212263828","doi":"10.1016/j.ress.2021.108191","title":"A deep learning predictive model for selective maintenance optimization","year":2021,"lang":"en","type":"article","venue":"Reliability Engineering & System Safety","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":83,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Predictive maintenance; Component (thermodynamics); Benchmarking; Modular design; Reliability engineering; Turbofan; Computer science; Set (abstract data type); Maintenance actions; Engineering; Machine learning","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":[0.0006426934,0.0003467395,0.0004844703,0.0000829082,0.0001600342,0.00005609681,0.0001544423,0.0002526554,0.00000611189],"category_scores_gemma":[0.0009452743,0.0003777262,0.0002100615,0.0004881919,0.00003098527,0.000328802,0.0000333523,0.0003667958,0.000005575666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001264584,"about_ca_system_score_gemma":0.00009030209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004859391,"about_ca_topic_score_gemma":0.000004049228,"domain_scores_codex":[0.9979246,0.00006205118,0.0006498881,0.0005691872,0.0002324531,0.0005618064],"domain_scores_gemma":[0.9983589,0.0002620745,0.00007690748,0.0004523595,0.0007088503,0.0001408932],"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":[0.00005872944,0.00002560579,0.00006260273,0.001178736,0.00006032558,0.000002076634,0.0004543432,0.9961627,0.0003340824,0.001214268,0.00009098959,0.0003555834],"study_design_scores_gemma":[0.0005864502,0.00004444555,0.0001328178,0.0002739159,0.00005152769,0.00001936364,0.000228324,0.9970028,0.0006845528,0.00005488511,0.0005475151,0.0003733859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008781425,0.0002585032,0.9942827,0.00005347943,0.0005655253,0.0008625485,0.00004185813,0.001553717,0.001503562],"genre_scores_gemma":[0.866058,0.0002211497,0.1327683,0.000009553055,0.0001121352,0.0003537119,0.0001355005,0.0001121405,0.0002295098],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8651798,"threshold_uncertainty_score":0.9998674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00378129399622761,"score_gpt":0.177417110569024,"score_spread":0.1736358165727964,"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."}}