{"id":"W4312999026","doi":"10.1016/j.ifacol.2022.09.554","title":"A Novel Predictive Selective Maintenance Strategy Using Deep Learning and Mathematical Programming","year":2022,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prognostics; Predictive maintenance; Component (thermodynamics); Reliability (semiconductor); Computer science; Process (computing); Modular design; Reliability engineering; Maintenance actions; Machine learning; Engineering; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0002420348,0.000187019,0.0002234312,0.00006812769,0.0002791987,0.0000450894,0.00008570527,0.00006090204,0.00007631748],"category_scores_gemma":[0.0001167168,0.0001882569,0.00005019268,0.0003010389,0.00007503574,0.0001673575,0.00007382264,0.0004954513,0.000002039481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002455231,"about_ca_system_score_gemma":0.0000288925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001672994,"about_ca_topic_score_gemma":0.00001021434,"domain_scores_codex":[0.998879,0.00004024602,0.0002293306,0.0002801904,0.0002017659,0.0003694978],"domain_scores_gemma":[0.9996279,0.00007329086,0.00005327032,0.00009661639,0.0000684776,0.00008039032],"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":[0.00004470465,0.0000923546,0.0002054824,0.0001006433,0.00006022449,0.000008507001,0.00174501,0.9759151,0.008066976,0.0004928615,0.000001110695,0.01326698],"study_design_scores_gemma":[0.0004772791,0.0001915942,0.0001811113,0.0000378155,0.00003420934,0.0001185943,0.003745349,0.994338,0.0001264397,0.0002519159,0.0002822836,0.000215445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2360174,0.000494553,0.7598499,0.0001149536,0.000161383,0.0007539702,0.00003862752,0.0005740011,0.001995217],"genre_scores_gemma":[0.6134775,0.00006212915,0.3860132,0.00002614935,0.00006733428,0.00009158399,0.00003023394,0.00005240392,0.0001794085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3774601,"threshold_uncertainty_score":0.7676893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009644971950502216,"score_gpt":0.2270474517347121,"score_spread":0.2174024797842099,"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."}}