{"id":"W3041091733","doi":"10.1016/j.neunet.2020.07.001","title":"Hybrid multi-mode machine learning-based fault diagnosis strategies with application to aircraft gas turbine engines","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":119,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Fault detection and isolation; Fault (geology); Cluster analysis; Artificial intelligence; Machine learning; Artificial neural network; Construct (python library); 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":[0.00003924544,0.0002518293,0.0002518257,0.00004850042,0.00007790943,0.00009440468,0.0001468861,0.00006574905,0.0000201011],"category_scores_gemma":[0.00001635827,0.0002168639,0.00006345566,0.0002657328,0.00001495883,0.0001136762,0.00001390047,0.0003685471,0.00003331906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002988655,"about_ca_system_score_gemma":0.000007044702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001237619,"about_ca_topic_score_gemma":0.0002343054,"domain_scores_codex":[0.999007,0.00003906788,0.0002219432,0.0002801932,0.0001570079,0.0002947325],"domain_scores_gemma":[0.9994909,0.00005953926,0.00003801874,0.0001631107,0.00004250962,0.0002059887],"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":[0.00006189073,0.00001283419,0.00102148,0.00003647828,0.00002239806,0.00000888332,0.00005561266,0.987945,0.0009321664,0.000004242458,0.0004851155,0.009413954],"study_design_scores_gemma":[0.0007512087,0.0001944031,0.0003365324,0.00001947836,0.00001811484,0.000005725919,0.00003223613,0.9858407,0.0008102455,8.539409e-7,0.01173768,0.0002528251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2124677,0.0006638825,0.7823668,0.001616155,0.000291307,0.0007185118,0.00001491813,0.00176664,0.00009409633],"genre_scores_gemma":[0.9982209,0.00002238641,0.0002712099,0.0005827632,0.0003967595,0.0003695793,0.00004937317,0.00006483586,0.00002219916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7857532,"threshold_uncertainty_score":0.8843454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007788203250872371,"score_gpt":0.2150424443501902,"score_spread":0.2072542410993178,"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."}}