{"id":"W2939021925","doi":"10.1109/rams.2019.8768978","title":"An Overview of Deep Learning in Prognostics and Health Management","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Department of Education of Guangdong Province; National Science Foundation","keywords":"Prognostics; Deep learning; Artificial intelligence; Computer science; Machine learning; Fault (geology); Feature (linguistics); Raw data; Field (mathematics); Supervised learning; Feature learning; Feature extraction; Fault detection and isolation; Data mining; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001799392,0.00005886785,0.0001203901,0.00007581419,0.000004797874,0.000006626023,0.00005224725,0.00001950545,0.00004788981],"category_scores_gemma":[0.000003020541,0.00005723981,0.000008256457,0.00008270203,0.000004010536,0.00005241948,0.00002271692,0.00007244093,0.00000379822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002135449,"about_ca_system_score_gemma":0.000001555855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006686533,"about_ca_topic_score_gemma":0.00009872027,"domain_scores_codex":[0.999605,0.00001487971,0.0001382483,0.00007937743,0.0000599274,0.0001025947],"domain_scores_gemma":[0.9998324,0.0000154008,0.0000157104,0.0001034579,0.000005134481,0.00002789881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001254689,0.00007207087,0.6556698,0.00214428,0.00001506068,0.000002360995,0.0002908535,0.008423418,0.0001189129,0.01406121,0.0002369113,0.3189639],"study_design_scores_gemma":[0.0003689337,0.0002892552,0.7062708,0.0003254073,0.000005318851,0.000001552674,0.0001431969,0.2861426,0.001294416,0.0004678619,0.004482314,0.0002083826],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651003,0.005089911,0.005618494,0.0001563479,0.00005439754,0.00104644,0.00000106175,0.0008259828,0.02210707],"genre_scores_gemma":[0.9836552,0.002877718,0.01335377,0.00005923577,0.000003200016,0.00001467111,0.000003198062,0.000012726,0.00002029509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3187555,"threshold_uncertainty_score":0.2334172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02199651251830944,"score_gpt":0.3381069825335505,"score_spread":0.3161104700152411,"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."}}