{"id":"W2889809771","doi":"10.1109/tii.2018.2868687","title":"A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":286,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; National Key Research and Development Program of China; Canada Foundation for Innovation","keywords":"Artificial neural network; Prognostics; Downtime; Computer science; Autoencoder; Feature extraction; Artificial intelligence; Bearing (navigation); Smoothing; Condition monitoring; Machine learning; Feature selection; Engineering; Data mining; Reliability engineering","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":[0.000470065,0.0002094209,0.0002494353,0.0001832775,0.0002648504,0.00007063324,0.0002422907,0.0002500467,0.00002037898],"category_scores_gemma":[0.00004251485,0.0001772551,0.0001330884,0.0003721334,0.0001122683,0.0003895106,0.000003051782,0.0005818738,8.553827e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009307073,"about_ca_system_score_gemma":0.0000272507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005815279,"about_ca_topic_score_gemma":0.000009761779,"domain_scores_codex":[0.9986377,0.00002617845,0.0007376983,0.00008885974,0.0002171383,0.0002923621],"domain_scores_gemma":[0.9990206,0.000298657,0.000164521,0.0003314439,0.0001014857,0.00008324686],"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":[0.00005283676,0.00003075246,0.00006377007,0.00004448382,0.00009353637,5.202842e-8,0.0008806644,0.9916252,0.0000723781,0.00002780964,0.0002608529,0.00684762],"study_design_scores_gemma":[0.0008347109,0.0001790532,0.00001239245,0.00004074869,0.0001144313,0.000004047774,0.0005003054,0.990619,0.007206551,0.000004240119,0.0003445429,0.0001399659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05314535,0.00001014945,0.9441267,0.00001024838,0.0009189535,0.0008551403,0.00008606695,0.0003787243,0.0004687014],"genre_scores_gemma":[0.9794058,0.00001367151,0.01981845,0.00006975897,0.0004959841,0.0001359026,0.00001035699,0.00004223739,0.000007894124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9262604,"threshold_uncertainty_score":0.7228253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07246992723042624,"score_gpt":0.2895721740420723,"score_spread":0.217102246811646,"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."}}