{"id":"W2864622186","doi":"10.1109/tie.2018.2860532","title":"Adaptive Power Transformer Lifetime Predictions Through Machine Learning and Uncertainty Modeling in Nuclear Power Plants","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":161,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kinectrics (Canada); Bruce Power (Canada)","funders":"","keywords":"Transformer; Predictive modelling; Computer science; Measurement uncertainty; Boosting (machine learning); Reliability engineering; Engineering; Machine learning; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001349336,0.0005499484,0.0005755117,0.0004467293,0.0002390608,0.0005473035,0.000492329,0.0005337699,0.0002379654],"category_scores_gemma":[0.003009539,0.0003245952,0.000356877,0.0003394108,0.0003133962,0.0006409736,0.0003349124,0.0007577307,0.00006955201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007238721,"about_ca_system_score_gemma":0.0005037911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131633,"about_ca_topic_score_gemma":0.007245316,"domain_scores_codex":[0.9997658,0.00008736675,0.00001631817,0.00005054741,0.00004987235,0.00003015665],"domain_scores_gemma":[0.9985352,0.001049569,0.0001417841,0.00007078917,0.0001639615,0.0000387619],"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":[0.00002271353,0.00001691046,0.0009850821,0.000005943934,0.000005586067,0.00001493011,0.000009115314,0.9934478,0.0002142863,0.0001622959,0.00005932554,0.005056082],"study_design_scores_gemma":[5.092551e-7,0.000002437081,0.0001578924,5.777852e-7,6.263037e-7,8.792244e-7,9.096462e-7,0.9996393,0.00008289766,0.0001048726,0.000008200514,7.967757e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7926041,0.0004171302,0.2049435,0.000338633,0.00002952027,0.00002284256,0.0001180395,0.0003767853,0.001149523],"genre_scores_gemma":[0.9953409,0.00005248509,0.004372465,0.00001160922,0.00000633939,0.000008174471,0.00006021223,0.000006587247,0.0001412055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0131633,"threshold_uncertainty_score":0.02617335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02133401764139877,"score_gpt":0.2266736918634139,"score_spread":0.2053396742220151,"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."}}