{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001562338,0.0002798708,0.000253615,0.0002085798,0.0002798046,0.00004722752,0.00009481753,0.0003464469,0.0002030726],"category_scores_gemma":[0.000007271199,0.000298794,0.00007898661,0.0003324885,0.00007321372,0.0003521064,6.238061e-7,0.001254486,0.00002620024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002725517,"about_ca_system_score_gemma":0.00008089597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000162807,"about_ca_topic_score_gemma":0.0003561938,"domain_scores_codex":[0.9985126,0.00004520393,0.0003900842,0.0002919204,0.0002202772,0.0005399741],"domain_scores_gemma":[0.9996156,0.00008453292,0.00002759941,0.0001235736,0.00004603493,0.0001027217],"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":[0.0005146489,0.0001673439,0.00001646024,0.000006671848,0.0001884431,0.000002744299,0.002463229,0.9861289,0.00178549,0.0004022785,0.00008671635,0.008237117],"study_design_scores_gemma":[0.002119805,0.001188402,0.000009767886,0.00009838612,0.00005559377,0.00001278191,0.0002315112,0.9822611,0.002622577,0.0002416788,0.01077937,0.0003790802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3670084,0.0004800215,0.6232071,0.0001797049,0.00130574,0.000694954,0.0002332846,0.0004684577,0.006422333],"genre_scores_gemma":[0.9981251,0.001482237,0.0001258783,0.00004385188,0.00008298275,0.00002605758,0.0000132511,0.0000688596,0.00003177655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6311167,"threshold_uncertainty_score":0.9999464,"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."}}