{"id":"W4379229446","doi":"10.23977/jeeem.2023.060302","title":"Condition Evaluation and Fault Diagnosis of Power Transformer Based on GAN-CNN","year":2023,"lang":"en","type":"article","venue":"Journal of Electrotechnology Electrical Engineering and Management","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Prognostics; Transformer; Reliability engineering; Computer science; Convolutional neural network; Artificial neural network; Fault (geology); Data mining; Condition monitoring; Rough set; Artificial intelligence; Engineering; Electrical engineering; Voltage","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003187655,0.0001236871,0.0001980453,0.0007947326,0.00002497571,0.00001008431,0.00006228109,0.0001005779,0.000007920803],"category_scores_gemma":[0.00005600059,0.0001169076,0.00004590346,0.0005395629,0.00001884644,0.0000711398,0.000002816373,0.0002445724,0.000001226286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006198744,"about_ca_system_score_gemma":0.000008509758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.706793e-7,"about_ca_topic_score_gemma":2.423838e-7,"domain_scores_codex":[0.9991484,0.00001013879,0.0002975635,0.00009575734,0.0002288285,0.0002193661],"domain_scores_gemma":[0.9996862,0.00009224763,0.00004742154,0.0000711165,0.00005808697,0.00004491252],"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":[0.000107441,0.0001738057,0.0004336808,0.0004721777,0.0005383025,0.00004736775,0.00009161576,0.7618545,0.03777109,0.01480245,0.001525717,0.1821819],"study_design_scores_gemma":[0.001502495,0.001262254,0.0109088,0.0001547219,0.0001857007,0.00001830113,0.00001162221,0.9278245,0.05312134,0.001122998,0.003682821,0.0002044228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8973711,0.001643956,0.09827788,0.0009393843,0.0002195631,0.0005544004,0.0000049949,0.0002355709,0.0007531986],"genre_scores_gemma":[0.9947672,0.004845003,0.0002888855,0.00002443914,0.00001183534,0.00003796264,0.000004169875,0.00001756827,0.000002922324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1819774,"threshold_uncertainty_score":0.4767354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005570028874903946,"score_gpt":0.2207605108710876,"score_spread":0.2151904819961836,"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."}}