{"id":"W2034341843","doi":"10.1007/s10845-013-0750-1","title":"Fault diagnosis in power transformers using multi-class logical analysis of data","year":2013,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":68,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Interpretability; Data mining; Artificial neural network; Identification (biology); Computer science; Transformer; Dissolved gas analysis; Artificial intelligence; Fault (geology); Pattern recognition (psychology); Fault detection and isolation; Support vector machine; Machine learning; Engineering","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":[0.00140755,0.0004754199,0.0005474198,0.002143868,0.0006347044,0.001880146,0.0007011931,0.0003886946,0.00121769],"category_scores_gemma":[0.00538068,0.0002029825,0.0005936844,0.00087018,0.0006314733,0.002192636,0.0005512402,0.0005201783,0.0001978991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008338332,"about_ca_system_score_gemma":0.001123097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002296699,"about_ca_topic_score_gemma":0.002892943,"domain_scores_codex":[0.9987788,0.0002636253,0.0001589691,0.0002125789,0.0004513575,0.0001346896],"domain_scores_gemma":[0.9952462,0.003015594,0.0005636651,0.0003679292,0.0006974359,0.0001092325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004409739,0.0008918688,0.04830089,0.0007530431,0.000443699,0.001892239,0.0007464834,0.1672311,0.08163868,0.03346265,0.003020399,0.6572092],"study_design_scores_gemma":[0.00004234471,0.0001736178,0.00319792,0.00003388766,0.0001084171,0.0003508908,0.0001505567,0.9514197,0.02571798,0.01772156,0.001058406,0.00002491341],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1999953,0.0003940362,0.7957091,0.0003060712,0.00008517966,0.0001061577,0.0003944456,0.001395223,0.001614475],"genre_scores_gemma":[0.9285393,0.0001433922,0.07057895,0.00005414086,0.00004342142,0.00004739385,0.000236582,0.00003304701,0.0003237593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002296699,"threshold_uncertainty_score":0.007443905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05617376495831859,"score_gpt":0.2892717134906774,"score_spread":0.2330979485323589,"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."}}