{"id":"W4390982491","doi":"10.20944/preprints202401.1266.v1","title":"Acoustic-Based Online Monitoring of Cooling Fan Malfunction in Air-Forced Transformers Using Learning Techniques","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Transformer; Overheating (electricity); Computer science; Random forest; Convolutional neural network; Feature extraction; Hyperparameter; Interpretability; Classifier (UML); Artificial intelligence; Machine learning; Pattern recognition (psychology); Engineering; Electrical 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005922706,0.0004418379,0.0005795667,0.0006806689,0.0000508152,0.00001598772,0.0002247502,0.0004922111,0.00004109827],"category_scores_gemma":[0.0001430973,0.0005219835,0.0002390369,0.000353688,0.00004567568,0.0001178384,0.0001304665,0.001787147,0.00001567828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004681968,"about_ca_system_score_gemma":0.0001352851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003307401,"about_ca_topic_score_gemma":0.00003034926,"domain_scores_codex":[0.9974599,0.00004450069,0.001220279,0.0005403167,0.0003254885,0.0004095079],"domain_scores_gemma":[0.9991585,0.0000917985,0.0002268766,0.0003260202,0.0001110153,0.00008580483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003339567,0.00004237488,0.1080946,0.00163911,0.00007045318,0.000006537132,0.0004067103,0.6683029,0.2198741,0.000007709569,2.695846e-7,0.001521769],"study_design_scores_gemma":[0.0002569306,0.00002453199,0.08764791,0.003217734,0.0001538912,0.000001929892,0.0001791096,0.3789796,0.52884,0.000160052,0.00007893322,0.0004594011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9348614,0.0002860362,0.06160278,0.00001866495,0.001161531,0.0006221015,0.00005174476,0.0006500738,0.0007457175],"genre_scores_gemma":[0.9965101,0.0004746815,0.002468731,0.000005458757,0.0001899808,0.00007221831,0.0001274395,0.0001352562,0.0000161328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3089659,"threshold_uncertainty_score":0.9997232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0675662201282503,"score_gpt":0.3210587198525179,"score_spread":0.2534924997242676,"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."}}