{"id":"W4408358637","doi":"10.1109/access.2025.3550097","title":"Convolutional Variational Autoencoder for Anomaly Detection in On-Load Tap Changers","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Power System Reliability and Maintenance","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec; Université du Québec à Chicoutimi","funders":"Natural Sciences and Engineering Research Council of Canada; Hydro-Québec","keywords":"Autoencoder; Computer science; Anomaly detection; Convolutional code; Pattern recognition (psychology); Artificial intelligence; Convolutional neural network; Anomaly (physics); Algorithm; Decoding methods; Deep learning; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002003457,0.00008661844,0.0001105915,0.0001138493,0.0000416669,0.00003352078,0.0001510277,0.00007868726,0.00001616717],"category_scores_gemma":[0.00006606187,0.00009073008,0.00004110234,0.0002130706,0.00001649977,0.0001877285,0.00001047614,0.00008236095,0.00001140066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003510045,"about_ca_system_score_gemma":0.00006654753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007790354,"about_ca_topic_score_gemma":0.0003438704,"domain_scores_codex":[0.999378,0.00001354358,0.0001714964,0.0001569544,0.0001061101,0.0001738945],"domain_scores_gemma":[0.9996548,0.0001160523,0.00002002419,0.0001160577,0.00007128158,0.00002172792],"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":[0.0003612447,0.0003345781,0.008013665,0.001414761,0.0002527299,0.00000995221,0.000555577,0.9048204,0.01037689,0.03020927,0.0266633,0.01698764],"study_design_scores_gemma":[0.001329645,0.00004053487,0.08799509,0.0001945591,0.00001540987,0.000002620259,0.00001753639,0.8685923,0.00960516,0.004858682,0.02707594,0.0002725286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0845343,0.0001645456,0.9005296,0.0003293449,0.00554622,0.0007462848,0.00005618078,0.0002217551,0.007871744],"genre_scores_gemma":[0.9986829,0.000006513383,0.0002543553,0.0001798503,0.0001027752,0.0004582175,0.000004732326,0.000007983789,0.0003026518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9141486,"threshold_uncertainty_score":0.3699865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01568750961618474,"score_gpt":0.2708188849191246,"score_spread":0.2551313753029398,"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."}}