{"id":"W4393353234","doi":"10.3390/en17071665","title":"Using Deep Learning to Detect Anomalies in On-Load Tap Changer Based on Vibro-Acoustic Signal Features","year":2024,"lang":"en","type":"article","venue":"Energies","topic":"Mechanical Failure Analysis and Simulation","field":"Engineering","cited_by":13,"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":"Tap changer; SIGNAL (programming language); Computer science; Artificial intelligence; Acoustics; Speech recognition; Pattern recognition (psychology); Engineering; Electrical engineering; Physics; Voltage; Transformer","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":[0.0001395148,0.0001517262,0.0001695661,0.0002818238,0.00004798431,0.0001030933,0.00006636235,0.00007747764,0.0001692022],"category_scores_gemma":[0.00005548325,0.0001335379,0.00007247906,0.0003792518,0.000006289308,0.00006001602,0.00001430832,0.0001961071,0.00003520021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000117888,"about_ca_system_score_gemma":0.00001134585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000317703,"about_ca_topic_score_gemma":0.0001563769,"domain_scores_codex":[0.9991902,0.00004079096,0.0001455993,0.0002006165,0.0002214096,0.0002013689],"domain_scores_gemma":[0.9996238,0.0001921584,0.000009591183,0.0001114802,0.00001613757,0.00004684155],"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":[0.00001346346,0.000004479431,0.00001489508,0.00003363099,0.00001644091,0.00002459346,0.0001506176,0.9358583,0.05259346,0.0001677483,0.00005639967,0.01106599],"study_design_scores_gemma":[0.00007416621,0.00007547594,0.000322958,0.0001430987,0.00002315916,6.175164e-7,0.00005795918,0.9822562,0.01523862,0.00005409143,0.001587985,0.0001656713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9225257,0.001212161,0.07327597,0.0001080656,0.0003572034,0.0001445518,0.000003126342,0.0005171162,0.001856112],"genre_scores_gemma":[0.9976377,0.00001091115,0.001905708,0.00009182785,0.000161079,0.00002045354,0.000005401717,0.0000329363,0.0001340121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07511198,"threshold_uncertainty_score":0.5445517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411241772290899,"score_gpt":0.2448515682257297,"score_spread":0.2307391505028207,"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."}}