{"id":"W4416829045","doi":"10.1016/j.engappai.2025.113256","title":"FlashDetR: A deep learning pipeline for early detection and time estimation of flashover in high-voltage insulators using infrared videos","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"High voltage insulation and dielectric phenomena","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Qatar National Library; Qatar University","keywords":"Arc flash; Detector; Estimator; Deep learning; Pipeline (software); Convolutional neural network; Power (physics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003709804,0.001016582,0.0005072073,0.0006447417,0.0001707578,0.0004013471,0.001254326,0.000597246,0.001900048],"category_scores_gemma":[0.0008600136,0.0003534662,0.0005975256,0.0003768958,0.0001711149,0.0007590012,0.00071715,0.0009690477,0.0008167486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005886579,"about_ca_system_score_gemma":0.0008267573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00814977,"about_ca_topic_score_gemma":0.01082716,"domain_scores_codex":[0.9998684,0.0000118586,0.0000063195,0.00005016053,0.00003518896,0.00002804805],"domain_scores_gemma":[0.999811,0.00004796006,0.00002957888,0.00002955328,0.0000597597,0.0000222772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004638715,0.0004740823,0.00802264,0.0002447871,0.0002549826,0.0003214756,0.00008002184,0.330311,0.04258337,0.001846442,0.01579547,0.5996019],"study_design_scores_gemma":[0.00001045972,0.00006043586,0.0008611754,0.000007020688,0.00001468342,0.00002848514,0.000006919071,0.9909002,0.006397692,0.0007358826,0.0009685456,0.000008576796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08030713,0.001033459,0.8977151,0.0002839699,0.0001268797,0.0001205951,0.001754734,0.01681538,0.00184275],"genre_scores_gemma":[0.7134395,0.000729304,0.270261,0.0003386375,0.00007298589,0.0002161152,0.006167883,0.0003810328,0.008393485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00814977,"threshold_uncertainty_score":0.01620466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00899487579843041,"score_gpt":0.2501187851353023,"score_spread":0.2411239093368719,"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."}}