{"id":"W4390457793","doi":"10.1016/j.ijpvp.2023.105123","title":"Development of a convolutional neural network model to predict the size and location of corrosion defects on pipelines based on magnetic flux leakage signals","year":2023,"lang":"en","type":"article","venue":"International Journal of Pressure Vessels and Piping","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Western University","keywords":"Magnetic flux leakage; Convolutional neural network; Pipeline transport; Leakage (economics); Parametric statistics; Corrosion; Artificial neural network; Engineering; Acoustics; Pipeline (software); Finite element method; Structural engineering; Computer science; Pattern recognition (psychology); Artificial intelligence; Materials science; Mechanical engineering; Mathematics; Electrical engineering; Metallurgy; Physics; Statistics; Electromagnetic coil","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004498277,0.00009948629,0.0001479053,0.0001308207,0.00004109771,0.00002150726,0.0001602903,0.0000368955,0.00000523276],"category_scores_gemma":[0.0003177442,0.00007676657,0.00002411739,0.0001694207,0.00003664139,0.00007264238,0.00004118048,0.0001227536,3.218689e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001981536,"about_ca_system_score_gemma":0.00005305219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001632734,"about_ca_topic_score_gemma":0.000001385281,"domain_scores_codex":[0.9990681,0.0000358234,0.0003603796,0.00008577373,0.0003549822,0.00009487566],"domain_scores_gemma":[0.9987413,0.0005681064,0.0001563472,0.00006017619,0.0004339513,0.00004007273],"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":[0.0001291836,0.00001789449,0.00195743,0.0001120516,0.00003465223,0.000002923736,0.0003664442,0.8864953,0.1080598,0.0005862282,0.0005506797,0.001687445],"study_design_scores_gemma":[0.0004949247,0.0002410456,0.05239198,0.001883312,0.00004164564,0.00001763548,0.00003039463,0.9229663,0.01731794,0.004387854,0.00009622693,0.0001307143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.936674,0.0003293587,0.06212437,0.0001886291,0.0003214261,0.0001561831,0.00001161884,0.00004704871,0.0001473453],"genre_scores_gemma":[0.9726689,0.00001996778,0.02710857,0.00006313853,0.0001109171,0.000005621974,0.000002611754,0.00001264673,0.000007576268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09074181,"threshold_uncertainty_score":0.313045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02133615199455679,"score_gpt":0.2588243646645801,"score_spread":0.2374882126700233,"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."}}