{"id":"W4385992970","doi":"10.1515/corrrev-2023-0027","title":"Image recognition model of pipeline magnetic flux leakage detection based on deep learning","year":2023,"lang":"en","type":"article","venue":"Corrosion Reviews","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baker Hughes (Canada)","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Magnetic flux leakage; Artificial intelligence; Pipeline (software); Computer science; Deep learning; Pattern recognition (psychology); Object detection; Cognitive neuroscience of visual object recognition; Leakage (economics); Computer vision; Feature extraction; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002881805,0.0006035077,0.000502955,0.0005761434,0.0002185284,0.0005440408,0.0009511136,0.0006305072,0.002295193],"category_scores_gemma":[0.0003789799,0.000277193,0.0008292988,0.0003416913,0.0002823742,0.0005444961,0.0003731789,0.0005852534,0.0005616936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000929084,"about_ca_system_score_gemma":0.0007535021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01855779,"about_ca_topic_score_gemma":0.008999311,"domain_scores_codex":[0.9998288,0.00001473878,0.000009318445,0.00006413113,0.00005455918,0.0000284195],"domain_scores_gemma":[0.9998847,0.00001887176,0.00001434087,0.000008513514,0.00006646808,0.000007055273],"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":[0.0001532581,0.00007875205,0.002373958,0.0001072077,0.00006651045,0.0001520266,0.00005903478,0.8179616,0.02075729,0.003438104,0.002211223,0.1526411],"study_design_scores_gemma":[0.000001806242,0.00001054104,0.0002276254,0.00000198528,0.000004414766,0.000009718024,0.000001459067,0.9982719,0.001136863,0.0001943935,0.0001365323,0.000002657472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07192974,0.0007236392,0.9181942,0.0004498879,0.0001374777,0.00006279899,0.0002116024,0.002002675,0.006287999],"genre_scores_gemma":[0.9434897,0.0004666575,0.0450852,0.0001487596,0.00003742256,0.0001129748,0.0003505164,0.00005006393,0.01025877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01855779,"threshold_uncertainty_score":0.03689957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03888941616402689,"score_gpt":0.2638529719466322,"score_spread":0.2249635557826053,"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."}}