{"id":"W3130269948","doi":"10.1007/s10845-021-01742-x","title":"Fault classification in the process industry using polygon generation and deep learning","year":2021,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Resources Canada","keywords":"Preprocessor; Artificial intelligence; Polygon (computer graphics); Computer science; Machine learning; Data pre-processing; Pattern recognition (psychology); Data mining; Feature extraction; Benchmark (surveying); Process (computing); Engineering","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":[0.0003968689,0.0005423912,0.0005249272,0.001342655,0.000332282,0.0006861727,0.0008179593,0.000890659,0.001761929],"category_scores_gemma":[0.00132505,0.0002919476,0.0006017284,0.0008511936,0.0003449245,0.000753248,0.0005345864,0.0006221001,0.0003404469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009432381,"about_ca_system_score_gemma":0.0007504259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01444766,"about_ca_topic_score_gemma":0.01080838,"domain_scores_codex":[0.9997862,0.0000313504,0.00001153993,0.00005836986,0.00005954733,0.00005292493],"domain_scores_gemma":[0.9993485,0.0002592928,0.00006960247,0.00007101378,0.0002090103,0.00004266847],"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":[0.000692969,0.0002261542,0.01082942,0.00007963183,0.00004813039,0.0002535146,0.00007213483,0.6259478,0.007309153,0.002210011,0.002931294,0.3493997],"study_design_scores_gemma":[0.00000276971,0.00001471861,0.0003959134,0.000001087924,0.000002566929,0.000007967524,0.000006096952,0.9979616,0.001018894,0.0005103404,0.00007625331,0.000001822203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4899848,0.0005506572,0.5027363,0.0006537747,0.0001495056,0.00007984947,0.000493197,0.002627873,0.002724086],"genre_scores_gemma":[0.9616348,0.00007014446,0.03686367,0.00003199971,0.00001764851,0.00001099139,0.0003055526,0.00003729101,0.001027803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01444766,"threshold_uncertainty_score":0.02872711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03003004831766434,"score_gpt":0.2701164868728682,"score_spread":0.2400864385552039,"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."}}