{"id":"W3158079487","doi":"10.1002/cjce.24153","title":"Chemical process fault diagnosis based on a combined deep learning method","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Deep learning; Convolutional neural network; Computer science; Artificial intelligence; Process (computing); Recurrent neural network; Fault (geology); Pattern recognition (psychology); Identification (biology); Artificial neural network; Raw data; Chemical process; Machine learning; Data mining; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002714838,0.0001760437,0.0002921878,0.0001210371,0.00005450198,0.00008394216,0.0002310395,0.0001243605,0.00007428916],"category_scores_gemma":[0.0005793204,0.0001487192,0.000156182,0.0003267739,0.00001908526,0.00005713726,0.000005059447,0.000814483,0.000006208082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002636652,"about_ca_system_score_gemma":0.0001441951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007897968,"about_ca_topic_score_gemma":0.00005974479,"domain_scores_codex":[0.9989511,0.00003423709,0.0003406305,0.0001048035,0.0002365023,0.0003326611],"domain_scores_gemma":[0.9989687,0.0002601497,0.00005403331,0.0001423949,0.0001334006,0.0004413685],"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":[0.00001248348,0.000007675215,0.00005802422,0.00007136323,0.00007126362,0.000100189,0.0001866273,0.9187692,0.07750744,0.00006030254,0.0001085981,0.003046773],"study_design_scores_gemma":[0.0005254772,0.00001991906,0.00001272521,0.0001320594,0.00002853717,0.0001283787,0.0000342966,0.7222885,0.2736379,0.00001909948,0.003013739,0.0001593526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9632893,0.001675026,0.0286427,0.001948578,0.001678887,0.0002582491,0.000008946395,0.0002986382,0.00219963],"genre_scores_gemma":[0.9989668,0.000001972366,0.0005930427,0.000123252,0.0002362935,0.00001812275,0.000002521677,0.00004489485,0.00001308337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1964807,"threshold_uncertainty_score":0.6064593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005760178404098535,"score_gpt":0.2068182229266236,"score_spread":0.2010580445225251,"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."}}