{"id":"W2582860853","doi":"10.1021/acs.iecr.6b01916","title":"Root Cause Diagnosis of Process Fault Using KPCA and Bayesian Network","year":2017,"lang":"en","type":"article","venue":"Industrial & Engineering Chemistry Research","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":149,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Root cause analysis; Computer science; Bayesian network; Root cause; Fault detection and isolation; Process (computing); Data mining; Fault (geology); Artificial intelligence; Kernel principal component analysis; Machine learning; Pattern recognition (psychology); Reliability engineering; Engineering; Kernel method; Support vector machine","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":[0.0005513075,0.0001904334,0.0003079383,0.00006421699,0.000243516,0.0001938711,0.0003763472,0.0003363878,0.0000384314],"category_scores_gemma":[0.0005846696,0.0002068328,0.00005213182,0.0002022491,0.00008965746,0.0001515571,0.00008431315,0.0007717418,0.000002013516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001038927,"about_ca_system_score_gemma":0.00005652325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001530274,"about_ca_topic_score_gemma":0.000007965978,"domain_scores_codex":[0.9984808,0.00002161593,0.0003118837,0.0002378879,0.0004118353,0.0005359673],"domain_scores_gemma":[0.9989985,0.0001342234,0.00005765064,0.0004893756,0.0001156148,0.000204628],"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":[0.00007936962,0.00004198133,0.02414317,0.001156675,0.0003537906,0.00006520996,0.000203724,0.5504425,0.4152068,0.0000195162,0.001556573,0.006730633],"study_design_scores_gemma":[0.001430114,0.00003564532,0.0005752638,0.0006497091,0.00002986477,0.00003549986,0.00008580185,0.5923879,0.3991883,0.00001874343,0.005168754,0.000394422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977502,0.0003692384,0.00008172911,0.00004276427,0.0003966877,0.0002441292,0.00001246714,0.0001432409,0.0009595809],"genre_scores_gemma":[0.9985179,0.00002796382,0.00001387012,5.389705e-7,0.001208499,0.00007486509,0.0000023219,0.00005005808,0.0001040295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04194536,"threshold_uncertainty_score":0.8434396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08120584543658335,"score_gpt":0.342692809834265,"score_spread":0.2614869643976816,"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."}}