{"id":"W2601232184","doi":"10.1002/cjce.22852","title":"Combination of KPCA and causality analysis for root cause diagnosis of industrial process fault","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Kernel principal component analysis; Process (computing); Causality (physics); Root cause; Fault (geology); Root cause analysis; Fault detection and isolation; Principal component analysis; Kernel (algebra); Nonlinear system; Computer science; Data mining; Artificial intelligence; Econometrics; Pattern recognition (psychology); Engineering; Reliability engineering; Mathematics; Kernel method; Support vector machine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.001293521,0.001072198,0.000935282,0.002236511,0.0004269081,0.0008424821,0.0004974828,0.0005499148,0.001019224],"category_scores_gemma":[0.004020236,0.0003762582,0.0007957815,0.001068422,0.0004076,0.0008235862,0.0006051297,0.0007744355,0.0001998972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008720663,"about_ca_system_score_gemma":0.001047301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008906491,"about_ca_topic_score_gemma":0.005458252,"domain_scores_codex":[0.9991204,0.0002959079,0.00006508322,0.0001781099,0.0002564044,0.00008411157],"domain_scores_gemma":[0.9978151,0.001346673,0.0002577302,0.000107887,0.00041728,0.00005520988],"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":[0.0003567279,0.0001454484,0.007446326,0.0002146888,0.0002480432,0.0003412839,0.0001129614,0.7230869,0.01172215,0.005758868,0.0006776883,0.2498888],"study_design_scores_gemma":[0.000003823166,0.00002179138,0.0009782854,0.000002498362,0.00001283124,0.00002522416,0.000007926915,0.9966947,0.001241192,0.0008748928,0.0001289386,0.000007956924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05932003,0.0003202012,0.9377494,0.0001329071,0.00002868299,0.00007502029,0.0000970844,0.00100479,0.001271948],"genre_scores_gemma":[0.891292,0.0001647318,0.1076626,0.00001761692,0.00001533726,0.00004492403,0.00009547522,0.00004232911,0.0006650632],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008906491,"threshold_uncertainty_score":0.01770926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02130209541132796,"score_gpt":0.2385156354674425,"score_spread":0.2172135400561145,"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."}}