{"id":"W2747498949","doi":"10.1002/cjce.22994","title":"A data‐driven fault detection approach with performance optimization","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Kernel (algebra); Realization (probability); Fault detection and isolation; Representation (politics); Computer science; Fault (geology); Gradient descent; Scheme (mathematics); Data-driven; External Data Representation; Algorithm; Kernel method; Decomposition; Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001171792,0.001025054,0.0009301304,0.0004296491,0.0002627747,0.001104306,0.001061738,0.0009361209,0.001364985],"category_scores_gemma":[0.002994666,0.0004311929,0.0007135597,0.0004457928,0.0007719263,0.00104711,0.001324286,0.0013901,0.0003253924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007838148,"about_ca_system_score_gemma":0.001077916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001498349,"about_ca_topic_score_gemma":0.0007776527,"domain_scores_codex":[0.9990413,0.0002828798,0.00005547069,0.0001841121,0.0003402758,0.00009591498],"domain_scores_gemma":[0.999036,0.0004193609,0.0001302953,0.0001150144,0.0002695862,0.00002974195],"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":[0.00008332367,0.00007173714,0.0003024307,0.0001536479,0.00004600017,0.00006884782,0.00009356144,0.884216,0.009319579,0.04625594,0.0006943808,0.05869449],"study_design_scores_gemma":[0.00000489854,0.00004687423,0.00005500646,0.000004484569,0.000005037849,0.00001223152,0.000004648756,0.9915131,0.002075298,0.005872867,0.0003982381,0.000007332194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002995976,0.00004554636,0.9961229,0.00005676288,0.000008673663,0.00001436126,0.000009150525,0.0000977566,0.000648818],"genre_scores_gemma":[0.7942,0.0001890447,0.2025353,0.0001210267,0.00005598066,0.0001937327,0.0001334634,0.0001023678,0.002469109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001498349,"threshold_uncertainty_score":0.006197155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01118127782259174,"score_gpt":0.1812152737599196,"score_spread":0.1700339959373278,"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."}}