{"id":"W4388496238","doi":"10.1002/cjce.25129","title":"A novel fault detection scheme for a nonlinear dynamic process based on generalized non‐negative matrix projection‐maximum mean discrepancy: Application on the <scp>DAMADICS</scp> benchmark process","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Principal component analysis; Fault detection and isolation; Residual; Kernel principal component analysis; Non-negative matrix factorization; Subspace topology; Algorithm; Projection (relational algebra); Kernel (algebra); Computer science; Benchmark (surveying); Nonlinear system; Pattern recognition (psychology); Autocorrelation; Process (computing); Mathematics; Artificial intelligence; Matrix decomposition; Kernel method; Statistics; Support vector machine; Eigenvalues and eigenvectors","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":[0.0008349224,0.0006316042,0.0008128224,0.0007436883,0.0004540363,0.0006202257,0.0007129011,0.0006431395,0.0008255524],"category_scores_gemma":[0.002023213,0.0002403207,0.0004692513,0.0004998811,0.0005621483,0.0007299908,0.0007287199,0.0008859577,0.0001796492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004535297,"about_ca_system_score_gemma":0.0007789002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002505066,"about_ca_topic_score_gemma":0.001774808,"domain_scores_codex":[0.9995254,0.00008836364,0.00003054686,0.0001379016,0.0001824034,0.00003542386],"domain_scores_gemma":[0.9992502,0.0002614663,0.0001338098,0.00007740097,0.0002352749,0.0000418096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006743966,0.0001884707,0.006156042,0.0003545173,0.00008960776,0.0003722515,0.0002510019,0.3590071,0.08290425,0.008231007,0.001586973,0.5401843],"study_design_scores_gemma":[0.000007115218,0.0000485829,0.0005437105,0.000003738267,0.000003838401,0.00003910344,0.00000834052,0.9926843,0.005787736,0.0005522587,0.0003114706,0.00000975035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04956193,0.0001716476,0.948894,0.0001281392,0.00003733127,0.00003540891,0.00003057158,0.0005489789,0.0005921013],"genre_scores_gemma":[0.7190526,0.0001033598,0.2798308,0.00004154585,0.00002064338,0.00004615129,0.00007910241,0.00003196023,0.0007939289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002505066,"threshold_uncertainty_score":0.004980981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00706212975053772,"score_gpt":0.2298473321318352,"score_spread":0.2227852023812975,"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."}}