{"id":"W4401781142","doi":"10.1002/cjce.25460","title":"A novel fault diagnosis framework empowered by <scp>LSTM</scp> and attention: A case study on the Tennessee Eastman process","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Preprocessor; Benchmark (surveying); Fault (geology); Process (computing); Sample (material); Data mining; Artificial intelligence; Population; Metric (unit); Fault detection and isolation; Function (biology); Machine learning; Pattern recognition (psychology); 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":[0.0003229407,0.0001925394,0.0002072273,0.0001224424,0.0001047346,0.0002857342,0.0002260869,0.00009661822,0.000009670983],"category_scores_gemma":[0.0002760292,0.0001236962,0.00008855558,0.0003188401,0.00003475711,0.0000759157,0.000008414378,0.0007584864,0.000004850875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001316118,"about_ca_system_score_gemma":0.00005555127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004743781,"about_ca_topic_score_gemma":0.0002182008,"domain_scores_codex":[0.9990681,0.00001566682,0.0003029301,0.0001201139,0.0002115419,0.0002816934],"domain_scores_gemma":[0.9990106,0.0004236932,0.00003526054,0.0001545939,0.00005115808,0.0003246457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005294726,0.0005062918,0.004027318,0.002822069,0.007620226,0.02012431,0.0814461,0.2608325,0.5651721,0.00351012,0.04105547,0.01283057],"study_design_scores_gemma":[0.002613922,0.0005868303,0.0005130022,0.003927726,0.0006910208,0.03546542,0.02091773,0.8711659,0.03000285,0.0003276325,0.03280489,0.0009830722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954802,0.001877361,0.001089304,0.0005814941,0.0006140739,0.0002191004,0.00001454334,0.00006233699,0.00006156985],"genre_scores_gemma":[0.9995101,0.000003999198,0.00001325699,0.00005559858,0.0002973506,0.00005327482,3.58814e-7,0.00004558676,0.00002043602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6103334,"threshold_uncertainty_score":0.5044186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00896921442482515,"score_gpt":0.2160725010516339,"score_spread":0.2071032866268087,"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."}}