{"id":"W4387353314","doi":"10.1016/j.jlp.2023.105185","title":"A method for the early prediction of abnormal conditions in chemical processes combined with physical knowledge and the data-driven model","year":2023,"lang":"en","type":"article","venue":"Journal of Loss Prevention in the Process Industries","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Interpretability; Generalizability theory; Variable (mathematics); Ranking (information retrieval); Key (lock); Process (computing); Computer science; Chemical process; Data mining; Partial least squares regression; Time series; Multivariate statistics; Feature (linguistics); Machine learning; Artificial intelligence; Engineering; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001092181,0.00008800456,0.0002186442,0.00009904033,0.00007221144,0.0000426955,0.000324219,0.00006050882,7.258591e-7],"category_scores_gemma":[0.0001791359,0.00004262055,0.00003412988,0.0006102885,0.0001336899,0.0003400906,0.00002419443,0.0003438379,2.273521e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001722841,"about_ca_system_score_gemma":0.0001117346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004746732,"about_ca_topic_score_gemma":0.00002757688,"domain_scores_codex":[0.9991505,0.00009763448,0.0003766317,0.000076383,0.0001906529,0.0001082291],"domain_scores_gemma":[0.9989056,0.000609605,0.0001779086,0.0001258955,0.0001640345,0.00001693395],"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":[0.004066826,0.0007022687,0.005475528,0.002439377,0.0009192447,0.000007690544,0.05639128,0.906171,0.001425931,0.003562269,0.002264497,0.01657408],"study_design_scores_gemma":[0.003982211,0.0001635104,0.001736281,0.0003403615,0.0001300361,0.0000581183,0.00386464,0.9831488,0.001134571,0.005273168,0.0001015992,0.00006672758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9751307,0.0002989204,0.02283688,0.0007618884,0.00007923096,0.0007252668,0.00007594145,0.00002925479,0.00006191034],"genre_scores_gemma":[0.999552,0.00004731216,0.00006617537,0.000004763066,0.00009682753,0.0001808634,0.000007586041,0.00000966642,0.00003483521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07697777,"threshold_uncertainty_score":0.1738016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03464610266895555,"score_gpt":0.3190408007117392,"score_spread":0.2843946980427836,"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."}}