{"id":"W2413557228","doi":"10.1016/j.ifacol.2015.09.005","title":"Soft Sensor Model Maintenance: A Case Study in Industrial Processes∗∗The authors would like to acknowledge the support from the DOW chemical company and the natural sciences and engineering research council of Canada (NSERC).","year":2015,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Soft sensor; Partial least squares regression; Process (computing); Kalman filter; Data mining; Computer science; Set (abstract data type); Engineering; Industrial engineering; Machine learning; Artificial intelligence; Control engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003469303,0.0001752983,0.0002676705,0.00003541973,0.0002207921,0.0001079922,0.0003570728,0.0001018854,0.000002910213],"category_scores_gemma":[0.001817941,0.00007885363,0.00002302786,0.0005762434,0.0002709302,0.00006706193,0.0001068808,0.0009870229,8.800696e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003602321,"about_ca_system_score_gemma":0.001430368,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.08918914,"about_ca_topic_score_gemma":0.457793,"domain_scores_codex":[0.9980596,0.0001410041,0.0002993045,0.0002410866,0.0008891633,0.0003697849],"domain_scores_gemma":[0.9984005,0.0008163485,0.00003549359,0.0002416417,0.0003848112,0.0001211985],"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":[0.003768325,0.0004720296,0.01021254,0.0004435517,0.0010401,0.0008786178,0.4270217,0.5035527,0.0226121,0.0001978877,0.01584795,0.01395254],"study_design_scores_gemma":[0.002550237,0.00006628488,0.0001741029,0.00005498781,0.00002459611,0.0001813951,0.0514483,0.9430444,0.00009282197,0.000009392836,0.00219402,0.0001595212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945374,0.0006948901,0.00002853143,0.003210379,0.0004056507,0.000942831,0.00004754486,0.00003075574,0.0001020253],"genre_scores_gemma":[0.9992397,0.000006613313,0.0001436959,0.0001153705,0.0002187781,0.00008535638,9.20052e-7,0.0000154516,0.0001740466],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4394917,"threshold_uncertainty_score":0.916876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09478916515296334,"score_gpt":0.2908371682373549,"score_spread":0.1960480030843916,"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."}}