{"id":"W3022837682","doi":"10.1016/j.cherd.2020.03.031","title":"Integrating dynamic neural network models with principal component analysis for adaptive model predictive control","year":2020,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Marshall Aid Commemoration Commission","keywords":"Principal component analysis; Computer science; Model predictive control; Recurrent neural network; Artificial neural network; Constraint (computer-aided design); Component (thermodynamics); Set (abstract data type); Artificial intelligence; Control theory (sociology); Machine learning; Control (management); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000679162,0.0008126744,0.000769496,0.0004558722,0.0003519657,0.0008394927,0.0008218188,0.0007428671,0.001359851],"category_scores_gemma":[0.002974238,0.0005670886,0.0004858706,0.0007159864,0.0003991493,0.001246574,0.0008078935,0.001302111,0.0004131798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004038182,"about_ca_system_score_gemma":0.0006515107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01101486,"about_ca_topic_score_gemma":0.009837038,"domain_scores_codex":[0.9997227,0.00009226886,0.00001636204,0.00005388039,0.0000874521,0.00002741654],"domain_scores_gemma":[0.9993919,0.0003371937,0.00005323323,0.00005062082,0.0001546157,0.00001236079],"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":[0.00003717302,0.00002581691,0.0001807996,0.00004011508,0.00004483546,0.00001729422,0.00001634313,0.9519264,0.0009868158,0.003499257,0.0003799851,0.04284519],"study_design_scores_gemma":[9.615273e-7,0.000003160581,0.00002971546,0.00000104127,0.000002075533,0.000001019713,4.901265e-7,0.9989012,0.00008961062,0.0009110859,0.00005785277,0.000001655133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008635833,0.0003226112,0.9894671,0.00009234894,0.00006363104,0.00001651375,0.00002286708,0.0003284114,0.001050715],"genre_scores_gemma":[0.802126,0.0007238746,0.192956,0.0000740856,0.0001246442,0.0001686282,0.0001565193,0.0001750871,0.003495015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01101486,"threshold_uncertainty_score":0.02190149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008995815501247506,"score_gpt":0.18043167871622,"score_spread":0.1714358632149725,"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."}}