{"id":"W2039637288","doi":"10.1115/ipc2010-31016","title":"Neural Network Based Predictive Emission Monitoring Module for a GE LM2500 Gas Turbine","year":2010,"lang":"en","type":"article","venue":"","topic":"Vehicle emissions and performance","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"TransCanada (Canada); Nova Chemicals (Canada)","funders":"","keywords":"NOx; Perceptron; Range (aeronautics); Artificial neural network; Gas compressor; Environmental science; Turbine; Standard deviation; Computer science; Engineering; Statistics; Mechanical engineering; Mathematics; Chemistry; Artificial intelligence; Aerospace 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":[0.0001155546,0.0001414588,0.0001228245,0.00003270359,0.000131985,0.00002761555,0.0001182717,0.0001070885,0.0001364182],"category_scores_gemma":[0.0000136629,0.0001158734,0.00005938099,0.0001161263,0.00001257993,0.0001356376,0.00002025287,0.0002708304,0.00000663478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001763281,"about_ca_system_score_gemma":0.00001269317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005981388,"about_ca_topic_score_gemma":0.000002495301,"domain_scores_codex":[0.9992705,0.000004870214,0.0001544236,0.0001477821,0.0000987623,0.0003236647],"domain_scores_gemma":[0.9995211,0.00006230939,0.00001749208,0.0002126089,0.00003839711,0.0001481002],"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":[0.00008746992,0.00002879284,0.02987219,0.0001156848,0.00002990003,0.000002699425,0.0001036055,0.8374034,0.09795453,0.00004443078,0.01186567,0.02249164],"study_design_scores_gemma":[0.000384695,0.00005160317,0.005637826,0.00003677752,0.000009016391,0.00000221819,0.000008850311,0.9444021,0.04193693,0.00005509408,0.007330291,0.0001446307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981939,0.00007489576,0.01327532,0.00009608766,0.001599539,0.0002324009,0.000009681037,0.0004452651,0.002327874],"genre_scores_gemma":[0.9901792,0.00001103128,0.007742026,0.00002139121,0.001393715,0.00005713881,0.00001060938,0.00003621304,0.0005486218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1069987,"threshold_uncertainty_score":0.472518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009981000069974339,"score_gpt":0.2265298775850774,"score_spread":0.216548877515103,"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."}}