{"id":"W2893913719","doi":"10.36001/phmconf.2018.v10i1.495","title":"Ensemble Learning Based Surrogate Modeling for Gas Turbine Blisk Temperature Predictions","year":2018,"lang":"en","type":"article","venue":"Annual Conference of the PHM Society","topic":"Turbomachinery Performance and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Life Prediction Technologies (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Surrogate model; Computer science; Computational fluid dynamics; Computational complexity theory; Ensemble forecasting; Ensemble learning; Artificial intelligence; Machine learning; Algorithm; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001462352,0.0001239033,0.0001279093,0.00001872062,0.0002591666,0.00003855605,0.0001748145,0.0001063801,0.00002658338],"category_scores_gemma":[0.00003770749,0.00009459745,0.0001499978,0.0001733965,0.00006119734,0.0002628059,0.00002953245,0.0002210808,0.000002843955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002375951,"about_ca_system_score_gemma":0.0000512125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001120408,"about_ca_topic_score_gemma":0.00001445064,"domain_scores_codex":[0.9993836,0.00001601473,0.0001633076,0.0001225479,0.0001198786,0.0001946544],"domain_scores_gemma":[0.9993317,0.0000293464,0.00004112356,0.0001737092,0.0003898808,0.00003423768],"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":[0.00001103184,0.00001253952,0.0002475214,0.00005435476,0.00003410068,2.702144e-8,0.002930201,0.9876648,0.005974135,0.00005338978,0.002753508,0.0002644428],"study_design_scores_gemma":[0.0003070564,0.00006475486,0.0000884714,0.00005185961,0.00003014506,7.697091e-7,0.0006947804,0.9891176,0.008800855,0.00009843749,0.000639172,0.0001060907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8708497,0.00005951943,0.1268794,0.000332875,0.0004756078,0.0002836736,0.0001021839,0.0002356765,0.0007813647],"genre_scores_gemma":[0.9969311,0.0000475722,0.002354278,0.00007882866,0.0002003571,0.0000205632,0.00004419619,0.00002192275,0.0003011611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1260815,"threshold_uncertainty_score":0.3857572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01493897607389456,"score_gpt":0.2224616100307671,"score_spread":0.2075226339568725,"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."}}