{"id":"W2970530649","doi":"10.1109/icphm.2019.8819433","title":"Data-Driven Model Selection Study for Long-Term Performance Deterioration of Gas Turbines","year":2019,"lang":"en","type":"article","venue":"","topic":"Technical Engine Diagnostics and Monitoring","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Life Prediction Technologies (Canada)","funders":"","keywords":"Term (time); Gas turbines; Computer science; Reliability engineering; Selection (genetic algorithm); Power (physics); Degradation (telecommunications); Performance enhancement; Data modeling; Automotive engineering; Engineering; Machine learning; Mechanical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006573189,0.001599726,0.001233541,0.0009566639,0.0006061335,0.001090619,0.001184782,0.001100493,0.001442553],"category_scores_gemma":[0.009844444,0.0006252561,0.001832816,0.0004592503,0.0004207104,0.0005882972,0.0007948739,0.001618942,0.0002019913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008155711,"about_ca_system_score_gemma":0.001307868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01135099,"about_ca_topic_score_gemma":0.006862914,"domain_scores_codex":[0.9984608,0.001127873,0.00006521907,0.0001389508,0.0001012761,0.0001058482],"domain_scores_gemma":[0.985577,0.01258739,0.0004952624,0.0002159858,0.0009854984,0.0001388745],"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":[0.0003158173,0.000248099,0.008037213,0.0001294677,0.0003077674,0.0001556527,0.00007985409,0.9811288,0.0009957167,0.0005752319,0.0002844139,0.007742079],"study_design_scores_gemma":[0.00001481581,0.0001186087,0.00118647,0.000005912016,0.00004258475,0.00001052023,0.0000288467,0.9979832,0.0003753554,0.0001525622,0.0000742585,0.000006767606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.824629,0.0007950472,0.1712248,0.0006188159,0.00005466476,0.0002453889,0.000711296,0.0005047203,0.001216185],"genre_scores_gemma":[0.9869788,0.0001329842,0.01108888,0.00005449491,0.00001633278,0.0001817186,0.000897109,0.00002845007,0.000621217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01135099,"threshold_uncertainty_score":0.03476274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02948228995069386,"score_gpt":0.274788765689283,"score_spread":0.2453064757385891,"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."}}