{"id":"W4416509088","doi":"10.1016/j.ress.2025.111979","title":"A generative modeling method to quantify the long-term benefit of neural-network-based RUL predictions to maintenance","year":2025,"lang":"en","type":"article","venue":"Reliability Engineering & System Safety","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Hong Kong Polytechnic University; National Natural Science Foundation of China; Ministry of Education - Singapore; National University of Singapore","keywords":"Prognostics; Component (thermodynamics); Condition-based maintenance; Key (lock); Artificial neural network; Feature (linguistics); Maintenance actions; Predictive maintenance; Focus (optics)","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":[0.002312318,0.0007571984,0.0006467341,0.0009757752,0.0003359444,0.0007039614,0.001402216,0.001104597,0.001522053],"category_scores_gemma":[0.006442628,0.0004180801,0.0008192554,0.0007351951,0.0008611776,0.001186924,0.0009712984,0.001126107,0.0002143661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001181176,"about_ca_system_score_gemma":0.0007179279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004786918,"about_ca_topic_score_gemma":0.006308016,"domain_scores_codex":[0.9994718,0.0001647222,0.00002229714,0.0001085464,0.0001745586,0.00005812978],"domain_scores_gemma":[0.9959459,0.002982575,0.0003184401,0.0003837591,0.0002753437,0.00009409714],"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":[0.00006565914,0.00004856949,0.001306468,0.00002242307,0.00005858934,0.00004027896,0.00002762441,0.96287,0.001981814,0.0114734,0.0003355907,0.0217696],"study_design_scores_gemma":[0.000001673307,0.000007621711,0.0001746704,0.000002039262,0.000006895518,0.000007477602,0.0000010478,0.9968826,0.0003049186,0.002567213,0.00004062449,0.000003327577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05610342,0.0002059084,0.9407687,0.0002230362,0.00004384018,0.00003465204,0.0001595896,0.0006113107,0.001849466],"genre_scores_gemma":[0.9504877,0.0001192814,0.04734112,0.000102916,0.00004781312,0.00006271097,0.0002263421,0.00009386976,0.001518251],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004786918,"threshold_uncertainty_score":0.01222885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008756641937136746,"score_gpt":0.2758870015198506,"score_spread":0.2671303595827138,"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."}}