{"id":"W2513688333","doi":"10.1109/icphm.2016.7542876","title":"Developing machine learning-based models to estimate time to failure for PHM","year":2016,"lang":"en","type":"article","venue":"","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; National Research Council Canada","funders":"","keywords":"Prognostics; Machine learning; Artificial intelligence; Predictive modelling; Computer science; Data modeling; Condition monitoring; Engineering; Reliability engineering; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001213798,0.0001061343,0.0001138393,0.00006147208,0.00004174752,0.00002158562,0.00008163006,0.00004554524,0.0001528941],"category_scores_gemma":[0.00009812398,0.00007465318,0.00003097776,0.0001076592,0.000005256894,0.0001167988,0.00001700104,0.00003111509,0.0003087117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009634522,"about_ca_system_score_gemma":0.00001835009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005971083,"about_ca_topic_score_gemma":0.00003081713,"domain_scores_codex":[0.9994262,0.000006477196,0.0001307753,0.0001530818,0.00006222436,0.0002211706],"domain_scores_gemma":[0.9996564,0.0000619773,0.000009056988,0.000117047,0.00007335159,0.00008216609],"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":[0.00001329811,0.000002875218,0.000006658888,0.00002657746,0.000004897563,1.485838e-7,0.00003219931,0.9889349,0.002441109,0.0009294082,0.002276467,0.005331499],"study_design_scores_gemma":[0.0002514415,0.00004280131,0.000007216615,0.00006828417,0.000003358025,3.403671e-7,0.000002386583,0.9654841,0.006906362,0.0006974788,0.02637628,0.0001599819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001723713,0.000004728162,0.9920456,0.004291426,0.00004100697,0.0003745595,0.000009015036,0.0004358458,0.001074088],"genre_scores_gemma":[0.2449492,0.000002917888,0.7477831,0.0004805042,0.00003578692,0.0001724086,0.00002249373,0.00005931268,0.006494354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2442625,"threshold_uncertainty_score":0.3967968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01267911968224412,"score_gpt":0.2298663767391884,"score_spread":0.2171872570569443,"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."}}