{"id":"W4407031371","doi":"10.1016/j.oceaneng.2025.120541","title":"Predictive maintenance for offshore wind farms with incomplete and biased prognostic information","year":2025,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Canada First Research Excellence Fund","keywords":"Offshore wind power; Complete information; Submarine pipeline; Marine engineering; Predictive maintenance; Environmental science; Computer science; Engineering; Reliability engineering; Wind power; Geotechnical engineering; Economics; Microeconomics","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":[0.00008538215,0.0001803501,0.000167115,0.0002033309,0.00003456755,0.00004998,0.000094794,0.0000572551,0.000001400264],"category_scores_gemma":[0.0001190846,0.0001651431,0.00002411461,0.000205334,0.00001848646,0.0003009555,0.00002537117,0.0001275428,7.007092e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000662996,"about_ca_system_score_gemma":0.0000116983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002660474,"about_ca_topic_score_gemma":0.000002248213,"domain_scores_codex":[0.9993955,0.00000311078,0.00018358,0.0001141616,0.00007805477,0.0002256294],"domain_scores_gemma":[0.9996214,0.0001191651,0.00002159069,0.0001369405,0.00005390883,0.00004700604],"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":[0.000132736,0.0000540359,0.08211017,0.004397636,0.0004624875,0.00000923313,0.001365756,0.8630573,0.001276492,0.007283944,0.01806075,0.02178948],"study_design_scores_gemma":[0.0007010431,0.000117691,0.04217331,0.0005930054,0.00004270885,0.000006309569,0.00004818039,0.9381478,0.00313525,0.0001093921,0.01464184,0.0002834414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3476976,0.0001467362,0.648038,0.00009285317,0.0001315082,0.00114595,0.00008609983,0.001503794,0.001157379],"genre_scores_gemma":[0.987896,0.00002320039,0.01184618,0.00004353513,0.00002577768,0.00007878266,0.00004450718,0.00002787131,0.0000140874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6401984,"threshold_uncertainty_score":0.6734341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003163984443678096,"score_gpt":0.2014119659425227,"score_spread":0.1982479814988446,"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."}}