{"id":"W3215874436","doi":"10.1016/j.compchemeng.2021.107612","title":"Data-driven predictive corrosion failure model for maintenance planning of process systems","year":2021,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canada Excellence Research Chairs, Government of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Genome Canada","keywords":"Corrosion; Workflow; Reliability engineering; Extreme value theory; Generalized extreme value distribution; Process (computing); Pipeline (software); Predictive maintenance; Computer science; Engineering; Materials science; Mathematics; Statistics; Metallurgy","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":[0.00005576272,0.0001780602,0.0003544379,0.00004782428,0.00002329993,0.00002878644,0.0003631856,0.0001439016,0.000001578969],"category_scores_gemma":[0.0001032001,0.00017139,0.00009327524,0.0002021033,0.000028962,0.0001605355,0.0001092152,0.0002574163,4.365725e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007048078,"about_ca_system_score_gemma":0.00002285309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000150726,"about_ca_topic_score_gemma":2.893919e-7,"domain_scores_codex":[0.9989995,0.000003366181,0.0003088745,0.0002999376,0.0001463127,0.0002420193],"domain_scores_gemma":[0.9992371,0.0001322688,0.00003788065,0.0003594194,0.0001528394,0.00008049169],"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":[0.000007087949,0.000007713073,0.00001350554,0.0008144026,0.00006462508,0.000002858196,0.0002014419,0.9258299,0.07209518,0.00009970198,0.0007787916,0.00008482273],"study_design_scores_gemma":[0.0002024678,0.000007375096,0.000006522979,0.0004788463,0.00005304362,0.00001408434,0.00008420795,0.967611,0.03118826,0.00004347147,0.0001335545,0.0001771485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1406199,0.000389727,0.858083,0.00002746311,0.0003430479,0.0001273008,0.0001850998,0.0002099985,0.00001445481],"genre_scores_gemma":[0.9703798,0.000009553775,0.02919061,0.000007192206,0.0001125323,0.00001791731,0.0002452506,0.00002786556,0.000009318463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8297599,"threshold_uncertainty_score":0.698908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01804563290103648,"score_gpt":0.2354450441683581,"score_spread":0.2173994112673217,"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."}}