{"id":"W4405637710","doi":"10.1016/j.conengprac.2024.106212","title":"Anomaly detection for drilling tools based on operating mode recognition and interval-augmented Mahalanobis distance","year":2024,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"China University of Geosciences, Wuhan; National Natural Science Foundation of China","keywords":"Mahalanobis distance; Interval (graph theory); Anomaly detection; Pattern recognition (psychology); Anomaly (physics); Mode (computer interface); Artificial intelligence; Computer science; Mathematics; Physics; Operating system","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":[0.0003686552,0.0002296448,0.000224275,0.0001668036,0.00008057361,0.0004104097,0.00005746093,0.0001031737,0.000005108938],"category_scores_gemma":[0.0005500074,0.0002399949,0.00008368427,0.0001669899,0.000007230974,0.0006473215,0.000004949431,0.0002647222,0.00002066206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001553591,"about_ca_system_score_gemma":0.00001128306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001933435,"about_ca_topic_score_gemma":0.00001126771,"domain_scores_codex":[0.9989867,0.00003332818,0.0003061654,0.0002868256,0.0001330396,0.0002539831],"domain_scores_gemma":[0.9987504,0.0009195526,0.00003494515,0.0001487818,0.00006880802,0.00007745705],"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":[0.0001248365,0.00001199131,0.000002417334,0.0004103245,0.0001272662,0.00001009301,0.00009108456,0.911091,0.03732735,0.00004937061,0.00003479908,0.05071951],"study_design_scores_gemma":[0.001098076,0.0001332709,0.00002272988,0.0003697808,0.00009191898,0.00002780708,0.00005336997,0.9709348,0.002667285,0.000006141137,0.02433664,0.0002581561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01117017,0.0009121487,0.9839627,0.0002054131,0.001520734,0.0006211359,0.00005762932,0.001125272,0.0004247699],"genre_scores_gemma":[0.9979199,0.00002605634,0.00103948,0.0001248856,0.000311249,0.0004362172,0.00001863679,0.00008070656,0.00004284811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9867498,"threshold_uncertainty_score":0.9786708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01378473017847267,"score_gpt":0.2377594942902235,"score_spread":0.2239747641117509,"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."}}