{"id":"W2915656323","doi":"10.1016/j.ces.2019.01.060","title":"Dynamic process fault detection and diagnosis based on a combined approach of hidden Markov and Bayesian network model","year":2019,"lang":"en","type":"article","venue":"Chemical Engineering Science","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":132,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Hidden Markov model; Bayesian network; Process (computing); Computer science; Conditional probability; Fault detection and isolation; Data mining; Bayesian probability; Pattern recognition (psychology); Artificial intelligence; Fault (geology); Dynamic Bayesian network; Medical diagnosis; Machine learning; Statistics; Mathematics","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":[0.0001640507,0.0001341015,0.0001804462,0.0000962816,0.00002962467,0.00003355677,0.0001246691,0.00007033532,0.000001564664],"category_scores_gemma":[0.00004591013,0.0001302008,0.00002280898,0.0003991914,0.00006178053,0.0001067241,0.00001714314,0.0001366722,7.4369e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005471931,"about_ca_system_score_gemma":0.00001228672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001883037,"about_ca_topic_score_gemma":2.033591e-7,"domain_scores_codex":[0.9991648,0.000003361695,0.0001524651,0.0002459432,0.0002045399,0.0002289272],"domain_scores_gemma":[0.9996471,0.00004815855,0.00002243697,0.0001517504,0.00002644453,0.0001041107],"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":[0.00001217767,0.000009796272,0.0001704461,0.0002420838,0.000004164725,1.487213e-7,0.00004181459,0.8353105,0.1618119,0.00001783344,0.000001590795,0.002377561],"study_design_scores_gemma":[0.0003606311,0.00003300199,0.0003210162,0.0000718361,0.000005246139,0.000003037856,0.0000107939,0.9747638,0.02427042,0.00001561909,0.00000331584,0.0001412914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9369848,0.00006791991,0.06205627,0.000009719438,0.0001259579,0.0002183828,0.000001979966,0.0001769645,0.0003579622],"genre_scores_gemma":[0.9976105,0.000004265659,0.002275849,0.00001043045,0.00001197625,0.00006072985,7.259345e-7,0.0000179098,0.000007595037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1394533,"threshold_uncertainty_score":0.5309434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003032898288390103,"score_gpt":0.1845222255458193,"score_spread":0.1814893272574292,"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."}}