{"id":"W4405028298","doi":"10.1007/978-981-97-8313-7_22","title":"A Feature Selection Approach for Unsupervised Steady-State Chiller Fault Detection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in civil engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Fault detection and isolation; Chiller; Feature selection; Computer science; Steady state (chemistry); Pattern recognition (psychology); Artificial intelligence; Selection (genetic algorithm); Chiller boiler system; Fault (geology); Engineering; Physics; Geology; Water chiller; Chemistry; Thermodynamics; Mechanical engineering; Seismology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006499998,0.0007664658,0.001093838,0.0008320866,0.0005170011,0.0006201045,0.00116417,0.0006798655,0.002095106],"category_scores_gemma":[0.0009729763,0.0003377895,0.0009542584,0.000947638,0.0003066922,0.0005463733,0.0006014961,0.0007850231,0.001015998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002765305,"about_ca_system_score_gemma":0.000477414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004173509,"about_ca_topic_score_gemma":0.005349974,"domain_scores_codex":[0.9995987,0.00008077643,0.00003069248,0.0001036517,0.0001344476,0.00005176608],"domain_scores_gemma":[0.9994146,0.0002894682,0.0000306097,0.00006362372,0.0001810194,0.00002076329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002412008,0.0002018332,0.001006861,0.00006065422,0.0001277564,0.0001219063,0.00005744374,0.05421007,0.0335829,0.001731561,0.006477149,0.9021807],"study_design_scores_gemma":[0.00001615164,0.0001046431,0.002298205,0.000006399192,0.00003872231,0.00009747691,0.00001998833,0.9848968,0.008467815,0.002272516,0.001763038,0.00001827242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01103316,0.0002680787,0.9866931,0.00006576353,0.00005332178,0.00003514423,0.0001154932,0.001112063,0.0006238846],"genre_scores_gemma":[0.3291099,0.0004279522,0.6575046,0.000186067,0.0002892134,0.0002516482,0.001490073,0.0003144979,0.01042613],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004173509,"threshold_uncertainty_score":0.008298457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006858680821711181,"score_gpt":0.1903693606877051,"score_spread":0.183510679865994,"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."}}