{"id":"W2517450510","doi":"10.1016/j.enbuild.2016.08.083","title":"PCA-based method of soft fault detection and identification for the ongoing commissioning of chillers","year":2016,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Outlier; HVAC; Identification (biology); Anomaly detection; Principal component analysis; Project commissioning; Data mining; Engineering; Computer science; Data set; Fault (geology); Fault detection and isolation; Set (abstract data type); Training set; Reliability engineering; Artificial intelligence; Air conditioning","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":[0.0002453521,0.00005772079,0.00009828475,0.00005175718,0.00007903233,0.00001017019,0.00003724168,0.00004502386,0.000002492695],"category_scores_gemma":[0.00005110836,0.00003519787,0.00003213256,0.00005829279,0.00002614684,0.0000520622,0.000005665735,0.00002048236,5.270119e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008888923,"about_ca_system_score_gemma":0.000003108313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006894765,"about_ca_topic_score_gemma":0.00002884965,"domain_scores_codex":[0.9996238,0.00001845936,0.0001607707,0.00007842753,0.00005414446,0.00006437501],"domain_scores_gemma":[0.9995332,0.0002794916,0.00006447422,0.00007314987,0.0000292648,0.00002046947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002321197,0.000002560904,0.0000433334,0.00004102831,0.0000248357,2.068044e-8,0.00006633243,0.009223782,0.6908488,0.0005473207,0.00001967209,0.2991591],"study_design_scores_gemma":[0.0006335157,0.00003625085,0.0005583342,0.00009493082,0.00002397711,0.000003399549,0.0001018482,0.3235008,0.6595008,0.0001661722,0.01530803,0.00007194815],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1760574,0.000378886,0.823156,0.0001020003,0.0001481266,0.00006088825,0.000002701711,0.00003808329,0.00005591526],"genre_scores_gemma":[0.9991185,0.00003499727,0.0006964438,0.00001094115,0.00002866561,0.00002097216,3.043063e-7,0.00000870827,0.00008047828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8230611,"threshold_uncertainty_score":0.1435328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006659736379484096,"score_gpt":0.2237514488798414,"score_spread":0.2170917125003573,"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."}}