Using thermal load matching strategy to locate historical benchmark data for moving-window PCA based fault detection in air handling units

被引:5
作者
Yang, Xuebin
He, Ruru
Wang, Ji
Li, Xinhai
Liu, Ran
机构
[1] Institute of Air Environment and Building Energy Conservation, College of Environmental Science and Engineering, Donghua University, Songjiang, Shanghai
[2] Shanghai Division, China Ship Development and Design Center, Minhang, Shanghai
[3] Beyondsoft Company Limited, Haidian, Beijing
基金
中国国家自然科学基金;
关键词
Thermal load matching strategy; Fault detection; Principal component analysis; Moving window; Air handling units; PRINCIPAL COMPONENT ANALYSIS; WAVELET ANALYSIS; DECISION-MAKING; DIAGNOSIS; SYSTEM; MODEL; CLASSIFICATION; EXTRACTION; DISTANCE; MIXTURE;
D O I
10.1016/j.seta.2022.102238
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Principal component analysis (PCA) methods have been reported to successfully detect some faults. Unfortunately, for the actual systems, there are few literatures on how to retrieve the historical fault-free operating information as training data which is the benchmark to characterize system performance. This study proposes a dynamic thermal load matching strategy to locate historical candidate information based on mass and thermal balance. Seven parameters related to thermal load are deduced to replace some variables such as solar flux, heat gain, and heat dissipation which are usually unavailable in most real systems. Combining with the movingwindow PCA fault detection method, the strategy is validated to detect the fault symptom in 52 fault-free and 54 fault days of air conditioning systems from ASHRAE 1312-RP. The data sizes of a time-series data window, moving speed, and historical candidate pool, are defined as 60, 10 and 900 data points, respectively. The detection results of fault symptom show that the proposed strategy exhibits higher percentages of fault symptom than those reported in the published literatures. On the other hand, the fault detection effects highly depend on the severity level of fault symptom, but present slightly tiny negative correlation with PCA similarity factors.
引用
收藏
页数:20
相关论文
共 59 条
[1]   A Modified Moving Window dynamic PCA with Fuzzy Logic Filter and application to fault detection [J].
Ammiche, Mustapha ;
Kouadri, Abdelmalek ;
Bensmail, Abderazak .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2018, 177 :100-113
[2]   An auto-deployed model-based fault detection and diagnosis approach for Air Handling Units using BIM and Modelica [J].
Andriamamonjy, Ando ;
Saelens, Dirk ;
Klein, Ralf .
AUTOMATION IN CONSTRUCTION, 2018, 96 :508-526
[3]   Improving occupants' satisfaction with effective maintenance management of HVAC system in office buildings [J].
Au-Yong, Cheong Peng ;
Ali, Azlan Shah ;
Ahmad, Faizah .
AUTOMATION IN CONSTRUCTION, 2014, 43 :31-37
[4]   Fault detection with moving window PCA using NIRS spectra for monitoring the anaerobic digestion process [J].
Awhangbo, L. ;
Bendoula, R. ;
Roger, J. M. ;
Beline, F. .
WATER SCIENCE AND TECHNOLOGY, 2020, 81 (02) :367-382
[5]   A wavelet-based clustering of multivariate time series using a Multiscale SPCA approach [J].
Barragan, Joao Francisco ;
Fontes, Cristiano Hora ;
Embirucu, Marcelo .
COMPUTERS & INDUSTRIAL ENGINEERING, 2016, 95 :144-155
[6]   Fault detection and diagnosis of nonlinear dynamical processes through correlation dimension and fractal analysis based dynamic kernel PCA [J].
Bounoua, Wahiba ;
Bakdi, Azzeddine .
CHEMICAL ENGINEERING SCIENCE, 2021, 229
[7]  
Chen YM, 2017, IEEE INT CONF BIG DA, P4050, DOI 10.1109/BigData.2017.8258421
[8]   Development and application of hardware-in-the-loop simulation for the HVAC systems [J].
Du, Zhimin ;
Jin, Xinqiao ;
Zhu, Yonghua ;
Wang, Yijun ;
Zhang, Wenbin ;
Chen, Zhijie .
SCIENCE AND TECHNOLOGY FOR THE BUILT ENVIRONMENT, 2019, 25 (10) :1482-1493
[9]   Advanced data analytics for enhancing building performances: From data-driven to big data-driven approaches [J].
Fan, Cheng ;
Yan, Da ;
Xiao, Fu ;
Li, Ao ;
An, Jingjing ;
Kang, Xuyuan .
BUILDING SIMULATION, 2021, 14 (01) :3-24
[10]   Process monitoring based on independent component analysis-principal component analysis (ICA-PCA) and similarity factors [J].
Ge, Zhiqiang ;
Song, Zhihuan .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2007, 46 (07) :2054-2063