Refrigerant charge fault diagnosis strategy for VRF systems based on stacking ensemble learning

被引:18
作者
Zhang, Li [1 ]
Cheng, Yahao [1 ]
Zhang, Jianxin [2 ]
Chen, Huanxin [1 ]
Cheng, Hengda [1 ]
Gou, Wei [1 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Energy & Power Engn, Dept Refrigerat & Cryogen Engn, Wuhan 430074, Hubei, Peoples R China
[2] Huazhong Univ Sci & Technol, China EU Inst Clean & Renewable Energy, Wuhan 430074, Hubei, Peoples R China
基金
中国国家自然科学基金;
关键词
Variable refrigerant flow system; Refrigerant charge fault; Stacking ensemble learning; Fault diagnosis; Recursive feature elimination; AIR-CONDITIONER; SENSOR;
D O I
10.1016/j.buildenv.2023.110209
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The VRF system frequently has refrigerant charge amount (RCA) fault, and this causes a large amount of building energy waste. The research on data-driven models used to diagnose this fault mostly focuses on the optimization of a single model, and it is difficult to maintain good performance at different fault levels. In view of this, this paper proposes the RCA fault diagnosis strategy of VRF system based on Stacking ensemble learning. Firstly, the strategy selects the low dimensional feature set through Recursive Feature Elimination (RFE) and correlation analysis. Then the initial Stacking ensemble learning model consists of two levels of learners. The output of the first-level learners and the original feature set are used as the feature input of the second-level learners. Then, the composition of the first-level learners in the model is adjusted according to the feature importance ranking re-sults of the RFE method. The results show that the classification accuracy (CA) of the model optimized by the proposed strategy in the training set and the test set is improved by 3.9% and 4.02% respectively, and there is little difference between the two, indicating the model generalization ability is improved.
引用
收藏
页数:13
相关论文
共 47 条
  • [1] A review of common faults in large-scale heat pumps
    Aguilera, Jose Joaquin
    Meesenburg, Wiebke
    Ommen, Torben
    Markussen, Wiebke Brix
    Poulsen, Jonas Lundsted
    Zuehlsdorf, Benjamin
    Elmegaard, Brian
    [J]. RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2022, 168
  • [2] Aircon, 2022, VRF SYST MARK REP
  • [3] Data-driven based HVAC optimisation approaches: A Systematic Literature Review
    Ala'raj, Maher
    Radi, Mohammed
    Abbod, Maysam F.
    Majdalawieh, Munir
    Parodi, Marianela
    [J]. JOURNAL OF BUILDING ENGINEERING, 2022, 46
  • [4] Virtual refrigerant charge sensor for booster refrigeration systems
    Andreasen, Glenn
    Izadi-Zamanabadi, Roozbeh
    Stoustrup, Jakob
    [J]. INTERNATIONAL JOURNAL OF REFRIGERATION, 2021, 122 : 59 - 68
  • [5] Distributed real-time optimal control of central air-conditioning systems
    Asad, Hussain Syed
    Wan, Hang
    Kasun, Hewage
    Rehan, Sadiq
    Huang, Gongsheng
    [J]. ENERGY AND BUILDINGS, 2022, 256
  • [6] Data-driven Fault Detection and Diagnosis for HVAC water chillers
    Beghi, A.
    Brignoli, R.
    Cecchinato, L.
    Menegazzo, G.
    Rampazzo, M.
    Simmini, F.
    [J]. CONTROL ENGINEERING PRACTICE, 2016, 53 : 79 - 91
  • [7] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [8] Confidence intervals for multinomial logistic regression in sparse data
    Bull, Shelley B.
    Lewinger, Juan Pablo
    Lee, Sophia S. F.
    [J]. STATISTICS IN MEDICINE, 2007, 26 (04) : 903 - 918
  • [9] Ensemble 1-D CNN diagnosis model for VRF system refrigerant charge faults under heating condition
    Cheng Hengda
    Chen Huanxin
    Li Zhengfei
    Cheng Xiangdong
    [J]. ENERGY AND BUILDINGS, 2020, 224
  • [10] New fault diagnostic strategies for refrigerant charge fault in a VRF system using hybrid machine learning method
    Ding, Xinlei
    Guo, Yabin
    Liu, Tao
    Liu, Qian
    Chen, Huanxin
    [J]. JOURNAL OF BUILDING ENGINEERING, 2021, 33