•  
  •  
 
Building Simulation: An International Journal

Article Title

A statistical-based online cross-system fault detection method for building chillers

Authors

Jiangyan Liu, Key Laboratory of Low-Grade Energy Utilization Technologies and Systems, Chongqing University, Ministry of Education, Chongqing, China; School of Energy and Power Engineering, Chongqing University, Chongqing, China
Xin Li, Key Laboratory of Low-Grade Energy Utilization Technologies and Systems, Chongqing University, Ministry of Education, Chongqing, China; School of Energy and Power Engineering, Chongqing University, Chongqing, China
Guannan Li, School of Urban Construction, Wuhan University of Science and Technology, Wuhan, China
Chuang Wu, Key Laboratory of Low-Grade Energy Utilization Technologies and Systems, Chongqing University, Ministry of Education, Chongqing, China; School of Energy and Power Engineering, Chongqing University, Chongqing, China
DingChao Li, Key Laboratory of Low-Grade Energy Utilization Technologies and Systems, Chongqing University, Ministry of Education, Chongqing, China; School of Energy and Power Engineering, Chongqing University, Chongqing, China
Qing Zhang, Key Laboratory of Low-Grade Energy Utilization Technologies and Systems, Chongqing University, Ministry of Education, Chongqing, China; School of Energy and Power Engineering, Chongqing University, Chongqing, China
Kuining Li, Key Laboratory of Low-Grade Energy Utilization Technologies and Systems, Chongqing University, Ministry of Education, Chongqing, China; School of Energy and Power Engineering, Chongqing University, Chongqing, China
Hailong Lu, Chongqing Midea General Refrigeration Equipment Co., Ltd, Chongqing, China
Yunqian Zhang, Chongqing Midea General Refrigeration Equipment Co., Ltd, Chongqing, China
Jinjiang Zhang, Chongqing Midea General Refrigeration Equipment Co., Ltd, Chongqing, China

Keywords

fault detection, cross-system, chiller, EWMA control chart

Abstract

Practical applications of data-driven fault detection (FD) are limited by their portability. The costs of model training and validation are extremely high when each system requires a model retrained on its own fault and fault-free data. Therefore, this paper proposes a statistical-based online cross-system FD method to address the problem of model portability. The proposed FD model can be cross-utilized between building chillers with various specifications while it only needs to update the original fault detection model by the normal operation data of the new chiller system, thus saving huge fault experimental costs for the fault detection of new chiller. First, a theoretical basis for the proposed cross-system fault detection method is presented. Then, experiments were conducted on three building chillers with different specifications. Both fault and fault-free data were collected from the three chillers. The development and validation of the proposed cross-system fault detection method are then conducted. Results show that the cross-system fault detection models perform well when used with different chillers. For instance, when the fault detection model of system #1 was cross-utilized to system #2, the detection accuracies of refrigerant leakage, refrigerant overcharge, and reduced evaporator water flow were 99.73%, 90.17%, and 96.94%, respectively. Compared with original models, the detection accuracies were improved by 33.78%, 84.07%, and 65.56%, respectively. Therefore, the proposed cross-system fault detection method has potential for online application to practical engineering FD.

Link to Full Text
Request a Copy

Share

COinS