共 49 条
Fault diagnosis of HVAC system sensors: A method based on Box-Cox transformation and multi-model fusion
被引:0
作者:
Tang, Junhao
[1
]
You, Yuwen
[1
]
Zhao, Yuan
[1
]
Guo, Chunmei
[1
]
Li, Zhe
[1
]
Yang, Bin
[1
]
机构:
[1] Tianjin Chengjian Univ, Sch Energy & Safety Engn, Tianjin 300384, Peoples R China
来源:
关键词:
Box-Cox transformation;
Gaussian model;
Multi-model fusion;
Sensor fault;
Fault diagnosis;
VIRTUAL SENSORS;
PCA METHOD;
STRATEGY;
IMPACT;
MODEL;
UNIT;
D O I:
10.1016/j.egyr.2025.03.012
中图分类号:
TE [石油、天然气工业];
TK [能源与动力工程];
学科分类号:
0807 ;
0820 ;
摘要:
Sensor failures in HVAC systems can alter control rules, which can negatively impact indoor thermal comfort and lead to energy inefficiencies. Most existing fault diagnosis methods assume Gaussian or linear data distributions. However, operational data from HVAC systems often deviate from a Gaussian distribution, limiting the effectiveness of Gaussian-based models. To address this issue, we propose a Gaussian Naive Bayes-based fusion model that incorporates a Box-Cox transformation to convert non-Gaussian data into approximately Gaussiandistributed data. In addition, ensemble techniques such as Bagging and Boosting are applied to combine multiple Gaussian Naive Bayes models. The impact of the Box-Cox transformation on the performance of models with varying data distribution requirements under concurrent sensor faults is analyzed. The results show that the BoxCox transformation improves the performance of the Gaussian ensemble model, as well as linear regression (LR) and support vector machine (SVM) models, to varying extents. However, it has minimal effect on decision tree (DT) models, which do not have specific distribution assumptions. The Gaussian ensemble model achieves the highest diagnostic accuracy, with an accuracy of 98.75 % and Hamming loss of only 0.0025. Furthermore, a model degradation analysis reveals that sensor failures significantly degrade the fault diagnosis model, with the greatest degradation observed in cases of complete sensor failure, where the degradation rate reaches 37.65 %.
引用
收藏
页码:3489 / 3503
页数:15
相关论文