Journal
BUILDING AND ENVIRONMENT
Volume 157, Issue -, Pages 24-33Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.buildenv.2019.04.029
Keywords
Deep learning; Deep neural network; Fault detection and diagnosis
Ask authors/readers for more resources
This study proposed a real-time fault diagnostic model for air-handling units (AHUs); the model used deep learning to improve the operational efficiency of AHUs and thereby reduce the energy consumption of HVAC-heating, ventilating, and air conditioning-systems in buildings. Additionally, EnergyPlus simulation software was employed to establish different types of fault operation behavior data to serve as references for deep learning, thus reducing the complexity of data preprocessing, retaining data completeness, and improving the reliability of the diagnostic model. The proposed deep neural network fault diagnostic model can serve as a reference for this research field; the model features five hidden layers, each comprising 200 neurons. Additionally, this study tested abnormal faults commonly observed in AHUs, including failure to control two-way hydronic valves and variable air volume box dampers as well as supply air temperature sensors exhibiting measurement error. After performing diagnosis with data that had not been used in the training or verification process, the diagnostic results indicated that the diagnostic model exhibited 95.16% accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available