A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Deep-learning-based fault detection and diagnosis of air-handling units
https://orcid.org/0000-0002-0461-569X
Abstract 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.
Highlights A robust tool was developed to improve the operation efficiency of the buildings. Deep learning was developed to detect the fault diagnostic system in AHU systems. The fault operational data produced by EnergyPlus can improve the reliability of the diagnostic model. The DNN model featuring 5 hidden layers with 200 neurons in each layer.
Deep-learning-based fault detection and diagnosis of air-handling units
https://orcid.org/0000-0002-0461-569X
Abstract 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.
Highlights A robust tool was developed to improve the operation efficiency of the buildings. Deep learning was developed to detect the fault diagnostic system in AHU systems. The fault operational data produced by EnergyPlus can improve the reliability of the diagnostic model. The DNN model featuring 5 hidden layers with 200 neurons in each layer.
Deep-learning-based fault detection and diagnosis of air-handling units
https://orcid.org/0000-0002-0461-569X
Abstract 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.
Highlights A robust tool was developed to improve the operation efficiency of the buildings. Deep learning was developed to detect the fault diagnostic system in AHU systems. The fault operational data produced by EnergyPlus can improve the reliability of the diagnostic model. The DNN model featuring 5 hidden layers with 200 neurons in each layer.
Deep-learning-based fault detection and diagnosis of air-handling units
Lee, Kuei-Peng (author) / Wu, Bo-Huei (author) / Peng, Shi-Lin (author)
Building and Environment ; 157 ; 24-33
2019-04-13
10 pages
Article (Journal)
Electronic Resource
English
Robust model-based fault diagnosis for air handling units
| Elsevier | 2014
Robust model-based fault diagnosis for air handling units
| Online Contents | 2015
Demonstration of Fault Detection and Diagnosis Methods for Air-Handling Units
| Taylor & Francis Verlag | 2002