A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Generative adversarial network for fault detection diagnosis of chillers
https://orcid.org/0000-0002-1611-6636
https://orcid.org/0000-0002-9486-4728
Abstract Automatic fault detection and diagnosis (AFDD) for chillers has significant impacts on energy saving, indoor environment comfort and systematic building management. Recent works show that the artificial intelligence (AI) enhanced techniques outperform most of the traditional fault detection and diagnosis methods. However, one serious issue has been raised in recent studies, which shows that insufficient number of fault training samples in the training phase of AI techniques can significantly influence the final classification accuracy. The insufficient number of fault samples refers to the imbalanced-class classification problem, which is a hot topic in the field of machine learning. In this study, we re-visit the imbalanced-class problem for fault detection and diagnosis of chiller in the heating, ventilation and air-conditioning (HVAC) system. The generative adversarial network is employed and customized to re-balance the training dataset for chiller AFDD. Experimental results demonstrate the effectiveness of the proposed GAN-integrated framework compared with traditional chiller AFDD methods.
Highlights This work proposes a chiller AFDD method integrating generative adversarial network. The traditional GAN is revised to meet the requirements of chiller AFDD. A comparative study is conducted to show the effectiveness of the proposed method.
Generative adversarial network for fault detection diagnosis of chillers
https://orcid.org/0000-0002-1611-6636
https://orcid.org/0000-0002-9486-4728
Abstract Automatic fault detection and diagnosis (AFDD) for chillers has significant impacts on energy saving, indoor environment comfort and systematic building management. Recent works show that the artificial intelligence (AI) enhanced techniques outperform most of the traditional fault detection and diagnosis methods. However, one serious issue has been raised in recent studies, which shows that insufficient number of fault training samples in the training phase of AI techniques can significantly influence the final classification accuracy. The insufficient number of fault samples refers to the imbalanced-class classification problem, which is a hot topic in the field of machine learning. In this study, we re-visit the imbalanced-class problem for fault detection and diagnosis of chiller in the heating, ventilation and air-conditioning (HVAC) system. The generative adversarial network is employed and customized to re-balance the training dataset for chiller AFDD. Experimental results demonstrate the effectiveness of the proposed GAN-integrated framework compared with traditional chiller AFDD methods.
Highlights This work proposes a chiller AFDD method integrating generative adversarial network. The traditional GAN is revised to meet the requirements of chiller AFDD. A comparative study is conducted to show the effectiveness of the proposed method.
Generative adversarial network for fault detection diagnosis of chillers
https://orcid.org/0000-0002-1611-6636
https://orcid.org/0000-0002-9486-4728
Abstract Automatic fault detection and diagnosis (AFDD) for chillers has significant impacts on energy saving, indoor environment comfort and systematic building management. Recent works show that the artificial intelligence (AI) enhanced techniques outperform most of the traditional fault detection and diagnosis methods. However, one serious issue has been raised in recent studies, which shows that insufficient number of fault training samples in the training phase of AI techniques can significantly influence the final classification accuracy. The insufficient number of fault samples refers to the imbalanced-class classification problem, which is a hot topic in the field of machine learning. In this study, we re-visit the imbalanced-class problem for fault detection and diagnosis of chiller in the heating, ventilation and air-conditioning (HVAC) system. The generative adversarial network is employed and customized to re-balance the training dataset for chiller AFDD. Experimental results demonstrate the effectiveness of the proposed GAN-integrated framework compared with traditional chiller AFDD methods.
Highlights This work proposes a chiller AFDD method integrating generative adversarial network. The traditional GAN is revised to meet the requirements of chiller AFDD. A comparative study is conducted to show the effectiveness of the proposed method.
Generative adversarial network for fault detection diagnosis of chillers
Yan, Ke (author) / Chong, Adrian (author) / Mo, Yuchang (author)
Building and Environment ; 172
2020-01-22
Article (Journal)
Electronic Resource
English
Performance Monitoring, Fault Detection, and Diagnosis of Reciprocating Chillers
| British Library Online Contents | 1996
Fault Detection and Diagnosis of Chillers Under Transient Conditions
| Springer Verlag | 2024
Performance Monitoring, Fault Detection, and Diagnosis of Reciprocating Chillers
| British Library Conference Proceedings | 1996
A Robust Fault Detection and Diagnosis Strategy for Centrifugal Chillers
| Taylor & Francis Verlag | 2006