Fault detection and diagnosis in AHU system using deep learning approach - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of The Franklin Institute Année : 2023

Fault detection and diagnosis in AHU system using deep learning approach

Résumé

Energy consumption in buildings increases with the failures of equipment involved in the energy exchange, and control networks in buildings. One of the ways to remedy this issue is to offer high-performance fault detection systems. This article proposes a Fault Detection and Diagnostics (FDD) system based on Convolutional Neural Network (CNN) and Long Term Short Memory (LSTM) neural networks, applied to an AHU and using an hybrid database containing data from simulation and real-world on an actual physical building. The proposed system is designed to effectively identify and categorize faults, whether they occur in the sensors or in the mechanical equipment responsible for critical functions such as heat exchanges, air transfer, and system control. The FDD system provides results with an overall accuracy of around 96.88 %.
Fichier non déposé

Dates et versions

hal-04409578 , version 1 (22-01-2024)

Identifiants

Citer

Yanis Masdoua, Moussa Boukhnifer, Kondo Hloindo Adjallah, Abdelmoudjib Benterki. Fault detection and diagnosis in AHU system using deep learning approach. Journal of The Franklin Institute, 2023, 360 (17), pp.13574-13595. ⟨10.1016/j.jfranklin.2023.09.046⟩. ⟨hal-04409578⟩
8 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More