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 %.