TY - JOUR
T1 - Building Artificial-Intelligence Digital Fire (AID-Fire) system
T2 - A real-scale demonstration
AU - Zhang, Tianhang
AU - Wang, Zilong
AU - Zeng, Yanfu
AU - Wu, Xiqiang
AU - Huang, Xinyan
AU - Xiao, Fu
N1 - Funding Information:
This work is funded by the Hong Kong Research Grants Council Theme-based Research Scheme ( T22-505/19-N ) and the PolyU Emerging Frontier Area (EFA) Scheme of RISUD ( P0013879 ). TZ thanks the support from the Hong Kong PhD Fellowship Scheme .
Publisher Copyright:
© 2022 Elsevier Ltd
PY - 2022/12/15
Y1 - 2022/12/15
N2 - The identification of building fire evolution in real-time is of great significance for firefighting, evacuation, and rescue. This work proposed a novel framework of Artificial-Intelligence Digital Fire (AID-Fire) that can identify complex building fire information in real-time. The smart system consists of four main parts, Internet of Things sensor network (data collection and transfer), cloud server (data storage and management), AI Engine (data processing), and User Interface (fire information display). A large numerical database, containing 533 fire scenarios with varying fire sizes, positions, and number of fire sources, is established to train a Convolutional Long-Short Term Memory (Conv-LSTM) neural network. The proposed fire digital twin is demonstrated and validated in a full-scale fire test room (26 m2). Results show that the AI engine successfully identify the fire information by learning the spatial-temporal features of the temperature data with a relative error of less than 15% and a delay time of less than 1 s. Moreover, detailed fire development and spread can be accurately displayed in the digital-twin interface. This proposed AID-Fire system can provide valuable support for smart firefighting practices, thus paving the way for a fire-resilient smart city.
AB - The identification of building fire evolution in real-time is of great significance for firefighting, evacuation, and rescue. This work proposed a novel framework of Artificial-Intelligence Digital Fire (AID-Fire) that can identify complex building fire information in real-time. The smart system consists of four main parts, Internet of Things sensor network (data collection and transfer), cloud server (data storage and management), AI Engine (data processing), and User Interface (fire information display). A large numerical database, containing 533 fire scenarios with varying fire sizes, positions, and number of fire sources, is established to train a Convolutional Long-Short Term Memory (Conv-LSTM) neural network. The proposed fire digital twin is demonstrated and validated in a full-scale fire test room (26 m2). Results show that the AI engine successfully identify the fire information by learning the spatial-temporal features of the temperature data with a relative error of less than 15% and a delay time of less than 1 s. Moreover, detailed fire development and spread can be accurately displayed in the digital-twin interface. This proposed AID-Fire system can provide valuable support for smart firefighting practices, thus paving the way for a fire-resilient smart city.
KW - Building fire
KW - Cyber-physics
KW - Deep learning
KW - Digital twin
KW - IoT
KW - Smart firefighting
UR - http://www.scopus.com/inward/record.url?scp=85140457338&partnerID=8YFLogxK
U2 - 10.1016/j.jobe.2022.105363
DO - 10.1016/j.jobe.2022.105363
M3 - Journal article
AN - SCOPUS:85140457338
SN - 2352-7102
VL - 62
JO - Journal of Building Engineering
JF - Journal of Building Engineering
M1 - 105363
ER -