Smart Detection of Fire Source in Tunnel Based on the Numerical Database and Artificial Intelligence

Wu, Xiaoni; Park, Younggi; Li, Ao; Huang, Xinyan; Xiao, Fu; Usmani, Asif

doi:10.1007/s10694-020-00985-z

Cited by 101 publications

(35 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, benefiting from the evolutions of artificial intelligence (AI) and big data, data-driven methods, especially artificial neural networks (ANNs) [19], have been increasingly applied in fire safety research. Wu et al [20] applied the framework of artificial intelligence (AI) and big data to predict fire sources in a numerical model of tunnels. Hong et al [21] proposed a method to automatically control fire-induced smoke by coupling a full-field CFD model and a PID algorithm.…”

Section: Hmentioning

confidence: 99%

Effect of the Metro Train on the Smoke Back-Layering Length under Different Tunnel Cross-Sections

et al. 2022

View full text Add to dashboard Cite

Smoke back-layering length is an important aspect of tunnel fire research, and the influence of metro train blockage cannot be ignored. In previous studies, less attention has been paid to the phenomenon of back-layering caused by the same train blocked in tunnels with different cross-sections. This paper investigates this point through dimensionless analysis and fire dynamic simulator (FDS) numerical simulation. Several full-scale model tunnels (300 m in length), with different tunnel cross-sections, were constructed in FDS. According to the FDS simulation result, the smoke back-layering length was compared and analyzed. To investigate the effect of the tunnel cross-sections on smoke back-layering length under metro train blocking, the headroom ratio ε was proposed. Then, the influence of the tunnel cross-section on the smoke back-layering length was discussed in detail. Based on the dimensional analysis and FDS simulation results, a new model for predicting the smoke back-layering length was proposed. The prediction model obtained in this paper was compared with the FDS simulation results and the prediction model proposed by our predecessors. It is proven that the proposed model can better predict the length of smoke back-layering when metro trains are blocked in tunnels with different cross-sections. The outcomes of this work are expected to provide theoretical guidance for fire smoke control in metro tunnels with different cross-sections.

show abstract

Section: Hmentioning

confidence: 99%

Effect of the Metro Train on the Smoke Back-Layering Length under Different Tunnel Cross-Sections

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The idea of using fire simulation models to generate synthetic data have been shown useful in recent studies such as fire detection in tunnel (Wu et al 2020), structural fire protection design (Zhang et al 2020), and hazard assessment (Lattimer et al 2020) as it avoids the need of conducting costly experiments and facilitate parametric studies of a problem. For example, Wu and his coworkers (Wu et al 2020) used a CFD model to generate detailed smoke and temperature data for different heat sensors at various locations with a wide range of fire and wind conditions. The advantage is clear.…”

Section: Generation Of Synthetic Dataset Using Simulation Modelsmentioning

confidence: 99%

Predicting Flashover Occurrence using Surrogate Temperature Data

Tam

Wang

et al. 2021

AAAI

View full text Add to dashboard Cite

Fire fighter fatalities and injuries in the U.S. remain too high and fire fighting too hazardous. Until now, fire fighters rely only on their experience to avoid life-threatening fire events, such as flashover. In this paper, we describe the development of a flashover prediction model which can be used to warn fire fighters before flashover occurs. Specifically, we consider the use of a fire simulation program to generate a set of synthetic data and an attention-based bidirectional long short-term memory to learn the complex relationships between temperature signals and flashover conditions. We first validate the fire simulation program with temperature measurements obtained from full-scale fire experiments. Then, we generate a set of synthetic temperature data which account for the realis-tic fire and vent opening conditions in a multi-compartment structure. Results show that our proposed method achieves promising performance for prediction of flashover even when temperature data is completely lost in the room of fire origin. It is believed that the flashover prediction model can facilitate the transformation of fire fighting tactics from traditional experience-based decision marking to data-driven decision marking and reduce fire fighter deaths and injuries.

show abstract

“…Furthermore, the rapid and complex development of fire inside the tunnel makes it difficult to predict and guide the rescuing and firefighting actions. Therefore, an accurate and timely prediction of tunnel fire is in urgent need (Beard 2009;Wu et al 2020;Zhang et al 2021).…”

Section: Introductionmentioning

confidence: 99%

A real-time forecast of tunnel fire based on numerical database and artificial intelligence

Zhang

Huang

et al. 2021

Build. Simul.

Self Cite

View full text Add to dashboard Cite

The extreme temperature induced by fire and hot smoke in tunnels threaten the trapped personnel and firefighters. To alleviate the potential casualties, fast while reasonable decisions should be made for rescuing, based on the timely prediction of fire development in tunnels. This paper targets to achieve a real-time prediction (within 1 s) of the spatial-temporal temperature distribution inside the numerical tunnel model by using artificial intelligence (AI) methods. A CFD database of 100 simulated tunnel fire scenarios under various fire location, fire size, and ventilation condition is established. The proposed AI model combines a Long Short-term Memory (LSTM) model and a Transpose Convolution Neural Network (TCNN). The real-time ceiling temperature profile and thousands of temperature-field images are used as the training input and output. Results show that the predicted temperature field 60 s in advance achieves a high accuracy of around 97%. Also, the AI model can quickly identify the critical temperature field for safe evacuation (i.e., a critical event) and guide emergency responses and firefighting activities. This study demonstrates the promising prospects of AI-based fire forecasts and smart firefighting in tunnel spaces.

show abstract

Smart Detection of Fire Source in Tunnel Based on the Numerical Database and Artificial Intelligence

Cited by 101 publications

References 47 publications

Effect of the Metro Train on the Smoke Back-Layering Length under Different Tunnel Cross-Sections

Effect of the Metro Train on the Smoke Back-Layering Length under Different Tunnel Cross-Sections

Predicting Flashover Occurrence using Surrogate Temperature Data

A real-time forecast of tunnel fire based on numerical database and artificial intelligence

Contact Info

Product

Resources

About