Perspectives of big experimental database and artificial intelligence in tunnel fire research

Xiao-ning, Zhang; Wu, Xiaoni; Park, Younggi; Zhang, Tianhang; Huang, Xinyan; Xiao, Fu; Usmani, Asif

doi:10.1016/j.tust.2020.103691

Cited by 55 publications

(22 citation statements)

References 167 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Atkinson and Wu (1996), Weng et al (2016), and Jiang et al (2022a) further analysed the critical velocity for sloping tunnels. Tang et al (2013), and Zhang et al (2021b) studied the critical velocity with partial blockage of the tunnel. The effect of blockage, as well as tunnel curvature and turning radius on the critical velocity, has also been investigated recently Zhang et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Numerical analysis of the performance of a PID control based real-time mechanical ventilation system to prevent smoke back-layering in tunnel fires

Hong

Merci

2022

Tunnelling and Underground Space Technology

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Numerical analysis of the performance of a PID control based real-time mechanical ventilation system to prevent smoke back-layering in tunnel fires

Hong

Merci

2022

Tunnelling and Underground Space Technology

View full text Add to dashboard Cite

“…Plenty of real-scale and reduced-scale tunnel fire tests have been conducted to quantify the key parameters related to the fire safety of the tunnel, including maximum temperature, smoke layer, and critical ventilation velocity (CVV) (Beard 2009;Li and Ingason 2018;Zhang et al 2021). Most of these studies installed many temperature sensors (e.g., thermocouple trees) and laser scanners for visualizing the smoke layer, while it is practically difficult to quantify the full temperature fields of a tunnel fire.…”

Section: Cfd Modeling Of Tunnel Firementioning

confidence: 99%

“…This is realized by defining a constant velocity across the whole tunnel section. Given that a CVV of 2.8 m/s is required to prevent smoke back-layering from an 80 MW fire (Danziger and Kennedy 1982;Ingason et al 2015;Zhang et al 2021), four different ventilation speeds of 0 m/s, 1 m/s, 2 m/s, and 4 m/s, were modeled. Overall, 5 fire locations, 5 HRRs and 4 ventilation conditions constitute 100 (= 5 × 5 × 4) fire scenarios.…”

Section: Cfd Modeling Of Tunnel Firementioning

confidence: 99%

“…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%

“…Dexters et al (2020) proposed an LR model to predict the occurrence of flashover in a compartment utilizing the information of fire intensity, fire duration, and the thickness of combustible materials from past experiments. In our previous work, we proposed a long short-term memory (LSTM) model to successfully identify the size and location of fire inside the tunnel, based on the training of 100 tunnel-fire numerical simulations (Wu et al 2020); and predict the required critical ventilation velocity by training an organized fire-test database (Zhang et al 2021).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Numerical investigation on smoke control with new‐style horizontal smoke baffle in an immersed road tunnel

Zhang,

Diao,

Shi

et al. 2024

Fire and Materials

View full text Add to dashboard Cite

To investigate the improvement induced by horizontal smoke baffles during lateral smoke exhaust, an immersed road tunnel with various horizontal smoke baffles positioned below the lateral exhaust vent was studied numerically. Together with the velocity field characteristics, the temperature distribution was investigated near the lateral smoke exhaust vent, followed by the analysis of lateral smoke exhaust efficiency under different horizontal smoke baffles. Results showed that after installing the horizontal smoke baffle, there was a significant decrease in the extracted cold air, while the high‐temperature smoke in the exhaust vent increases, indicating the plug‐holing is effectively suppressed. It is known that the efficiency of smoke exhaust increases when the length exceedance ratio of the horizontal smoke baffle is smaller than 100%, while it changes slightly when the baffle length continues to increase. When the width ratio of horizontal baffle is smaller than 40%, the efficiency of smoke exhaust increases with the baffle width and then changes slightly with a wider smoke baffle. With a larger aspect ratio, the wider and shorter lateral exhaust vent is beneficial for improving the lateral smoke exhaust. Under the current conditions, the case shows the optimal smoke exhaust performance with a horizontal baffle length exceedance ratio of 100%, a baffle width ratio of 40%, and exhaust vent aspect ratio of 3:1. Finally, an empirical model is developed to describe the improvement of smoke exhaust efficiency caused by horizontal smoke baffle. These outcomes are helpful to the design of lateral smoke extraction system in road tunnels.

show abstract

Perspectives of big experimental database and artificial intelligence in tunnel fire research

Cited by 55 publications

References 167 publications

Numerical analysis of the performance of a PID control based real-time mechanical ventilation system to prevent smoke back-layering in tunnel fires

Numerical analysis of the performance of a PID control based real-time mechanical ventilation system to prevent smoke back-layering in tunnel fires

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

Numerical investigation on smoke control with new‐style horizontal smoke baffle in an immersed road tunnel

Contact Info

Product

Resources

About