An intelligent tunnel firefighting system and small-scale demonstration

Wu, Xiaoni; Zhang, Xiaoning; Jiang, Yishuo; Huang, Xinyan; Huang, GQ; Usmani, Asif

doi:10.1016/j.tust.2021.104301

Cited by 56 publications

(12 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is necessary to improve the informatization level of tunnel construction to enhance the safety and efficiency of tunnel construction, thereby promoting the development of highway tunnels toward intelligent, integrated, and environmentally sustainable systems. [ 262 , 263 , 264 ] One aspect to consider is that the narrow and elongated configuration of the area facilitates the efficient collection of significant quantities of wind energy, mechanical energy, and other related forms of energy. The practice of harnessing and utilizing energy that would otherwise be squandered has the potential to enhance both the safety and comfort of driving.…”

Section: Teng‐enabled Smart Tunnelsmentioning

confidence: 99%

Triboelectric Nanogenerator‐Enabled Digital Twins in Civil Engineering Infrastructure 4.0: A Comprehensive Review

Pang,

He,

Liu

et al. 2024

Advanced Science

View full text Add to dashboard Cite

The emergence of digital twins has ushered in a new era in civil engineering with a focus on achieving sustainable energy supply, real‐time sensing, and rapid warning systems. These key development goals mean the arrival of Civil Engineering 4.0.The advent of triboelectric nanogenerators (TENGs) demonstrates the feasibility of energy harvesting and self‐powered sensing. This review aims to provide a comprehensive analysis of the fundamental elements comprising civil infrastructure, encompassing various structures such as buildings, pavements, rail tracks, bridges, tunnels, and ports. First, an elaboration is provided on smart engineering structures with digital twins. Following that, the paper examines the impact of using TENG‐enabled strategies on smart civil infrastructure through the integration of materials and structures. The various infrastructures provided by TENGs have been analyzed to identify the key research interest. These areas encompass a wide range of civil infrastructure characteristics, including safety, efficiency, energy conservation, and other related themes. The challenges and future perspectives of TENG‐enabled smart civil infrastructure are briefly discussed in the final section. In conclusion, it is conceivable that in the near future, there will be a proliferation of smart civil infrastructure accompanied by sustainable and comprehensive smart services.

show abstract

Section: Teng‐enabled Smart Tunnelsmentioning

confidence: 99%

Triboelectric Nanogenerator‐Enabled Digital Twins in Civil Engineering Infrastructure 4.0: A Comprehensive Review

Pang,

He,

Liu

et al. 2024

Advanced Science

View full text Add to dashboard Cite

show abstract

“…Complex structures and dynamic fires complicate escape by occupants without assistance. Therefore, intervention by professional firefighting teams is crucial (Wu et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Firefighters’ behavior via vertical shafts in natural-ventilated tunnels

Zhang,

Rui,

Zhu

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Tunnel load traffic flows day and night, and is highly susceptible to catching tunnel fires. When a tunnel is on fire, occupants are endangered by the rapid deterioration of the tunnel environment during burning, and their self-evacuation is limited by their unfamiliarity with tunnels. Therefore, efficient and effective firefighting and rescue methods are urgently required to guarantee the safety of occupants during tunnel fires. During firefighting, one of the most important issues is that a fire brigade may encounter difficulties identifying the fire source. They have to deal with congestion and navigate cars piling into the tunnel, which wastes significant time. Therefore, this study provides an alternative approach for firefighters to access fire sources in naturally ventilated tunnels equipped with vertical shafts. This study explored three routes for firefighters from the ground to a fire source in a tunnel. The duration and speed of taking the three routes, along with the use of facilities, firefighters’ communication, and emotions, were presented and analyzed. This indicates that firefighting and rescue via vertical shafts is a feasible and optimized method for naturally ventilated tunnels because the estimated duration decreased by 56.2% (without smoke) and 60.0% (with smoke) compared to traditional routes when the minimum distance from the fire to the nearest exit is 2000 m. In addition, the study provides field experimental data on vertical firefighting in tunnels, which are expected to be used to build and calibrate models for firefighters in future studies.

show abstract

“…To overcome the low robustness and slow detection speed in the existing OFDs, the one-stage deep learning (DL)-based object detection methods, which recognize objects directly, have gained wide attention. They are effective in many fields, such as intelligent security [ 12 ], intelligent transportation [ 13 ], and intelligent firefighting [ 14 ]. Specifically, the DL model automatically discovers and extracts the most relevant and salient features of each object class through neural networks training data [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

A deep learning-based dynamic deformable adaptive framework for locating the root region of the dynamic flames

Tao,

Wang,

Liu

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Traditional optical flame detectors (OFDs) in flame detection are susceptible to environmental interference, which will inevitably cause detection errors and miscalculations when confronted with a complex environment. The conventional deep learning-based models can mitigate the interference of complex environments by flame image feature extraction, which significantly improves the precision of flame recognition. However, these models focus on identifying the general profile of the static flame, but neglect to effectively locate the source of the dynamic flame. Therefore, this paper proposes a novel dynamic flame detection method named Dynamic Deformable Adaptive Framework (DDAF) for locating the flame root region dynamically. Specifically, to address limitations in flame feature extraction of existing detection models, the Deformable Convolution Network v2 (DCNv2) is introduced for more flexible adaptation to the deformations and scale variations of target objects. The Context Augmentation Module (CAM) is used to convey flame features into Dynamic Head (DH) to feature extraction from different aspects. Subsequently, the Layer-Adaptive Magnitude-based Pruning (LAMP) where the connection with the smallest LAMP score is pruned sequentially is employed to further enhance the speed of model detection. More importantly, both the coarse- and fine-grained location techniques are designed in the Inductive Modeling (IM) to accurately delineate the flame root region for effective fire control. Additionally, the Temporal Consistency-based Detection (TCD) contributes to improving the robustness of model detection by leveraging the temporal information presented in consecutive frames of a video sequence. Compared with the classical deep learning method, the experimental results on the custom flame dataset demonstrate that the AP0.5 value is improved by 4.4%, while parameters and FLOPs are reduced by 25.3% and 25.9%, respectively. The framework of this research extends applicability to a variety of flame detection scenarios, including industrial safety and combustion process control.

show abstract

An intelligent tunnel firefighting system and small-scale demonstration

Cited by 56 publications

References 56 publications

Triboelectric Nanogenerator‐Enabled Digital Twins in Civil Engineering Infrastructure 4.0: A Comprehensive Review

Triboelectric Nanogenerator‐Enabled Digital Twins in Civil Engineering Infrastructure 4.0: A Comprehensive Review

Firefighters’ behavior via vertical shafts in natural-ventilated tunnels

A deep learning-based dynamic deformable adaptive framework for locating the root region of the dynamic flames

Contact Info

Product

Resources

About