Qing Deng

Dr. Qing Deng

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2022 in Fire
Verified
Journal Article
Open access
PDF file
QDQing Deng
Qing Deng
BZBo Zhang
Bo Zhang
ZZZheng Zhou
Zheng Zhou
HDHongyu Deng
Hongyu Deng
LZLiang Zhou
Liang Zhou
HJHuiling Jiang
Huiling Jiang
Fire is one of the most common and harmful disasters in real life. In 2021, firefighting teams in China reported 748,000 fires, resulting in 1987 deaths, 2225 injuries and CNY 6.75 billion of direct property losses, which account for 0.05‰ of GDP. Scientific and accurate estimation of evacuation time can provide decision support for intelligent fire evacuation. This paper aims to effectively improve the evacuation efficiency of people in large buildings, especially for a scenario with intricate evacuation passages. There are many factors that make a difference in evacuation time, such as individual behavior, occupant density, exit width, and so on. The people distribution density is introduced to effectively assess the impact of unstable pedestrian flow and unbalanced distribution in the process of evacuation. The verification results show that there is a strong positive correlation between people distribution density and evacuation time. Combining the people distribution density with many other factors, the training dataset is built by Pathfinder to learn the relationship between evacuation time and influencing factors. Finally, an evacuation time prediction model is established to estimate the consumption time that occupants spend on moving in the evacuation process based on stacking integration. The model can assist occupants in choosing different channels for evacuation in advance. After testing, the average error between the predicted evacuation consumption time and the reference time is 3.63 s. The result illustrates that the model can accurately predict the time consumed in the process of evacuation.

27 December 2023 in Energies
Verified
Journal Article
Open access
PDF file
XXXingyu Xiao
Xingyu Xiao
BQBen Qi
Ben Qi
Jingang LiangJingang Liang
Jingang Liang
JTJiejuan Tong
Jiejuan Tong
QDQing Deng
Qing Deng
PCPeng Chen
Peng Chen
In nuclear power plants, the loss-of-coolant accident (LOCA) stands out as the most prevalent and consequential incident. Accurate breach size diagnosis is crucial for the mitigation of LOCAs, and identifying the cause of an accident can prevent catastrophic consequences. Traditional methods mostly focus on combining model algorithms and utilize intricate composite model neural network architectures. However, it is crucial to investigate whether greater complexity necessarily leads to better performance. In addition, the consideration of the impact of dataset construction and data preprocessing on model performance is also needed for model building. This paper proposes a framework named DeepLOCA-Lattice to experiment with different preprocessing approaches to fundamental deep learning models for a comprehensive analysis of the diagnosis of LOCA breach size. The DeepLOCA-Lattice involves data preprocessing via the lattice algorithm and equal-interval partitioning and deep-learning-based models, including the multi-layer perceptron (MLP), recurrent neural networks (RNNs), convolutional neural networks (CNNs), and the transformer model in LOCA breach size diagnosis. After conducting rigorous ablation experiments, we have discovered that even rudimentary foundational models can achieve accuracy rates that exceed 90%. This is a significant improvement when compared to the previous models, which yield an accuracy rate of lower than 50%. The results interestingly demonstrate the superior performance and efficacy of the fundamental deep learning model, with an effective dataset construction approach. It elucidates the presence of a complex interplay among diagnostic scales, sliding window size, and sliding stride. Furthermore, our investigation reveals that the model attains its highest accuracy within the discussed range when utilizing a smaller sliding stride size and a longer sliding window length. This study could furnish valuable insights for constructing models for LOCA breach size estimation.

2 January 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DZDingli Zhang
Dingli Zhang
GHGuozhong Huang
Guozhong Huang
HLHaoxuan Li
Haoxuan Li
QDQing Deng
Qing Deng
Xuehong GaoXuehong Gao
Xuehong Gao
Electric vehicle (EV) fire accidents are caused by multiple factors, including the traffic conditions, parking environment and firefighting facilities, and are a typical public safety issue in cities. Owing to the lack of accurate and quick estimation methods for the EV fire analysis in roadside parking scenarios and their impacts, this study applied the solid flame model to simplify the determination of the dynamic turbulence characteristics of the EV fire flames and proposed a thermal radiation model of an EV thermal runaway combustion flame based on the peak heat release rate. Subsequently, the radiation accuracy of the model near the flame was verified by a simulation and a comparison with the point source flame model, where the safety threshold of the fire accident propagation was determined. Finally, the evacuation strategy for pedestrians in an EV fire was investigated based on the proposed model. From the results, the safe distance of adjacent vehicles and the cumulative value of the pedestrians affected by the thermal radiation of EV fires can be obtained under the influence of the environmental factors. The proposed model can be used to optimize the design of roadside parking lots and guide the formulation of pedestrian emergency plans during an EV fire.