Real-time forecast of compartment fire and flashover based on deep learning

Zhang, Tianhang; Wang, Zilong; Wong, Ho Yin; Tam, Wai Cheong; Huang, Xinyan; Xiao, Fu

doi:10.1016/j.firesaf.2022.103579

Cited by 54 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of this report is to develop a methodology for estimating the heat release rate of a fire by using its recorded video data and deep learning techniques. There are a few publications [8], [9], [17]- [21] that make use of video recordings to estimate flame height and heat release rate. Omiotek and Kotyra [18] combined flame image processing with a deep convolutional neural network for identifying undesired combustion states.…”

Section: Empirical Methods For Estimating Heat Release Ratementioning

confidence: 99%

Predicting heat release rate from fire video data:

Prasad

2024

View full text Add to dashboard Cite

A novel approach for estimating transient heat release rate from fire images and video using deep learning techniques is presented. The heat release rate (HRR) is a critical parameter in characterizing the fire hazard and thermal effects of a burning item. It is an effective indicator of the fire growth rate and fire hazard that is used extensively in building fire safety design. However, for outdoor fires, heat release rate measurements are usually not available due to lack of measurement equipment.The goal of this work is to develop and demonstrate a novel technique based on "image calorimetry" for predicting heat release rate using video data and recurrent neural network models. The proposed methodology only requires video camera data and can be extended to outdoor fire experiments. Results of the trained neural network model on the investigated set of experiments conducted in a laboratory setting, show excellent comparison between predicted and temporally evolving heat release rate measurements, with an overall accuracy score of 0.94.

show abstract

Section: Empirical Methods For Estimating Heat Release Ratementioning

confidence: 99%

Predicting heat release rate from fire video data:

Prasad

2024

View full text Add to dashboard Cite

show abstract

“…The use of Support Vector Machines and Dynamic Time Warping Kernel function has been explored with the aim of improving and optimising the performance of fire detection sensors [39]. The capabilities of the Internet of Things (IoT) have been combined with Deep Learning (DL) algorithms to predict developed fire temperatures in compartments [40]. The results of physical testing have been used for training the DL model.…”

Section: Monitoring and Management Planningmentioning

confidence: 99%

A review of the contributions of Artificial Intelligence in fire engineering, in a world rapidly realising the need for sustainable design

Bakas

Kontoleon

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

With sustainability being at the forefront of international civil and structural engineering professional bodies agendas, Artificial Intelligence (AI), and its numerous facets, has potential of providing an invaluable tool. Although the notion of AI is not new, it only recently started gaining momentum in the sector of fire engineering. The combination of tangible benefits in scientific and industrial applications, in conjunction with a developing understanding of its functionality, requirements and deliverables, from practitioners and researchers alike, supported a wider acceptance of the method. Acknowledging the scope of AI applications is vast, a focus will be given to fire engineering scientific projects. A selection of recent, representative scientific papers will be reviewed with the aim of debating the attributes of Artificial Intelligence in the context of sustainability, while also assessing its current contribution to the technical advancement of the field.

show abstract

“…Whileas CFD fire simulations typically take large periods of time to complete, and their results would not be available in time to be of use during an emergency. Motivated by these observations, an artificial intelligence system is proposed to fast forecast the compartment fire development and flashover in advance based on a temperature sensor network and a deep-learning algorithm [6]. The traveling fire and hybrid simulations are explored to solve the spatiotemporal fire evolutions as flashover [7].…”

Section: Introductionmentioning

confidence: 99%

Forecasting Flashover in a Compartment Fire by Using a Real-time Moving Average from Temperature Recordings

Bouaoud¹,

Lebey²,

Wang³

et al. 2023

J. Civ. Eng. Constr.

View full text Add to dashboard Cite

A series of flashover fire tests were carried out using standard wood as fuel with various ventilation, and a comprehensive set of experimental data is presented. Fighting against compartment fires with occurance of flashover could cause fatal consequences on firefighters. This work shows that the potential dangers as flashover can be detected as soon as possible thanks to the comparison between two moving averages in the past calculated from a temperature recording in a very short time. The present study aims to evaluate the possibility of using only commonly available measurements as data to be assimilated into the model. A real-time decision method is developed, allowing to the selection of optimal intervention to minimize firefight occupant exposure to the detected hazard. This approach includes the mathematical analysis which is based on the comparison of two moving averages centered in the past, calculated on the recordings of the smoke temperature. Firefighters would greatly benefit from this predictive method in real time, able to assist their decision making process during operations against a compartment fire. From the safety point of view, the model gives conservative predictions for flashover fire.

show abstract

Real-time forecast of compartment fire and flashover based on deep learning

Cited by 54 publications

References 36 publications

Predicting heat release rate from fire video data:

Predicting heat release rate from fire video data:

A review of the contributions of Artificial Intelligence in fire engineering, in a world rapidly realising the need for sustainable design

Forecasting Flashover in a Compartment Fire by Using a Real-time Moving Average from Temperature Recordings

Contact Info

Product

Resources

About