☆ 4.7 Article

Inverse tracing of fire source in a single room based on CFD simulation and deep learning

JOURNAL OF BUILDING ENGINEERING (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Civil

A multiple back propagation neural network fusion algorithm for ceiling temperature prediction in tunnel fires

Bin Sun et al.

Summary: This study presents a multiple back propagation neural network (BPNN) fusion algorithm to predict the ceiling temperature distribution and the maximum ceiling temperature in tunnel fires. The algorithm is a data-driven artificial intelligence method that is not limited to specific tunnel fire scenes. It utilizes a strong multiple BPNN and an additional external iteration procedure to improve the prediction precision. Large-scale pool fire experiments were conducted to verify the algorithm and the results show that it outperforms traditional BPNN algorithm and developed theoretical models in predicting ceiling temperature in different ventilation conditions.

ENGINEERING STRUCTURES (2023)

Add to Collection

Article Engineering, Civil

Rapid prediction of mine tunnel fire smoke movement with machine learning and supercomputing techniques

Yao Hong et al.

Summary: A method combining supercomputing and machine learning was proposed to predict fire smoke spread in mine tunnels quickly. Numerical simulations and ML models were used to predict fire dynamics, showing that ventilation velocity and tunnel inclination angle are critical factors affecting fire dynamics.

FIRE SAFETY JOURNAL (2022)

Add to Collection

Article Energy & Fuels

An ensemble deep learning model for exhaust emissions prediction of heavy oil-fired boiler combustion

Zhezhe Han et al.

Summary: The study introduces a novel ensemble deep learning model for exhaust emissions prediction, which extracts deep features from flame images and combines multiple forecasting engines to achieve accurate final predictions.

FUEL (2022)

Add to Collection

Article Thermodynamics

An improved approach towards more robust deep learning models for chemical kinetics

Xu Han et al.

Summary: The study successfully developed a deep learning model as a fast alternative to numerical integration for ignition simulations, proposing methodological improvements to extend the model's applicable range. These techniques can unlock further potentials of artificial neural networks in making reliable predictions in practical applications. The comparison between these methods and conventional ones also provides a deeper understanding of the impact of data distribution and network architecture on the performance of ANN models.

COMBUSTION AND FLAME (2022)

Add to Collection

Article Engineering, Civil

Machine learning-based surrogate model for calibrating fire source properties in FDS models of fa?ade fire tests

Hoang T. Nguyen et al.

Summary: This paper proposes a machine-learning based surrogate modelling technique to assist in the calibration of fire sources in simulations of facade fire tests. Two case studies are conducted to evaluate the feasibility of the proposed method.

FIRE SAFETY JOURNAL (2022)

Add to Collection

Article Engineering, Civil

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

Tianhang Zhang et al.

Summary: This study proposes an AI system that utilizes a temperature sensor network and a deep-learning algorithm to forecast the development and spread of fires in buildings. The system, after training, can accurately identify fire development and predict fire spread with a 20-second lead time. It performs well for fires with different fuel types and ventilation conditions, and has the potential to be applied in various fire scenarios.

FIRE SAFETY JOURNAL (2022)

Add to Collection

Article Engineering, Civil

Radiative transfer calculations in fire simulations: An assessment of different gray gas models using the software FDS

C. S. Fernandes et al.

Summary: The study found that the gray gas (GG) assumption is effective for modeling weakly-sooting fuels such as ethanol and heptane in fire simulations. Three different GG formulations were compared in Fire Dynamics Simulator (FDS), with the default FDS formulation and the weighted-sum-of-gray-gases formulation showing better performance.

FIRE SAFETY JOURNAL (2021)

Add to Collection

Article Engineering, Civil

Brain-STORM: A deep learning model for computationally fast transient high-rise fire simulations

Tyler Buffington et al.

Summary: This paper presents a deep learning model called Brain-STORM for quickly predicting the temporal evolution of smoke, temperature, and pressure in a high-rise fire scenario. The model is trained using a Gaussian process generative model and compared to a physics-based fire model Fire-STORM, showing nearly identical results but running over 100 times faster. The accuracy of Brain-STORM is evaluated for realistic use cases involving heat release rate curves not present in the training set.

FIRE SAFETY JOURNAL (2021)

Add to Collection

Article Engineering, Civil

Deep learning based inverse model for building fire source location and intensity estimation

Luyao Kou et al.

Summary: The study introduces a deep learning model based on GRU for estimating fire locations and intensity, showing high testing accuracy through simulations of multiple fire scenarios and evaluation with various data configurations. The estimation of fire location is not affected by the precision of fire simulations, but only the intensity inversion is sensitive to deviations, indicating the model's reliability and efficiency in fire source parameter estimation.

FIRE SAFETY JOURNAL (2021)

Add to Collection

Article Engineering, Civil

Applying the FDS pyrolysis model to predict heat release rate in small-scale forced ventilation tunnel experiments

Xiaoyun Wang et al.

FIRE SAFETY JOURNAL (2020)

Add to Collection

Article Engineering, Civil

Fire induced pressure in airthigh houses: Experiments and FDS validation

S. Brohez et al.

FIRE SAFETY JOURNAL (2020)

Add to Collection

Article Engineering, Civil

Using machine learning in physics-based simulation of fire

B. Y. Lattimer et al.

FIRE SAFETY JOURNAL (2020)

Add to Collection

Article Engineering, Civil

Compartment fire predictions using transpose convolutional neural networks

Jonathan L. Hodges et al.

FIRE SAFETY JOURNAL (2019)

Add to Collection

Article Engineering, Chemical

BLEVE fireball modeling using Fire Dynamics Simulator (FDS) in an Algerian gas industry

Ilyas Sellami et al.

JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

Early fire detection using convolutional neural networks during surveillance for effective disaster management

Khan Muhammad et al.

NEUROCOMPUTING (2018)

Add to Collection

Article Water Resources

A sparse grid based Bayesian method for contaminant source identification

Lingzao Zeng et al.

ADVANCES IN WATER RESOURCES (2012)

Add to Collection

Article Construction & Building Technology

Theoretical and numerical studies of coupling multizone and CFD models for building air distribution simulations

L. Wang et al.

INDOOR AIR (2007)

Add to Collection

Article Environmental Sciences

Bayesian inference for source determination with applications to a complex urban environment

Andrew Keats et al.

ATMOSPHERIC ENVIRONMENT (2007)

Add to Collection

© Peeref 2019-2024. All rights reserved.