Smart performance-based design for building fire safety: Prediction of smoke motion via AI

Abstract The performance-based design (PBD) has been widely adopted for building fire safety over the last three decades, but it requires a laborious and costly process of design and approval. This work presents a smart framework for fire-engineering PBD to predict the smoke motion and the Available Safe Egress Time (ASET) in the atrium by Artificial Intelligence (AI). A CFD database of visibility profile in atrium fires is established, including various fire scenarios, atrium volumes, and ventilation conditions. After the database is trained with the transposed convolutional neural network (TCNN), the AI model can accurately predict the smoke visibility profile and ASET in the atrium fire. Compared to conventional CFD-based PBD by professional fire engineers, AI method provides more consistent and reliable results within a much shorter time. This research verified the feasibility of using AI in fire-engineering PBD, which may reduce the time and cost in creating a fire-safety built environment.

[1]  V. R. Beck,et al.  Performance-based Fire Engineering Design And Its Application In Australia , 1997 .

[2]  Guillermo Rein,et al.  A posteriori modelling of the growth phase of Dalmarnock Fire Test One , 2011 .

[3]  James A. Milke,et al.  Using FDS to Simulate Smoke Layer Interface Height in a Simple Atrium , 2007 .

[4]  Thomas Gernay,et al.  A Digitized Fuel Load Surveying Methodology Using Machine Vision , 2020, Fire Technology.

[5]  Mamoru Kohno,et al.  Performance Based Fire Engineering in Japan , 2013 .

[6]  Guillermo Rein,et al.  Characterisation of Dalmarnock fire Test One , 2008 .

[7]  Chris Eliasmith,et al.  Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn , 2014, SciPy.

[8]  Guillermo Rein,et al.  Experimental data and numerical modelling of 1.3 and 2.3 MW fires in a 20 m cubic atrium , 2009 .

[9]  C. Zhong,et al.  Atrium-Corridor Structure Fire Smoke Simulation , 2012 .

[10]  Stephen J. Pyne,et al.  Flammable Cities: Urban Conflagration and the Making of the Modern World , 2012 .

[11]  G. Hadjisophocleous,et al.  An investigation of the effect of make-up air velocity on smoke layer height with asymmetric openings and rotational air flow in atrium fires , 2020 .

[12]  Thomas G. Cleary,et al.  Generating Synthetic Sensor Data to Facilitate Machine Learning Paradigm for Prediction of Building Fire Hazard , 2019, Fire Technology.

[13]  Satar Mahdevari,et al.  Prediction of tunnel convergence using Artificial Neural Networks , 2012 .

[14]  Grunde Jomaas,et al.  Testing for knowledge: Application of machine learning techniques for prediction of flashover in a 1/5 scale ISO 13784‐1 enclosure , 2020, Fire and Materials.

[15]  J. Hodges.  Predicting Large Domain Multi-Physics Fire Behavior Using Artificial Neural Networks , 2018 .

[16]  C. Gutiérrez-Montes,et al.  Influence of different make-up air configurations on the fire-induced conditions in an atrium , 2010 .

[17]  Andrew H. Buchanan,et al.  Implementation of performance-based fire codes , 1999 .

[18]  Ao Li,et al.  Smart Detection of Fire Source in Tunnel Based on the Numerical Database and Artificial Intelligence , 2020, Fire Technology.

[19]  M. Z. Naser.  Mechanistically Informed Machine Learning and Artificial Intelligence in Fire Engineering and Sciences , 2021, Fire Technology.

[20]  Paul M. Mather,et al.  The use of backpropagating artificial neural networks in land cover classification , 2003 .

[21]  S. L. Poon,et al.  A Dynamic Approach to ASET/RSET Assessment in Performance based Design , 2014 .

[22]  M. Z. Naser.  Fire resistance evaluation through artificial intelligence - A case for timber structures , 2019, Fire Safety Journal.

[23]  Roberto T. Leon,et al.  Evolution and Future of Building Codes in the USA , 2012 .

[24]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[25]  Hyu Soung Shin,et al.  An Application of a Deep Learning Algorithm for Automatic Detection of Unexpected Accidents Under Bad CCTV Monitoring Conditions in Tunnels , 2019, 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML).

[26]  Yichao Cao,et al.  An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke Recognition , 2019, IEEE Access.

[27]  Charles Fleischmann,et al.  Is Prescription the Future of Performance Based Design , 2011 .

[28]  Jitendra Kumar,et al.  Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters , 2018 .

[29]  Thomas Gernay,et al.  Probabilistic Models for Temperature-Dependent Strength of Steel and Concrete , 2020 .

[30]  Bart Merci,et al.  Special Issue on Fire Safety of High-Rise Buildings , 2017 .

[31]  Guillermo Rein,et al.  Round-robin study of a priori modelling predictions of the Dalmarnock Fire Test One , 2009 .

[32]  Brian Y. Lattimer,et al.  Compartment fire predictions using transpose convolutional neural networks , 2019, Fire Safety Journal.

[33]  S. C. Tsui.  PERFORMANCE-BASED FIRE SAFETY DESIGN IN HONG KONG , 2004 .

[34]  Frederick W. Mowrer.  Enclosure Smoke Filling and Fire-Generated Environmental Conditions , 2016 .

[35]  Siuming Lo,et al.  A novel artificial neural network fire model for prediction of thermal interface location in single compartment fire , 2004 .

[36]  Albert W. Jones,et al.  Research Roadmap for Smart Fire Fighting , 2015 .

[37]  Jin Young Choi,et al.  An Integrated Framework for 24-hours Fire Detection , 2016, ECCV Workshops.

[38]  Xuanya Liu,et al.  Study on Fire Smoke Control in Super-high Building Atrium , 2018 .

[39]  M. Z. Naser,et al.  Concrete under fire: an assessment through intelligent pattern recognition , 2019, Engineering with Computers.

[40]  Wan Ki Chow,et al.  Performance-based approach to determining fire safety provisions for buildings in the Asia-Oceania regions , 2015 .

[41]  C. K. Chan,et al.  Numerical simulation of the spread of smoke in an atrium under fire scenario , 2009 .

[42]  M. Z. Naser,et al.  Machine Learning-Driven Assessment of Fire-Induced Concrete Spalling of Columns , 2020, ACI Materials Journal.

[43]  Johan Andersson,et al.  A Round Robin of Fire Modelling for Performance Based Design , 2019 .

[44]  Thomas Gernay,et al.  Demonstrating adequate safety for a concrete column exposed to fire, using probabilistic methods , 2019 .

[45]  Himan Shahabi,et al.  Hybrid artificial intelligence models based on a neuro-fuzzy system and metaheuristic optimization algorithms for spatial prediction of wildfire probability , 2019, Agricultural and Forest Meteorology.

[46]  Taku Yamazaki,et al.  Early Detection System for Gas Leakage and Fire in Smart Home Using Machine Learning , 2019, 2019 IEEE International Conference on Consumer Electronics (ICCE).

[47]  Ove Njå,et al.  The concept of validation in performance-based fire safety engineering , 2013 .

[48]  Luke Bisby,et al.  The Need for Hierarchies of Acceptance Criteria for Probabilistic Risk Assessments in Fire Engineering , 2018, Fire Technology.

[49]  Mohammed A. Fadhel,et al.  Classification of Red Blood Cells in Sickle Cell Anemia Using Deep Convolutional Neural Network , 2018, ISDA.

[50]  M. Chaos,et al.  Combustion Characteristics of Materials and Generation of Fire Products , 2016 .

[51]  Guillermo Rein,et al.  Sensor Assisted Fire Fighting , 2010 .

[52]  Howard R. Baum,et al.  Fire Induced Flow Field - Theory And Experiment , 1989 .

[53]  Yehuda E. Kalay,et al.  Performance-based design , 1999 .

[54]  Asif Usmani,et al.  A real-time forecast of tunnel fire based on numerical database and artificial intelligence , 2021, Building Simulation.

[55]  Luke Bisby,et al.  A Review of Sociological Issues in Fire Safety Regulation , 2016, Fire Technology.

[56]  Fu Xiao,et al.  Perspectives of big experimental database and artificial intelligence in tunnel fire research , 2020 .

[57]  Younes Oulad Sayad,et al.  Predictive modeling of wildfires: A new dataset and machine learning approach , 2019, Fire Safety Journal.

[58]  Robert M. Haralick,et al.  Feature normalization and likelihood-based similarity measures for image retrieval , 2001, Pattern Recognit. Lett..

[59]  Wai Cheong Tam,et al.  P-Flash - A Machine Learning-based Model for Flashover Prediction using Recovered Temperature Data. , 2021, Fire safety journal.