Abstract
Precise online identification of safe-zone evolution has been long desired in the context of indoor chemical attack events. Computational fluid dynamics (CFD) technology can provide great accuracy but is incapable of applying on online predictions of a large-scale fluid system due to the enormous computational costs to date. In this paper, we propose a Multi-Step Spatial-Temporal Situational-Awareness Network (MSSTP-SA Net) based on deep learning algorithms for rapid online estimation of concentration field. The dataset is firstly created by CFD simulation considering different poisonous gas release and decontamination scenarios in pre-specific domain with various combinations of airflow conditions and source parameters. Corresponding experiments are also provided for validations. The test experiments of the trained network suggest that the evolution of concentration field's distribution can be predicted faithfully in millisecond computation time costs. We hope this approach to be highly useful in most chemical attack scenarios to reduce casualties.
Highlights
Accidental biological and chemical attacks in indoor environments would bring devastating blows and put tremendous damage on public safety
Drivas et al proposed a model to describe the concentration as a function of time and position, following an instantaneous chemical source release and assumed no significant air velocities in space [12].Yang et al presented a method of concentration prediction with the scales of accessibility of contaminant source (ACS) and accessibility of supply air (ASA) where flow field keeps constant [13]
This paper focuses on the estimation of safe-zone spatiotemporal evolution under poisoners-gas-attack indoor scenarios
Summary
Accidental biological and chemical attacks in indoor environments would bring devastating blows and put tremendous damage on public safety. Besides the complexity of the model would lead to intense computation consumption These all significantly limit the CFD simulations to provide real-time prediction results during an on-going emergency event. The method is based on CFD modeling and deep learning The former can provide a numerous amount of simulation data covering different kinds of instantiation of the scenarios to ensure the validity of the datasets regarding the deployments. The latter builds neural networks for extracting the complicated multi-scale features based on the dataset created by CFD models. It is shown that R is larger than 0.91 in different modes of the fluid fields, suggesting an acceptable consistency between the numerical simulation and experimental measurement results
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
