Deep-Learning Emulators of Transient Compartment Fire Simulations for Inverse Problems and Room-Scale Calorimetry

Deep-Learning Emulators of Transient Compartment Fire Simulations for Inverse Problems and Room-Scale Calorimetry
复制标题

反演问题和室内量热法瞬态舱室火灾模拟的深度学习模拟器

DOI:
10.1007/s10694-020-01037-2
复制
发表时间:
2021
期刊:
影响因子:
3.4
通讯作者:
Ezekoye, Ofodike A.
Ezekoye, Ofodike A.
中科院分区:
工程技术3区
文献类型:
--
作者:
Buffington, Tyler;Cabrera, Jan-Michael;Kurzawski, Andrew;Ezekoye, Ofodike A.

文献摘要

参考文献

被引文献

相似文献

这项工作描述了一种用于“模拟”CFD 软件火灾动力学模拟器 (FDS) 产生的温度输出的深度学习方法。一系列人工神经网络 (ANN) 经过训练,可以根据瞬态热释放率 (HRR) 输入来预测指定位置的瞬态温度。这些位置对应于实验燃烧结构中使用的热电偶的位置。为了构建训练集,使用高斯过程 (GP) 框架来开发生成模型,该模型可生成随机可行的 HRR 斜坡。尽管此过程可能需要数千次 FDS 运行才能构建足够的训练集,但迁移学习的应用可以将所需的运行次数减少近一个数量级。这是指最初训练 ANN 来预测火灾和烟雾传输综合模型 (CFAST) 的输出,然后将其知识转移到 ANN 学习预测 FDS 输出的过程。 CFAST 是一个比 FDS 快得多的模型,因此可以快速生成大型训练集。训练模拟 CFAST 的 ANN 的最终状态用作学习模拟 FDS 的 ANN 的初始状态。结果是生成的 FDS 温度预测平均绝对误差 (MAE) 小于 2°C,并且运行速度比 FDS 快五个数量级以上。模拟器还能够学习逆映射;即对于给定的温度输出,他们可以预测会导致 FDS 产生温度响应的 HRR 斜坡。这种 HRR 曲线反演能力是根据从峰值 HRR 高达 200 kW 的八个火灾实验收集的数据来实现的,其中包括四个丙烷燃烧器火灾、两个甲醇池火灾和两个正己烷池火灾。该模型对实验 HRR 进行反演,燃烧器测试的 MAE 为 5.8 kW-15.4 kW (11.3%–16.7%),水池火灾测试的 MAE 为 5.0 kW–25.5 kW (12.1%–28.6%),倾向于低估水池火灾的 HRR。最后,仿真器的计算速度允许将 CFD 物理学纳入贝叶斯参数反演中。例如,这被证明可以根据实验和合成数据以及 FDS 验证指南中报告的不确定性来推断辐射分数。
This work describes a deep learning methodology for “emulating” temperature outputs produced by the Fire Dynamics Simulator (FDS), a CFD software. An array of artificial neural networks (ANNs) is trained to predict transient temperatures at specified locations for a transient heat release rate (HRR) input. These locations correspond to the locations of thermocouples used in an experimental burn structure. In order to build the training set, A Gaussian process (GP) framework is used to develop a generative model that produces random viable HRR ramps. Although this procedure may require thousands of FDS runs to build a sufficient training set, the application of transfer learning can reduce the required number of runs by nearly an order of magnitude. This refers to the process of initially training an ANN to predict the output of the Consolidated Model of Fire and Smoke Transport (CFAST) and then transferring its knowledge to an ANN that learns to predict FDS outputs. CFAST is a much faster model than FDS, so a large training set can be generated quickly. The final state of the ANN trained to emulate CFAST is used as the initial state of an ANN that learns to emulate FDS. The result is a model that produces FDS temperature predictions with a mean absolute error (MAE) of less than 2°C and runs over five orders of magnitude faster than FDS. The emulators are also capable of learning inverse mappings; i.e. for a given temperature output, they can predict the HRR ramp that would cause FDS to produce the temperature response. This ability to invert for the HRR profile is exercised on data collected from eight fire experiments with peak HRRs up to 200 kW, including four propane burner fires, two methanol pool fires, and two n-Hexane pool fires. The model inverts for the experimental HRR with a MAE of 5.8 kW-15.4 kW (11.3%–16.7%) for the burner tests and 5.0 kW–25.5 kW (12.1%–28.6%) for the pool fire tests, with a tendency to underestimate the HRR of the pool fires. Finally, the computational speed of the emulators allows for the incorporation of CFD physics in Bayesian parameter inversion. As an example, this is demonstrated to infer the radiative fraction from experimental and synthetic data in conjunction with reported uncertainties from the FDS Validation Guide.
使用带有调查和物理数据的整体火灾模型量化广义住宅火灾风险
DOI: --
发表时间: 2018
期刊: Fire technology
影响因子: 3.4
作者:
A. Anderson;O. Ezekoye
通讯作者: O. Ezekoye
小须芒草的燃料特性和火灾蔓延速率的表征
DOI: --
发表时间: 2012
期刊: Fire technology
影响因子: 3.4
作者:
K. Overholt;J. Cabrera;A. Kurzawski;M. Koopersmith;O. Ezekoye
通讯作者: O. Ezekoye
通过受火暴露的石膏隔断进行传热和传质
DOI: --
发表时间: 2009
期刊:
影响因子: --
作者:
S. Kukuck
通讯作者: S. Kukuck
热释放率量热法
DOI: --
发表时间: 1996
期刊:
影响因子: --
作者:
E. Smith
通讯作者: E. Smith
Cfast,火灾增长和烟雾输送的综合模型
DOI: --
发表时间: 2018
期刊:
影响因子: --
作者:
R. Peacock
通讯作者: R. Peacock