基于物理模型分析与深度神经网 络融合的爆炸流场实时模拟方法  

Real-time explosion field modeling by fusing physical model-based analysis with deep neural network

作　　者：周沈楠 王仲琦[1] 李其中[2] ZHOU Shennan;WANG Zhongqi;LI Qizhong(State Key Laboratory of Explosion Science and Technology,Beijing Institute of Technology,Beijing 100081,China;School of Safety Engineering,North China Institute of Science and Technology,Yanjiao 065201,Hebei,China)

机构地区：[1]北京理工大学爆炸科学与技术国家重点实验室,北京100081 [2]华北科技学院安全工程学院,河北燕郊065201

出　　处：《安全与环境学报》2024年第5期1681-1690,共10页Journal of Safety and Environment

基　　金：国家重点研发计划课题(2021YFC3001204)。

摘　　要：爆炸流场预测研究是爆炸安全性分析重要的组成部分,当前基于物理模型的CFD模拟已成为复杂空间环境下爆炸场景定量分析的首选工具,然而其计算效率较低,无法支持实时应急响应。借助基于机器学习(Machine Learning,ML)算法的代理模型可以有效缩短定量分析周期,但可供算法学习的数据量少是该项技术在化工事故后果分析中应用所面临的主要问题。因此,将物理模型分析与深度神经网络相融合,通过数据集构建、数据降维、数据回归和数据生成4个步骤,最终构建高效的卷积变分自编码器(Variational Autoencoder with Deep Convolutional Layers,VAEDC)与多层前馈神经网络(Multi-layer Forward Neural Network,MFNN)混合模型,用于实时预测区域爆炸压力场。基于特定区域,根据定义的算法输入与输出,利用CFD技术对各种爆炸过程进行模拟以获得大量的数据;基于CFD模拟数据,利用VAEDC将区域压力场的高维特征降维为隐空间变量,利用MFNN拟合爆炸相关参数、流场观测时刻与隐变量的映射关系,并以储罐区为例进行建模分析。结果表明,所建模型预测结果的平均误差为12.8%,单次预测平均耗时0.0142 s,VAEDC与MFNN混合模型可以快速准确地预测特定条件下任意时刻的爆炸压力场。To make a rapid and accurate prediction for regional pressure fields produced by Vapor Cloud Explosions(VCEs),this paper proposed a methodology that fuses the physical model-based analysis with a Deep Neural Network(DNN).This fusion method comprises 4 steps,including the construction of a database,dimensionality reduction,data regression,and data generation.For a specific region,terrain parameters such as spatial layout and natural and geographical conditions normally remain the same for a long time or change very little in a short time,presenting static states.Besides,when performing numerical simulations for different types of generic VCEs,the arrangement of observation points would be fixed.Therefore,the parameters of the explosive source and the observation time were defined as explosion scenario-related variables.By randomly changing the explosive source-related parameters of each generic VCE and calculating them in the CFD tool,a large number of blast data could be obtained.After that,the inference algorithm of the Variational Autoencoder with Deep Convolutional Layers(VAEDC)model was used to reduce the dimensions of the regional pressure field and get the latent variables,meanwhile,the generative model was used to map the latent variables to the pressure field data.The role of data regression is to correlate the latent variables with the explosion scenario-related variables by the Multi-layer Forward Neural Network(MFNN)model,making the hybrid model can predict the regional pressure field provided with a combination of explosion scenario-related parameters.Furthermore,a progressive-training approach was adopted to improve the DNN s learning efficiency.Data on simple explosion scenarios were first fed into the model,and then data on more sophisticated explosion scenarios were provided to the model in turn.VCEs occurring in a typical tank farm were selected as an example for illustration.Through analyzing the effects of the VAEDC s structure and latent space size,as well as MFNN s loss function type on the g

关 键 词：安全工程 爆炸流场 实时预测 CFD模拟 深度神经网络 

分 类 号：X932[环境科学与工程—安全科学]