A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks
A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks
复制标题
DOI：
10.1016/j.ijheatmasstransfer.2023.123890
复制
发表时间：
2023-05
影响因子：
5.2
通讯作者：
Amirsaman Eghtesad;Farhin Tabassum;S. Hajimirza
中科院分区：
文献类型：
--
作者：
Amirsaman Eghtesad;Farhin Tabassum;S. Hajimirza
许多工程应用的核心是评估材料和器件的辐射响应，特别是在高温下。几十年来，研究人员一直将注意力集中在多孔介质中的辐射热传输(RHT)的研究上。蒙特卡罗射线追踪(MCRT)是一种可靠的计算方法，可以替代非均匀介质中RHT的昂贵或不可行的实验测量。考虑到收敛要求、材料的复杂性(例如，多孔介质中的大量颗粒)以及输入物理规范的空间(例如，入射光线的角度和/或位置、波长等)，MCRT模拟的计算成本可能是繁重的。这项研究是用有监督学习算法取代MCRT模拟的一次尝试。对随机重叠和非重叠圆形填充多孔介质，通过求解经典的辐射传递方程(RTE)，利用MCRT生成了地面真实标示数据。利用工程几何特征，建立了一个低成本的基于物理和几何的人工神经网络(ANN)模型，用于预测任意多孔结构的辐射特性。利用神经网络模型进行了灵敏度分析，以评估设计特征的相对重要性。这种洞察力有助于识别最关键的特征，以改进对更复杂几何图形的学习。预测的精度是基于对训练数据所做的不同假设来计算的，即全尺寸类、壁式类和点式类。结果表明，当使用重叠圆作为训练时，所设计的模型能够预测前两类样本外数据的辐射特性，其精度分别为R2>；0.944和R2>；0.787，而前一类需要更多的定向工程特征才能达到更高的精度。结果表明，该模型具有较强的泛化能力，适用于多种多孔构型。
At the core of many engineering applications is the evaluation of the radiative responses of materials and devices, particularly at high temperatures. Researchers have focused their attention for decades on the investigation of radiation heat transport (RHT) in porous media. Monte Carlo ray tracing (MCRT) is a reliable computational alternative to the otherwise expensive or infeasible experimental measurements for RHT in heterogeneous media. Despite the accuracy, the computational cost of MCRT simulations can be burdensome given the convergence requirements, the complexity of materials (eg, large number of particles in a porous medium), and space of input physical specifications (eg, angle and/or location of incoming rays, wavelength, etc.). This study is an attempt to replace MCRT simulations with supervised learning algorithms. Ground truth labeling data is generated using MCRT for random overlapping and non-overlapping circular packed porous media and solving the classical radiative transfer equation (RTE). A significantly low-cost physical and geometrical-based artificial neural network (ANN) model is developed to forecast the radiative characteristics of arbitrary porous configurations, using engineered geometric features. Using the ANN model, a sensitivity analysis is conducted to assess the relative importance of the designed features. This insight helps in identifying the most crucial features to improve the learning for more complex geometries. The precision of predictions is calculated based on different hypotheses made over the training data, ie, whole-size, wall-wise, and pointwise classes. It is shown that when overlapping circles are used as training, the designed model can predict the radiative properties of out-sample data for the first two classes with the accuracy of R 2> 0.944 and R 2> 0.787, while more directional engineering features are required to achieve higher accuracies for the former class. Results show that the current model is highly generalizable and applicable to a variety of porous configurations.