Purpose

The purpose of this study is to adapt the incompressible smoothed particle hydrodynamics (ISPH) method with artificial intelligence to manage the physical problem of double diffusion inside a porous L-shaped cavity including two fins.

Design/methodology/approach

The ISPH method solves the nondimensional governing equations of a physical model. The ISPH simulations are attained at different Frank–Kamenetskii number, Darcy number, coupled Soret/Dufour numbers, coupled Cattaneo–Christov heat/mass fluxes, thermal radiation parameter and nanoparticle parameter. An artificial neural network (ANN) is developed using a total of 243 data sets. The data set is optimized as 171 of the data sets were used for training the model, 36 for validation and 36 for the testing phase. The network model was trained using the Levenberg–Marquardt training algorithm.

Findings

The resulting simulations show how thermal radiation declines the temperature distribution and changes the contour of a heat capacity ratio. The temperature distribution is improved, and the velocity field is decreased by 36.77% when the coupled heat Cattaneo–Christov heat/mass fluxes are increased from 0 to 0.8. The temperature distribution is supported, and the concentration distribution is declined by an increase in Soret–Dufour numbers. A rise in Soret–Dufour numbers corresponds to a decreasing velocity field. The Frank–Kamenetskii number is useful for enhancing the velocity field and temperature distribution. A reduction in Darcy number causes a high porous struggle, which reduces nanofluid velocity and improves temperature and concentration distribution. An increase in nanoparticle concentration causes a high fluid suspension viscosity, which reduces the suspension’s velocity. With the help of the ANN, the obtained model accurately predicts the values of the Nusselt and Sherwood numbers.

Originality/value

A novel integration between the ISPH method and the ANN is adapted to handle the heat and mass transfer within a new L-shaped geometry with fins in the presence of several physical effects.

中文翻译：

---

相邻 ISPH 方法和人工智能用于带翅片的多孔 L 形腔内双扩散热辐射

目的

本研究的目的是将不可压缩平滑粒子流体动力学 (ISPH) 方法与人工智能相结合，来解决包含两个翅片的多孔 L 形腔内双扩散的物理问题。

设计/方法论/途径

ISPH 方法求解物理模型的无量纲控制方程。 ISPH 模拟是在不同的 Frank-Kamenetskii 数、Darcy 数、耦合 Soret/Dufour 数、耦合 Cattaneo-Christov 热/质量通量、热辐射参数和纳米颗粒参数下获得的。人工神经网络 (ANN) 是使用总共 243 个数据集开发的。数据集经过优化，其中 171 个数据集用于训练模型，36 个用于验证，36 个用于测试阶段。网络模型使用 Levenberg-Marquardt 训练算法进行训练。

发现

由此产生的模拟显示了热辐射如何降低温度分布并改变热容比的轮廓。当耦合热 Cattaneo-Christov 热/质量通量从 0 增加到 0.8 时，温度分布得到改善，速度场降低 36.77%。温度分布得到支持，并且浓度分布随着 Soret-Dufour 数的增加而下降。索雷-杜福尔数的上升对应于速度场的下降。 Frank-Kamenetskii 数对于增强速度场和温度分布很有用。达西数的减少会导致高孔隙斗争，从而降低纳米流体的速度并改善温度和浓度分布。纳米颗粒浓度的增加会导致流体悬浮液粘度升高，从而降低悬浮液的速度。在人工神经网络的帮助下，所获得的模型准确地预测了努塞尔数和舍伍德数的值。

原创性/价值

ISPH 方法和 ANN 之间的新颖集成适用于在存在多种物理效应的情况下处理带有翅片的新 L 形几何形状内的传热和传质。