Purpose

This study aims to introduce a deep neural network (DNN) to estimate the effective thermal conductivity of the flat heat pipe with spreading thermal resistance.

Design/methodology/approach

A total of 2,160 computational fluid dynamics simulation cases over up to 2,000 W/mK are conducted to regress big data and predict a wider range of effective thermal conductivity up to 10,000 W/mK. The deep neural networking is trained with reinforcement learning from 10–12 steps minimizing errors in each step. Another 8,640 CFD cases are used to validate.

Findings

Experimental, simulational and theoretical approaches are used to validate the DNN estimation for the same independent variables. The results from the two approaches show a good agreement with each other. In addition, the DNN method required less time when compared to the CFD.

Originality/value

The DNN method opens a new way to secure data while predicting in a wide range without experiments or simulations. If these technologies can be applied to thermal and materials engineering, they will be the key to solve thermal obstacles that many longing to overcome.

中文翻译：

---

扁平热管有效导热系数和扩散热阻的深度神经网络预测

目的

本研究旨在引入深度神经网络 (DNN) 来估算具有扩散热阻的扁平热管的有效导热系数。

设计/方法/途径

总共进行了 2,160 个高达 2,000 W/mK 的计算流体动力学模拟案例，以回归大数据并预测更广泛的有效导热系数，高达 10,000 W/mK。深度神经网络通过 10-12 个步骤的强化学习进行训练，最大限度地减少每个步骤中的错误。另有 8,640 个 CFD 案例用于验证。

发现

实验、模拟和理论方法用于验证相同自变量的 DNN 估计。两种方法的结果表明彼此非常吻合。此外，与 CFD 相比，DNN 方法需要的时间更少。

原创性/价值

DNN 方法开辟了一种新的方式来保护数据，同时无需实验或模拟即可在大范围内进行预测。如果这些技术能够应用于热学和材料工程，它们将成为解决许多人渴望克服的热障碍的关键。