School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ, 85287, USA.
Independent researcher, Chandler, Arizona, USA.
Sci Rep. 2022 Aug 10;12(1):13614. doi: 10.1038/s41598-022-16867-z.
This article explores the deep learning approach towards approximating the effective electrical and thermal conductivities of copper (Cu)-carbon nanotube (CNT) composites with CNTs aligned to the field direction. Convolutional neural networks (CNN) are trained to map the two-dimensional images of stochastic Cu-CNT networks to corresponding conductivities. The CNN model learns to estimate the Cu-CNT composite conductivities for various CNT volume fractions, interfacial electrical resistances, R = 20 Ω-20 kΩ, and interfacial thermal resistances, R = 10-10 mK/W. For training the CNNs, the hyperparameters such as learning rate, minibatch size, and hidden layer neurons are optimized. Without iteratively solving the physical governing equations, the trained CNN model approximates the electrical and thermal conductivities within a second with the coefficient of determination (R) greater than 98%, which may take longer than 100 min for a convectional numerical simulation. This work demonstrates the potential of the deep learning surrogate model for the complex transport processes in composite materials.
本文探讨了深度学习方法在预测沿场方向排列的碳纳米管（CNT）增强铜（Cu）复合材料的有效电导率和热导率方面的应用。卷积神经网络（CNN）被训练用于将随机 Cu-CNT 网络的二维图像映射到相应的电导率。该 CNN 模型可以学习预测各种 CNT 体积分数、界面电阻（R=20-20kΩ）和界面热阻（R=10-10mK/W）下的 Cu-CNT 复合材料的电导率。为了训练 CNN，优化了学习率、小批量大小和隐藏层神经元等超参数。通过训练的 CNN 模型可以在一秒内近似电导率和热导率，无需迭代求解物理控制方程，决定系数（R）大于 98%，而传统的数值模拟可能需要 100 多分钟。这项工作展示了深度学习替代模型在复合材料复杂输运过程中的潜力。
