论文标题
从随机“ Minecraft”系统中近似3D电子系统中的全场温度演变
Approximating the full-field temperature evolution in 3D electronic systems from randomized "Minecraft" systems
论文作者
论文摘要
神经网络随着快速物理模拟器而具有许多工程设计任务的潜力。广泛应用程序的先决条件是易于使用的工作流程，用于在合理的时间内生成培训数据集，并且网络可以推广到看不见的系统的能力。与大多数以前的培训系统类似于评估数据集的工作相反，我们建议将培训系统的类型调整到网络体系结构中。具体而言，我们应用一个完全卷积的网络，因此设计了具有随机分配的物理属性的随机体素的3D系统。该想法对电子系统中的瞬时热扩散进行了测试。仅在随机的“ Minecraft”系统上训练，我们获得了对电子系统的良好概括，这是训练系统的四倍（一步预测误差为0.07％，比0.8％）。
Neural Networks as fast physics simulators have a large potential for many engineering design tasks. Prerequisites for a wide-spread application are an easy-to-use workflow for generating training datasets in a reasonable time, and the capability of the network to generalize to unseen systems. In contrast to most previous works where training systems are similar to the evaluation dataset, we propose to adapt the type of training system to the network architecture. Specifically, we apply a fully convolutional network and, thus, design 3D systems of randomly located voxels with randomly assigned physical properties. The idea is tested for the transient heat diffusion in electronic systems. Training only on random "Minecraft" systems, we obtain good generalization to electronic systems four times as large as the training systems (one-step prediction error of 0.07% vs 0.8%).
