物理启发的深度学习模型及其在热端部件散热中的应用

A Physics-Informed Deep Learning Model and Its Application in Heat Dissipation for Hot Section Components

关键词:  热端部件  冲击冷却  神经网络  深度学习  数值模拟

Key words:  Hot section component  Impingement cooling  Neutral network  Deep learning  Numerical simulation

摘要:

为提高神经网络对于高维的物理场的拟合能力，基于卷积算子和有限差分求解方式的类比关系，提出了一种物理启发式的深度学习模型。以横向出流的冲击冷却为例，开展了变计算域大小、变工况、变尺寸的批量数值模拟，获取了冲击冷却关键特征的小样本图像数据。进一步通过神经网络的训练，构建了多参数、大范围内有较好拟合能力的温度、传热系数、压力代理模型。研究表明，物理启发神经网络模型对于计算域大小没有限制，可以统一表达不同空间范围内获取的物理数据的共性规律。模型的各类超参设定均具有明确的物理意义，且与经典的微分方程求解理论有一定的类比关系，增强了神经网络调参的方向性。通过传热物理规律与黑箱模型的融合，实现了小样本多参数物理数据的共性建模。

Abstract:

To improve the capability of neutral network in high-dimensional physics information regression， based on the analogy between the convolution operators and the derivatives， a physics-informed recurrent convolutional neural network was proposed. Taking the impingement cooling with cross-flow effect as an example task， a batch of numerical simulations with variable computational domain， working conditions， and sizes were conducted， and a small batch of image datasets of key features in the impingement cooling were obtained. The dataset was used to train a neural network to predict temperature， heat transfer coefficient and pressure， which had a high accuracy within a large parameter range. The research results indicated that the physics-informed neural network model proposed had no limitation on the size of the computational domain and could efficiently express the commonness of physical data acquired in different spatial ranges. The hyper-parameters of the model had clear physical meanings and had an analogy with the classic partial differential equation numerical solution theory， which enhances the directionality of the neural network parameter tuning. Through the integration of the heat transfer physics law with the black box model， this study realized a universal commonness modeling for physical data.