基于深度学习的涡轮叶片压力预测
Pressure Predictions of Turbine Blades with Deep Learning
摘要:
深度学习已被用于许多领域,例如图像中的特征检测和围棋游戏。本文提出了一项研究,试图使用深度学习方法来预测性能。建立并训练了三种不同的深度神经网络,用于涡轮翼型压力分布的预测。首先使用基于欧拉方程的方法预测涡轮翼型库的性能,然后将其用于训练和验证深度学习神经网络。结果表明,四层卷积神经网络和两层全连接神经网络的网络提供了最好的预测。对于最佳神经网络结构,99%以上位置的压力预测优于3%,90%位置的压力预测优于1%。
英文摘要:
Deep learning has been used in many areas, such as feature detections in images and the game of go. This paper presents a study that attempts to use the deep learning method to predict turbomachinery performance. Three different deep neural networks are built and trained to predict the pressure distributions of turbine airfoils. The performance of a library of turbine airfoils were firstly predicted using methods based on Euler equations, which were then used to train and validate the deep learning neural networks. The results show that network with four layers of convolutional neural network and two layers of fully connected neural network provides the best predictions. For the best neural network architecture, the pressure prediction on more than 99% locations are better than 3% and 90% locations are better than 1%.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。