基于机器学习方法的三维粒子重构技术

Particle reconstruction of volumetric particle image velocimetry with strategy of machine learning

通过三维粒子重构获取粒子场的分布情况是层析粒子图像测速的关键步骤,有限二维投影下的三维粒子重构是一个欠定的反问题,其精确解往往很难得到。一般情况下,可以通过优化方法得到近似解。为了获取质量更高的粒子场并用于层析粒子图像测速,提出了一种基于卷积神经网络(Convolutional Neural Networks,CNN)的粒子重构方法。所提出的技术可以从基于传统的代数重构技术(Algebraic Reconstruction Technique,ART)的方法所得到的粗略粒子分布中进一步提高粒子重构质量。与现有的基于ART的算法相比,新技术在重构质量方面有了显著的改进,可以有效剔除虚假粒子并更准确地还原粒子形状,并且在粒子浓度较稠密的情况下计算速度至少快了一个数量级。

Three-dimensional particle reconstruction with limited two-dimensional projections is an underdetermined inverse problem that the exact solution is often difficult to be obtained.In general,approximate solutions can be obtained by optimization methods.In order to obtain a better quality particle field for Tomographic PIV,in the current work,a practical particle reconstruction method based on convolutional neural network(CNN)is proposed.The proposed technique can refine the particle reconstruction from a very coarse initial guess of particle distribution from any traditional algebraic reconstruction technique(ART)based methods.Compared with available ART-based algorithms,the novel technique makes significant improvements in terms of reconstruction quality.It can effectively eliminate ghost particles and restore the shape of particles more accurately,and is at least an order of magnitude faster withdense particle concentration.