基于SRCNN的太赫兹弹性超分辨应力成像

Super-resolution stress imaging for terahertz-elastic based on SRCNN

受衍射极限的限制,空间分辨率低是太赫兹成像的缺点之一。空间分辨率低也是限制太赫兹应力测量发展的原因之一。本文将太赫兹时域光谱(THz-TDS)技术的全场应力测量与超分辨率卷积神经网络(SRCNN)算法相结合,实现低分辨应力场到高分辨应力场端到端的映射,进而获得高空间分辨率的平面应力场。本文建立了从平面应力状态到THz-TDS信号的调制模型,获得了大量的仿真训练集来训练SRCNN模型。将训练好的SRCNN模型应用于对径受压圆盘实验,提高了由捕获的THz-TDS信号计算出的应力场的空间分辨率。

Limited by diffraction limit,low spatial resolution is one of the shortcomings of terahertz imaging.Low spatial resolution is also one of the reasons limiting the development of stress measurement using terahertz imaging.In this paper,the full-field stress measurement using Terahertz Time Domain Spectral(THz-TDS)is combined with Super-Resolution Convolutional Neural Network(SRCNN)algorithm to realize end-to-end mapping from low resolution stress field to high resolution stress field.Then the plane stress field with high spatial resolution is obtained.A modulation model from a plane stress state to THz-TDS signal is constructed.A large number of simulated training sets are obtained to train the SRCNN model.By applying the trained SRCNN model to the numerical and physical stress fields,the spatial resolution of stress field calculated from the captured THz-TDS signal is improved.