摘要
在基于激光技术的现代光学实验和光学应用中,光学元器件表面的微杂质和微缺陷是影响光学系统精密程度的主要因素之一,因而光学表面杂质和缺陷的定位检测是一个重要的问题.本文提出利用深度神经网络来辅助光学杂质检测的理论方案.模拟了一束探测激光脉冲照射到具有单个微小杂质的光学表面时,反射信号和透射信号中所携带杂质的位置信息可被一个深度卷积神经网络学习并定位.此外,通过改变杂质大小、折射率等属性生成了一系列泛化数据集,并讨论了神经网络在泛化数据集上的表现.泛化结果表明,神经网络对杂质位置的预测能力具有较高的鲁棒性.最后,还对比了卷积神经网络和全连接神经网络这两种不同架构网络的学习能力.
Laser technology plays fundamental roles in the modern optical experiments and applications.The performance of optical devices will be significantly affected by micro impurities and defects on the optical surfaces.Therefore,precisely positioning the optical impurities and defects is an important issue in optics.In this paper,we theoretically propose to adopt the deep learning neural networks in addressing this problem.Specifically,we generate the training data via simulating the dynamic process in which a probe optical pulse being scattered by a micro-impurity on an optical surface,and then the position information of the impurity carried by the reflection and the transmission signal can be efficiently learned by a deep convolutional neural network.One step further,we show that the deep neural network can make precise predictions on the generalization datasets generated through varying the size,refractive index,and geometry of the impurity,respectively.Additionally,we also compared the learning capability of two different networks architectures.This work provides new perspective for the impurity and defect detections in the field of precision optics.
作者
张瑶
张云波
陈立
Zhang Yao;Zhang Yun-Bo;Chen Li(State Key Laboratory of Quantum Optics and Quantum Optics Devices,Institute of Theoretical Physics,Shanxi University,Taiyuan 030006,China;Key Laboratory of Optical Field Manipulation of Zhejiang Province,Physics Department,Zhejiang Sci-Tech University,Hangzhou 310018,China)
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2021年第16期347-355,共9页
Acta Physica Sinica
基金
国家自然科学基金(批准号:11804205,12074340)资助的课题。
关键词
光学杂质缺陷
机器学习
神经网络
深度学习
optical impurity detection
machine learning
neural network
deep learning
