搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于深度学习的光学表面杂质检测

张瑶 张云波 陈立

引用本文:
Citation:

基于深度学习的光学表面杂质检测

张瑶, 张云波, 陈立

Deep-learning-assisted micro impurity detection on an optical surface

Zhang Yao, Zhang Yun-Bo, Chen Li
PDF
HTML
导出引用
  • 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.
      通信作者: 张云波, ybzhang@zstu.edu.cn ; 陈立, lchen@sxu.edu.cn
    • 基金项目: 国家自然科学基金(批准号: 11804205, 12074340)资助的课题
      Corresponding author: Zhang Yun-Bo, ybzhang@zstu.edu.cn ; Chen Li, lchen@sxu.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11804205, 12074340)
    [1]

    Gyongyosi L, Imre S 2019 Comput. Sci. Rev. 31 51Google Scholar

    [2]

    Williams C P 2010 Explorations in Quantum Computing (London: Springer Science and Business Media) p3

    [3]

    Bruzewicz C D, Chiaverini J, McConnell R, Sage J M 2019 Appl. Phys. Rev. 6 021314Google Scholar

    [4]

    Gisin N, Thew R 2007 Nat. Photonics 1 165Google Scholar

    [5]

    Brassard G 2003 Found. Phys. 33 1593Google Scholar

    [6]

    Nauerth S, Moll F, Rau M, Fuchs C, Horwath J, Frick S, Weinfurter H 2013 Nat. Photonics 7 382Google Scholar

    [7]

    夏志林, 邵建达, 范正修 2007 物理学报 56 400Google Scholar

    Xia Z L, Shao J D, Fan Z X 2007 Acta Phys. Sin. 56 400Google Scholar

    [8]

    张文学, 王继红, 任戈 2020 强激光与粒子束 32 051001

    Zhang W X, Wang J H, Ren G 2020 High Power Laser Part. Beams 32 051001

    [9]

    陆冬筱, 房文汇, 李玉瑶, 李金华, 王笑军 2020 中国光学 13 919Google Scholar

    Lu D X, Fang W H, Li Y Y, Li J H, Wang X J 2020 Chin. Opt. 13 919Google Scholar

    [10]

    Liu W B, Wang Z D, Liu X H, Zeng N Y, Liu Y R, Alsaadi F E 2017 Neurocomputing 234 11Google Scholar

    [11]

    Koutsoukas A, Monaghan K J, Li X L, Huan J 2017 J. Cheminformatics 9 42Google Scholar

    [12]

    Gibney E 2016 Nature 529 445Google Scholar

    [13]

    Gibney E 2016 Nature 531 284Google Scholar

    [14]

    Upadhya V, Sastry P S 2019 J. Indian Inst. Sci. 99 225Google Scholar

    [15]

    Zhang N, Ding S F, Zhang J, Xue Y 2018 Neurocomputing 275 1186Google Scholar

    [16]

    Carleo G, Troyer M 2017 Science 355 602Google Scholar

    [17]

    Shawe T J, Sun S 2011 Neurocomputing 74 3609Google Scholar

    [18]

    Barakat N, Bradley A P 2010 Neurocomputing 74 178Google Scholar

    [19]

    Vapnik V 1999 IEEE Trans. Neural Networks 10 988Google Scholar

    [20]

    Chrapkiewicz R 2015 J. Opt. Soc. Am. B 31 B8

    [21]

    Lugiato L A, Pessina E M 1993 Quantum Opt. 5 341Google Scholar

    [22]

    Jackson J D 2001 Classical Electrodynamics (3rd Ed.) (New York: John Wiley and Sons) p13

    [23]

    Hecht D L 1977 IEEE Trans. Sonics Ultrason. 24 7Google Scholar

    [24]

    郭硕鸿 2009 电动力学 (第三版) (北京: 高等教育出版社) 第112 页

    Guo S H 2009 Electrodynamics (3rd Ed.) (Beijing: Higher Education Press) p112 (in Chinese)

    [25]

    Xiu D 2009 Commun. Comput. Phys. 5 242

    [26]

    Tian C S, Larkin A I 2004 Phys. Rev. B 70 035305Google Scholar

    [27]

    Bao W Z, Jiang S D, Tang Q L, Zhang Y 2015 J. Comput. Phys. 296 72Google Scholar

    [28]

    徐频捷, 王诲喆, 李策, 唐丹, 赵地 2020 计算机工程与科学 42 397Google Scholar

    Xu P J, Wang H Z, Li C, Tang D, Zhao D 2020 Comput. Eng. Sci. 42 397Google Scholar

    [29]

    Song Y, Schwing A G, Zemel R S, Urtasun R 2016 Comput. Sci. 48 2169

    [30]

    Kroese D P, Porotsky S, Rubinstein R Y 2006 Method. Comput. Appl. Probab. 8 383Google Scholar

    [31]

    Chren W A 1998 IEEE Trans. Circuits Syst. II-Express Briefs 45 303Google Scholar

    [32]

    Lavrać N, Cestnik B, Gamberger D, Flach P 2004 Mach. Learn. 57 115Google Scholar

    [33]

    宋鹤鸣 2019 工业控制计算机 32 99Google Scholar

    Song H M 2019 Ind. Control Comput. 32 99Google Scholar

    [34]

    Zhuo H H, Yang Q 2014 Artif. Intell. 212 80Google Scholar

    [35]

    He K M, Zhang X Y, Ren S Q, Sun J 2016 2016 IEEE Conference on Computer Vision and Pattern Recognition Seattle, America, June 27–30, 2016 p770

  • 图 1  (a) 模型示意图; (b) 光强度分布, 其中实线表示入射光信号, 虚线和点划线分别表示反射光$I^{\rm R}$和透射光$I^{\rm T}$; (c) 卷积神经网络示意图

    Fig. 1.  (a) Schematic of our model; (b) light intensity distributions where the solid line is the probe light, and the dashed and the dot-dashed lines denote $I^{\rm R}$ and $I^{\rm T}$, respectively; (c) architecture of the convolutional neural network.

    图 2  (a) 训练过程中, 损失函数${\cal{L}}$随epoch的变化; (b) 训练过程精确度$VA$随epoch的变化; (c) 反射信号训练出的网络的预测概率分布$P^{\rm R}(z^{\rm c}|I)$; (d)透射信号训练出的网络的预测概率分布$P^{\rm T}(z^{\rm c}|I)$

    Fig. 2.  (a) Dependence of ${\cal{L}}$ on epochs in the training process; (b) dependence of $VA$ on epochs in the training process; (c) typical inferential probability $P^{\rm R}(z^{\rm c}|I)$; (d) typical inferential probability $P^{\rm T}(z^{\rm c}|I)$.

    图 3  (a) 杂质大小泛化; (b) 杂质折射率泛化; (c) 杂质形状泛化. (a1), (b1)和(c1)表示泛化精确度; (a2), (b2)和(c2)表示典型数据下的泛化预测概率$P^{\rm R}(z^{\rm c}|I)$. (d) 多形状杂质联合训练后的网络预测, 其中(d1)表示测试精确度, (d2)表示典型数据下的预测概率

    Fig. 3.  (a)–(c) Generalization capability of the convolutional neural network, where (a1), (b1) and (c1) denote the generalization $VA$, and (a2), (b2), (c2) correspond to the typical inferential probability $P^{\rm R}(z^{\rm c}|I)$, respectively; (d) inferential probability of neural network trained by impurities with different geometries, where (d1) denotes the testing $VA$, and (d2) corresponds to the typical inferential probability $P^{\rm R}(z^{\rm c}|I)$.

    图 4  (a) FCNN结构示意图; (b)−(d) 两种神经网络的泛化能力比较, 其中 (b1), (c1)和(d1)分别表示反射信号训练下网络杂质大小、杂质折射率和杂质形状的泛化精确度, (b2), (c2) 和(d2)分别表示透射信号训练下网络杂质大小、杂质折射率和杂质形状的泛化精确度

    Fig. 4.  (a) Architecture of the fully connected neural network; (b)−(d) comparison of the generalization capability between the CNN and the FCNN. (b1), (c1) and (d1) display the $VA$ of the NNs trained by the reflection signals, and (b2), (c2) and (d2) show the $VA$ of the NNs trained by the transmission signals.

    图 5  (a) 凹杂质的训练过程中, 损失函数${\cal{L}}$随epoch的变化; (b) 杂质大小的泛化精确度

    Fig. 5.  (a) Dependence of ${\cal{L}}$ on epochs in the training process of concave impurity; (b) generalization $VA$ of the impurity size.

  • [1]

    Gyongyosi L, Imre S 2019 Comput. Sci. Rev. 31 51Google Scholar

    [2]

    Williams C P 2010 Explorations in Quantum Computing (London: Springer Science and Business Media) p3

    [3]

    Bruzewicz C D, Chiaverini J, McConnell R, Sage J M 2019 Appl. Phys. Rev. 6 021314Google Scholar

    [4]

    Gisin N, Thew R 2007 Nat. Photonics 1 165Google Scholar

    [5]

    Brassard G 2003 Found. Phys. 33 1593Google Scholar

    [6]

    Nauerth S, Moll F, Rau M, Fuchs C, Horwath J, Frick S, Weinfurter H 2013 Nat. Photonics 7 382Google Scholar

    [7]

    夏志林, 邵建达, 范正修 2007 物理学报 56 400Google Scholar

    Xia Z L, Shao J D, Fan Z X 2007 Acta Phys. Sin. 56 400Google Scholar

    [8]

    张文学, 王继红, 任戈 2020 强激光与粒子束 32 051001

    Zhang W X, Wang J H, Ren G 2020 High Power Laser Part. Beams 32 051001

    [9]

    陆冬筱, 房文汇, 李玉瑶, 李金华, 王笑军 2020 中国光学 13 919Google Scholar

    Lu D X, Fang W H, Li Y Y, Li J H, Wang X J 2020 Chin. Opt. 13 919Google Scholar

    [10]

    Liu W B, Wang Z D, Liu X H, Zeng N Y, Liu Y R, Alsaadi F E 2017 Neurocomputing 234 11Google Scholar

    [11]

    Koutsoukas A, Monaghan K J, Li X L, Huan J 2017 J. Cheminformatics 9 42Google Scholar

    [12]

    Gibney E 2016 Nature 529 445Google Scholar

    [13]

    Gibney E 2016 Nature 531 284Google Scholar

    [14]

    Upadhya V, Sastry P S 2019 J. Indian Inst. Sci. 99 225Google Scholar

    [15]

    Zhang N, Ding S F, Zhang J, Xue Y 2018 Neurocomputing 275 1186Google Scholar

    [16]

    Carleo G, Troyer M 2017 Science 355 602Google Scholar

    [17]

    Shawe T J, Sun S 2011 Neurocomputing 74 3609Google Scholar

    [18]

    Barakat N, Bradley A P 2010 Neurocomputing 74 178Google Scholar

    [19]

    Vapnik V 1999 IEEE Trans. Neural Networks 10 988Google Scholar

    [20]

    Chrapkiewicz R 2015 J. Opt. Soc. Am. B 31 B8

    [21]

    Lugiato L A, Pessina E M 1993 Quantum Opt. 5 341Google Scholar

    [22]

    Jackson J D 2001 Classical Electrodynamics (3rd Ed.) (New York: John Wiley and Sons) p13

    [23]

    Hecht D L 1977 IEEE Trans. Sonics Ultrason. 24 7Google Scholar

    [24]

    郭硕鸿 2009 电动力学 (第三版) (北京: 高等教育出版社) 第112 页

    Guo S H 2009 Electrodynamics (3rd Ed.) (Beijing: Higher Education Press) p112 (in Chinese)

    [25]

    Xiu D 2009 Commun. Comput. Phys. 5 242

    [26]

    Tian C S, Larkin A I 2004 Phys. Rev. B 70 035305Google Scholar

    [27]

    Bao W Z, Jiang S D, Tang Q L, Zhang Y 2015 J. Comput. Phys. 296 72Google Scholar

    [28]

    徐频捷, 王诲喆, 李策, 唐丹, 赵地 2020 计算机工程与科学 42 397Google Scholar

    Xu P J, Wang H Z, Li C, Tang D, Zhao D 2020 Comput. Eng. Sci. 42 397Google Scholar

    [29]

    Song Y, Schwing A G, Zemel R S, Urtasun R 2016 Comput. Sci. 48 2169

    [30]

    Kroese D P, Porotsky S, Rubinstein R Y 2006 Method. Comput. Appl. Probab. 8 383Google Scholar

    [31]

    Chren W A 1998 IEEE Trans. Circuits Syst. II-Express Briefs 45 303Google Scholar

    [32]

    Lavrać N, Cestnik B, Gamberger D, Flach P 2004 Mach. Learn. 57 115Google Scholar

    [33]

    宋鹤鸣 2019 工业控制计算机 32 99Google Scholar

    Song H M 2019 Ind. Control Comput. 32 99Google Scholar

    [34]

    Zhuo H H, Yang Q 2014 Artif. Intell. 212 80Google Scholar

    [35]

    He K M, Zhang X Y, Ren S Q, Sun J 2016 2016 IEEE Conference on Computer Vision and Pattern Recognition Seattle, America, June 27–30, 2016 p770

  • [1] 郭焱, 吕恒, 丁春玲, 袁晨智, 金锐博. 分数阶涡旋光衍射过程的机器学习识别. 物理学报, 2025, 74(1): 1-8. doi: 10.7498/aps.74.20241458
    [2] 张旭, 丁进敏, 侯晨阳, 赵一鸣, 刘鸿维, 梁生. 基于机器学习的激光匀光整形方法. 物理学报, 2024, 73(16): 164205. doi: 10.7498/aps.73.20240747
    [3] 张嘉晖. 蛋白质计算中的机器学习. 物理学报, 2024, 73(6): 069301. doi: 10.7498/aps.73.20231618
    [4] 刘鸿江, 刘逸飞, 谷付星. 基于深度学习的微纳光纤自动制备系统. 物理学报, 2024, 73(10): 104207. doi: 10.7498/aps.73.20240171
    [5] 欧阳鑫健, 张岩星, 王之龙, 张锋, 陈韦嘉, 庄园, 揭晓, 刘来君, 王大威. 面向铁电相变的机器学习: 基于图卷积神经网络的分子动力学模拟. 物理学报, 2024, 73(8): 086301. doi: 10.7498/aps.73.20240156
    [6] 黄宇航, 陈理想. 基于未训练神经网络的分数傅里叶变换成像. 物理学报, 2024, 73(9): 094201. doi: 10.7498/aps.73.20240050
    [7] 刘烨, 牛赫然, 李兵兵, 马欣华, 崔树旺. 机器学习在宇宙线粒子鉴别中的应用. 物理学报, 2023, 72(14): 140202. doi: 10.7498/aps.72.20230334
    [8] 管星悦, 黄恒焱, 彭华祺, 刘彦航, 李文飞, 王炜. 生物分子模拟中的机器学习方法. 物理学报, 2023, 72(24): 248708. doi: 10.7498/aps.72.20231624
    [9] 欧秀娟, 肖奕. RNA扭转角预测的深度学习方法. 物理学报, 2023, 72(24): 248703. doi: 10.7498/aps.72.20231069
    [10] 孙涛, 袁健美. 基于深度学习原子特征表示方法的Janus过渡金属硫化物带隙预测. 物理学报, 2023, 72(2): 028901. doi: 10.7498/aps.72.20221374
    [11] 朱琦, 许多, 张元军, 李玉娟, 王文, 张海燕. 基于卷积神经网络的白蚀缺陷超声探测. 物理学报, 2022, 71(24): 244301. doi: 10.7498/aps.71.20221504
    [12] 战庆亮, 葛耀君, 白春锦. 基于深度学习的流场时程特征提取模型. 物理学报, 2022, 71(7): 074701. doi: 10.7498/aps.71.20211373
    [13] 赵智鹏, 周双, 王兴元. 基于深度学习的新混沌信号及其在图像加密中的应用. 物理学报, 2021, 70(23): 230502. doi: 10.7498/aps.70.20210561
    [14] 林键, 叶梦, 朱家纬, 李晓鹏. 机器学习辅助绝热量子算法设计. 物理学报, 2021, 70(14): 140306. doi: 10.7498/aps.70.20210831
    [15] 陈江芷, 杨晨温, 任捷. 基于波动与扩散物理系统的机器学习. 物理学报, 2021, 70(14): 144204. doi: 10.7498/aps.70.20210879
    [16] 徐昭, 周昕, 白星, 李聪, 陈洁, 倪洋. 基于深度学习的相位截断傅里叶变换非对称加密系统攻击方法. 物理学报, 2021, 70(14): 144202. doi: 10.7498/aps.70.20202075
    [17] 王伟, 揭泉林. 基于机器学习J1-J2反铁磁海森伯自旋链相变点的识别方法. 物理学报, 2021, 70(23): 230701. doi: 10.7498/aps.70.20210711
    [18] 陈炜, 郭媛, 敬世伟. 基于深度学习压缩感知与复合混沌系统的通用图像加密算法. 物理学报, 2020, 69(24): 240502. doi: 10.7498/aps.69.20201019
    [19] 郎利影, 陆佳磊, 于娜娜, 席思星, 王雪光, 张雷, 焦小雪. 基于深度学习的联合变换相关器光学图像加密系统去噪方法. 物理学报, 2020, 69(24): 244204. doi: 10.7498/aps.69.20200805
    [20] 神经网络的自适应删剪学习算法及其应用. 物理学报, 2001, 50(4): 674-681. doi: 10.7498/aps.50.674
计量
  • 文章访问数:  6042
  • PDF下载量:  221
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-03-03
  • 修回日期:  2021-04-14
  • 上网日期:  2021-05-14
  • 刊出日期:  2021-08-20

/

返回文章
返回