深度神经网络在自动瞄靶技术中的应用研究

doi:10.16568/j.0254-6086.2022s1006

核聚变与等离子体物理 ›› 2022, Vol. 42 ›› Issue (s1): 125-130.DOI: 10.16568/j.0254-6086.2022s1006

深度神经网络在自动瞄靶技术中的应用研究

夏立琼，陈伯伦，王鹏，王峰*

(中国工程物理研究院激光聚变研究中心，绵阳 621900)

收稿日期:2021-07-22 修回日期:2022-01-28 出版日期:2022-05-15 发布日期:2022-05-23
作者简介:夏立琼(1990-)，女，重庆人，硕士研究生，助理工程师，从事等离子体诊断系统控制技术研究。

Research on the application of deep neural network in automatic targeting technology

XIA Li-qiong, CHEN Bo-lun, WANG Peng, WANG feng

(Laser Fusion Research Center, China Academy of Engineering Physics (CAEP), Mianyang 621900)

Received:2021-07-22 Revised:2022-01-28 Online:2022-05-15 Published:2022-05-23

摘要/Abstract

摘要： 基于Mask R-CNN模型，对惯性约束聚变实验研究中靶图进行关键结构的语义分割，通过计算中心来定位目标靶点位置，通过模拟靶图数据来验证算法的可行性。在算法验证过程中通过程序批量生成不同结构参数、不同角度的模拟靶图作为数据集，然后通过增噪、成像位置变换等操作拓展样本数量。在大样本数量基础上对算法模型进行训练测试，实现语义分割，通过计算注入孔的中心得到目标靶点位置。测试结果显示准确率和召回率均在97%以上，在靶点识别精度上优于10个像素点。

关键词: ICF, 双目瞄准, Mask R-CNN, 语义分割

Abstract: Using the Mask R-CNN to segment the key structure of the CCDs image in inertial confinement fusion (ICF) experimental research, the center of the entrance hole is calculated as the position of the target, and the rationality and feasibility is verified with the simulated image data. Firstly, the program generates batches of simulated images with different structure parameters and different angles as a data set, secondly the operation of noise enhancement and position transformation are made to expand the samples, finally the algorithm model is trained and tested based on the samples, and the center of the entrance hole can be located as the position of the target. The test results show that the accuracy rate and recall rate are above 97%, and the target recognition accuracy is better than 10 pixels.

Key words: ICF, The binocular vision system, Mask R-CNN, Semantic segmentation

中图分类号:

TL62+9

夏立琼, 陈伯伦, 王鹏, 王峰. 深度神经网络在自动瞄靶技术中的应用研究[J]. 核聚变与等离子体物理, 2022, 42(s1): 125-130.

XIA Li-qiong, CHEN Bo-lun, WANG Peng, WANG feng. Research on the application of deep neural network in automatic targeting technology[J]. Nuclear Fusion and Plasma Physics, 2022, 42(s1): 125-130.

参考文献

[1] Haynam C A, Wegner P J, Auerbach J M. et al. National ignition facility laser performance status [J]. Applied Optics, 2007, 46(16): 3276.

[2] Cavailler C. Inertial fusion with the LMJ [J]. Plasma Phys. Contr. Fusion, 2005, 47(12B): B389.

[3] Bell P M. Diagnostic technology development for NIF by LLNL experimental programs [C]. USA: IEEE International Conference on Plasma Science, 2004.

[4] Nishimura H., Azechi H., Nakai M., et al. Recent progress on diagnostic developments for ICF research at ILE Osaka [J]. Plasma Physics Reports, 2003, 24(2): 114−122.

[5] Bell P M, Landen O L, Weber F A, et al. Target diagnostic technology research for the LLNL ICF and HED program [J]. Fusion Science and Technology, 2003, Sup: 871−876.

[6] 汪威, 史铁林, 来五星, 等. ICF诊断设备搭载平台结构设计与误差分析 [J]. 强激光与粒子束, 2010, 22(6): 85−90.

[7] 齐文博, 张琦, 何俊华, 等. 激光核聚变诊断设备双光束交汇瞄准技术研究 [J]. 应用光学, 2009, 30(6): 1032−1035.

[8] 卢卫涛, 闫亚东, 张敏, 等. 公共诊断搭载平台双CCD交汇瞄准系统 [J]. 应用光学, 2011, 32(4): 630−635.

[9] 王传珂, 江少恩, 丁永坤, 等. 我国激光惯性约束聚变实验与诊断技术早期研究历史 [J]. 物理, 2014, 43(2): 120−126.

[10] 王峰, 张兴, 理玉龙, 等. 激光惯性约束聚变研究中高时空诊断技术研究进展 [J]. 强激光与粒子束, 2020, 32(11): 20−35.

[11] Clayton D, Tritz K, Stutman D, et al. Electron temperature profile reconstructions from multi-energy SXR measurements using neural networks [J]. Plasma Phys. Contr. Fusion, 2013, 55(9): 095015.

[12] Girshick R. Fast R-CNN [C]. USA: 2015 IEEE International Conference on Computer Vision (ICCV), 2015.

[13] Ren S，HeKaiming, Girshick R，et al. Faster RCNN towards real-time object detection with region proposal networks [J]. IEEE Transon Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137−1149．

[14] He K, Gkioxari G, Dollár P, et al. Mask R-CNN [C]. USA: IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017.

[15] Fawcett T. ROC graphs: notes and practical consideration for researchers [J]. Pattern Recognition Letters, 2003, 31(8): 1−38.

深度神经网络在自动瞄靶技术中的应用研究

Research on the application of deep neural network in automatic targeting technology

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics