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

基于人工神经网络在线学习方法优化磁屏蔽特性参数

彭向凯 吉经纬 李琳 任伟 项静峰 刘亢亢 程鹤楠 张镇 屈求智 李唐 刘亮 吕德胜

引用本文:
Citation:

基于人工神经网络在线学习方法优化磁屏蔽特性参数

彭向凯, 吉经纬, 李琳, 任伟, 项静峰, 刘亢亢, 程鹤楠, 张镇, 屈求智, 李唐, 刘亮, 吕德胜

Online learning method based on artificial neural network to optimize magnetic shielding characteristic parameters

Peng Xiang-Kai, Ji Jing-Wei, Li Lin, Ren Wei, Xiang Jing-Feng, Liu Kang-Kang, Cheng He-Nan, Zhang Zhen, Qu Qiu-Zhi, Li Tang, Liu Liang, Lü De-Sheng
PDF
HTML
导出引用
  • 磁屏蔽在磁场敏感的装置如原子钟、原子干涉仪等精密设备中发挥重要的作用, 在变化外磁场下的某个磁屏蔽内部剩余磁场, 可以通过Jiles-Atherton磁滞模型和磁屏蔽系数计算得出, 根据计算结果可以进行主动补偿来抵消内部磁场的改变. 然而实际应用中磁滞模型中五个与磁屏蔽相关的参数以及磁场衰减的两个参数的准确值的获得是比较困难的, 通常根据实测磁滞回线人工匹配调节参数会花费大量时间且很难确保最终参数是全局最优值. 基于人工神经网络的机器学习方法已经成为一种对复杂模型进行参数优化的有效手段, 得益于现代计算机强大的运算能力, 该过程通常远远快于人工参数调节, 并有更大概率找到全局最优值, 获得优于手工调节的参数值. 本文利用人工神经网络在线机器学习的方法, 对磁滞模型的五个参数与磁屏蔽的另外两个屏蔽相关参数进行优化测定, 并对模拟卫星磁场环境下磁屏蔽内剩余磁场进行预测. 通过实际测量屏蔽筒内剩余磁场与预测值比对, 发现通过机器学习方法得到的磁屏蔽特性参数优于手动找到的参数, 且所用时间大大缩短. 该结果不仅有助于更好地进行磁场补偿, 用于冷原子系统参数优化调整, 更重要的是验证了神经网络在多参数物理系统中的应用, 可以使其他多参数共同作用的物理实验进行最优参数的快速确定.
    Magnetic shielding plays an important role in magnetically susceptible devices such as cold atom clocks, atomic interferometers and other precision equipment. The residual magnetic field in a magnetic shield under a varying external magnetic field can be calculated by the Jiles-Atherton (J-A) hysteresis model and magnetic shielding coefficient. According to the calculation results, the variation of internal magnetic field can be compensated for the active compensation coils. However, it is difficult to practically obtain the exact values of the five magnetic-shielding-related parameters in the J-A hysteresis model and the other two magnetic-field-attenuation-related parameters. It usually takes a lot of time to match the parameters manually according to the measured hysteresis loop and it is difficult to ensure that the final parameters are the global optimal values. The machine learning method based on artificial neural network has been used as an efficient method to optimize the parameters of complex systems. Owing to the powerful computing capability of modern computers, using the artificial neural network to optimize parameters is usually much faster than manual optimization method, and has a greater probability of finding the global optimal parameters. In this paper, the five J-A parameters and the other two parameters relating to magnetic field attenuation are optimized by the method of online learning based on artificial neural network, and the residual magnetic field in the magnetic shield is predicted under the simulated satellite magnetic field environment. By comparing the measured residual magnetic field with the predicted value, it is found that the machine learning method can optimize the magnetic shielding characteristic parameters more quickly and accurately than the manual optimization method. This result can not only help us to compensate for the magnetic field better and optimize the parameters of our cold atom system, but also validate the application of neural network in a multi-parameter physical system. This proves that the in-depth learning neural network can be conveniently applied to other physical experiments with multi-parameter interaction, and can quickly determine the optimal parameters needed in the experiment. This application is especially effective for remote experiments with slow response to parameter adjustment, such as scientific experiments carried out on satellites or deep space.
      通信作者: 刘亮, liang.liu@siom.ac.cn ; 吕德胜, dslv@siom.ac.cn
    • 基金项目: 国家自然科学基金(批准号: 11704391)资助的课题.
      Corresponding author: Liu Liang, liang.liu@siom.ac.cn ; Lü De-Sheng, dslv@siom.ac.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant No. 11704391).
    [1]

    Guéna J, Abgrall M, Rovera D, Laurent P H, Chupin B, Lours M, Santarelli G, Rosenbusch P, Tobar M E, Li R X, Gibble K, Clairon A, Bize S 2012 IEEE Trans. Ultra. Ferro. Freq. Cont. 59 391Google Scholar

    [2]

    Ovchinnikov Y, Marra G 2011 Metrologia 48 87Google Scholar

    [3]

    Levi F, Calonico D, Calosso C E, Godone A, Micalizio S, Costanzo G A 2014 Metrologia 51 270Google Scholar

    [4]

    Gerginov V, Nemitz N, Weyers S, Schroder R, Griebsch D, Wynands R 2010 Metrologia 47 65Google Scholar

    [5]

    王瑾, 詹明生 2018 物理学报 67 160402Google Scholar

    Wang J, Zhan M S 2018 Acta Phys. Sin. 67 160402Google Scholar

    [6]

    Moric I, Laurent P, Chatard P, de Graeve C M, Thomin S, Christophe V, Grosjean O 2014 Acta Astronaut. 102 287Google Scholar

    [7]

    Kubelka-Lange A, Herrmann S, Grosse J, Lämmerzahl C, Rasel E M, Braxmaier C 2016 Rev. Sci. Instrum. 87 063101Google Scholar

    [8]

    Morić I, de Graeve C M, Grosjean O, Laurent P 2014 Rev. Sci. Instrum. 85 075117Google Scholar

    [9]

    Li L, Ji J W, Ren W, Zhao X, Peng X K, Xiang J F, Lü D S, Liu L 2016 Chin. Phys. B 25 073201Google Scholar

    [10]

    Peng X K, Li L, Ren W, Ji J W, Xiang J F, Zhao J B, Ye M F, Zhao X, Wang B, Qu Q Z, Li T, Liu L, Lü D S 2019 AIP Adv. 9 035222Google Scholar

    [11]

    Liu L, Lü D S, Chen W B, Li T, Qu Q Z, Wang B, Li L, Ren W, Dong Z R, Zhao J B, Xia W B, Zhao X, Ji J W, Ye M F, Sun Y G, Yao Y Y, Song D, Liang Z G, Hu S J, Yu D H, Hou X, Shi W, Zang H G, Xiang J F, Peng X K, Wang Y Z 2018 Nat. Commun. 9 2760Google Scholar

    [12]

    Jiles D C, Atherton D L 1984 J. Appl. Phys. 55 2115Google Scholar

    [13]

    Jiles D C, Thoelke J B 1989 IEEE Trans. Magn. 25 3928Google Scholar

    [14]

    Jiles D C, Thoelke J B, Devine M K 1992 IEEE Trans. Magn. 28 27Google Scholar

    [15]

    Goodfellow I, Bengio Y, Courville A 2016 Deep Learning (Cambridge: MIT press) pp2-15

    [16]

    Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, Graves A, Riedmiller M, Fidjeland A K, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D 2015 Nature 518 529Google Scholar

    [17]

    Silver D, Huang A, Maddison C J, Guez A, Sifre L, Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D 2016 Nature 529 484Google Scholar

    [18]

    Wigley P B, Everitt P J, van den Hengel A, Bastian J W, Sooriyabandara M A, McDonald G D, Hardman K S, Quinlivan C D, Manju P, Kuhn C C N, Petersen I R, Luiten A N, Hope J J, Robins N P, Hush M R 2016 Sci. Rep. 6 25890Google Scholar

    [19]

    Geisel I, Cordes K, Mahnke J, Jöllenbeck S, Ostermann J, Ertmer W, Klempt C 2013 Appl. Phys. Lett. 102 214105Google Scholar

    [20]

    Heinze G, Rudolf A, Beil F, Halfmann T 2010 Phys. Rev. A 81 053801Google Scholar

    [21]

    Palittapongarnpim P, Wittek P, Zahedinejad E, Vedaie S, Sanders B C 2017 Neurocomputing 268 116Google Scholar

    [22]

    Li C, de Celis Leal D R, Rana S, Gupta S, Sutti A, Greenhill S, Slezak T, Height M, Venkatesh S 2017 Sci. Rep. 7 5683Google Scholar

    [23]

    August M, Ni X 2017 Phys. Rev. A 95 012335Google Scholar

    [24]

    Ju S, Shiga T, Feng L, Hou Z, Tsuda K, Shiomi J 2017 Phys. Rev. X 7 021024

    [25]

    Mavadia S, Frey V, Sastrawan J, Dona S, Biercuk M J 2017 Nat. Commun. 8 14106Google Scholar

    [26]

    Tranter A D, Slatyer H J, Hush M R, Leung A C, Everett J L, Paul K V, Vernaz-Gris P, Lam P K, Buchler B C, Campbell G T 2018 Nat. Commun. 9 4360Google Scholar

    [27]

    Li H Q, Li Q F, Xu X B, Lu T B, Zhang J J, Li L 2009 IEEE Trans. Magn. 47 1094

    [28]

    李慧奇, 杨延菊, 邓聘 2012 电网与清洁能源 28 19Google Scholar

    Li H Q, Yang Y J, Deng P 2012 Power System and Clean Energy 28 19Google Scholar

    [29]

    Araneo R, Celozzi S 2003 IEEE Trans. Magn. 39 1046Google Scholar

    [30]

    Bergqvist A J 1996 IEEE Trans. Magn. 32 4213Google Scholar

    [31]

    Bastos J P A, Sadowski N 2003 Electromagnetic Modeling by Finite Element Methods (Boca Raton: CRC press) pp250-275

    [32]

    Hush M R, Slatyer H 2017 https://github.com/charmasaur/M-LOOP [2019-2-22]

    [33]

    Byrd R H, Lu P H, Nocedal J, Zhu C 1995 SIAM J. Sci. Comput. 16 1190Google Scholar

    [34]

    Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Ghemawat S 2015 tensorflow.org[2019-2-22]

    [35]

    Hart R A, Xu X, Legere R, Gibble K 2007 Nature 446 892Google Scholar

    [36]

    Wang B, Lü D S, Qu Q Z, Zhao J B, Li T, Liu L, Wang Y Z 2011 Chin. Phys. Lett. 28 63701Google Scholar

  • 图 1  (a)实验装置示意图, 同时也是有限元仿真时所用的模型图; (b)对模型进行测试所用的近地轨道环境磁场

    Fig. 1.  (a) The schematic diagram of the experimental device and also the model diagram used in our finite element simulation; (b) low Earth orbit environmental magnetic field used to test the model.

    图 2  (a)数据所在磁屏蔽筒截面示意图; (b)有限元仿真所得到屏蔽内一个截面上的屏蔽效率分布图; (c)有限元仿真得到的屏蔽内一个截面上的磁化强度比例系数图

    Fig. 2.  (a) A schematic view of the section of the data; (b) the shielding efficiency distribution on a section inside the shield calculated by FEM software; (c) the magnetization intensity ratio coefficient on a section of the shield calculated by FEM software.

    图 3  神经网络调参原理示意图 使用2个隐藏层的全连接神经网络, 每层32个神经元, 一旦神经网络训练完成, 就能调用scipy库预测最优参数

    Fig. 3.  Principle of optimizing with neural network. We use 2 hidden layers of full connected neural network, 32 neurons per layer. Once the neural network training is completed, we can use scipy to predict the optimal parameters

    图 4  (a)当选用2层网络各32个神经元时, 预测标准差收敛性好且最小值仅为4.9; (b)当选用3层网络各64个神经元时, 由于过拟合预测标准差振荡且最小值为27

    Fig. 4.  (a) When 32 neurons of the 2 layers network are selected, the convergence of the prediction standard deviation is good and the minimum value is only 4.9; (b) when 64 neurons of the 3 layers network are selected, the convergence of the prediction standard deviation is poor because of over-fit and the minimum value is 27.

    图 5  自动调参的流程图

    Fig. 5.  The flow chart of optimizing magnetic shielding characteristic parameters.

    图 6  (a)一个典型的求参过程图, 预测参数值的标准差随实验轮次逐渐降低; (b)相应参数计算得到的磁滞回线与实测回线的比较

    Fig. 6.  (a) A typical continuation process graph, the standard deviation of the predicted parameter values is gradually reduced with the experimental round; (b) comparison of hysteresis loop and measured loop calculated by corresponding parameters.

    图 7  另外两组不同随机初始训练参数下, 标准差随实验轮次的收敛图

    Fig. 7.  Convergence graph of standard deviation with experimental rounds under two different random initial training parameters.

    图 8  在近地轨道磁场环境下实测磁场与计算磁场的对比图 (a)横坐标为时间; (b)横坐标为环境磁场; (c) 使用手动调节参数, 自动求得的参数, 以及仅考虑衰减项不考虑磁化项, 计算磁场与实测磁场的差值, 横坐标为时间; (d)横坐标为环境磁场

    Fig. 8.  A comparison of the measured magnetic field with the calculated magnetic field in a near-Earth orbit magnetic field environment; (a) The x axis is time; (b) the x-axis is the ambient magnetic field; (c) use manual adjustment parameters, automatically obtained parameters, and simple $ {B_{SE}}$ to calculate the difference between the magnetic field and the measured magnetic field, the abscissa is time; (d) the x-axis is the ambient magnetic field.

    表 1  手动调参和自动调参得到的参数值

    Table 1.  Parameter values obtained by manual tuning and automatic tuning.

    参数名称 手动参数 自动参数
    Ms 540000 540074
    a 19555 19817
    k 8.0 9.50
    α 0 0
    c 0.2 0.58
    SE 31 36.37
    C –1.8 –2.37
    下载: 导出CSV
  • [1]

    Guéna J, Abgrall M, Rovera D, Laurent P H, Chupin B, Lours M, Santarelli G, Rosenbusch P, Tobar M E, Li R X, Gibble K, Clairon A, Bize S 2012 IEEE Trans. Ultra. Ferro. Freq. Cont. 59 391Google Scholar

    [2]

    Ovchinnikov Y, Marra G 2011 Metrologia 48 87Google Scholar

    [3]

    Levi F, Calonico D, Calosso C E, Godone A, Micalizio S, Costanzo G A 2014 Metrologia 51 270Google Scholar

    [4]

    Gerginov V, Nemitz N, Weyers S, Schroder R, Griebsch D, Wynands R 2010 Metrologia 47 65Google Scholar

    [5]

    王瑾, 詹明生 2018 物理学报 67 160402Google Scholar

    Wang J, Zhan M S 2018 Acta Phys. Sin. 67 160402Google Scholar

    [6]

    Moric I, Laurent P, Chatard P, de Graeve C M, Thomin S, Christophe V, Grosjean O 2014 Acta Astronaut. 102 287Google Scholar

    [7]

    Kubelka-Lange A, Herrmann S, Grosse J, Lämmerzahl C, Rasel E M, Braxmaier C 2016 Rev. Sci. Instrum. 87 063101Google Scholar

    [8]

    Morić I, de Graeve C M, Grosjean O, Laurent P 2014 Rev. Sci. Instrum. 85 075117Google Scholar

    [9]

    Li L, Ji J W, Ren W, Zhao X, Peng X K, Xiang J F, Lü D S, Liu L 2016 Chin. Phys. B 25 073201Google Scholar

    [10]

    Peng X K, Li L, Ren W, Ji J W, Xiang J F, Zhao J B, Ye M F, Zhao X, Wang B, Qu Q Z, Li T, Liu L, Lü D S 2019 AIP Adv. 9 035222Google Scholar

    [11]

    Liu L, Lü D S, Chen W B, Li T, Qu Q Z, Wang B, Li L, Ren W, Dong Z R, Zhao J B, Xia W B, Zhao X, Ji J W, Ye M F, Sun Y G, Yao Y Y, Song D, Liang Z G, Hu S J, Yu D H, Hou X, Shi W, Zang H G, Xiang J F, Peng X K, Wang Y Z 2018 Nat. Commun. 9 2760Google Scholar

    [12]

    Jiles D C, Atherton D L 1984 J. Appl. Phys. 55 2115Google Scholar

    [13]

    Jiles D C, Thoelke J B 1989 IEEE Trans. Magn. 25 3928Google Scholar

    [14]

    Jiles D C, Thoelke J B, Devine M K 1992 IEEE Trans. Magn. 28 27Google Scholar

    [15]

    Goodfellow I, Bengio Y, Courville A 2016 Deep Learning (Cambridge: MIT press) pp2-15

    [16]

    Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, Graves A, Riedmiller M, Fidjeland A K, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D 2015 Nature 518 529Google Scholar

    [17]

    Silver D, Huang A, Maddison C J, Guez A, Sifre L, Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D 2016 Nature 529 484Google Scholar

    [18]

    Wigley P B, Everitt P J, van den Hengel A, Bastian J W, Sooriyabandara M A, McDonald G D, Hardman K S, Quinlivan C D, Manju P, Kuhn C C N, Petersen I R, Luiten A N, Hope J J, Robins N P, Hush M R 2016 Sci. Rep. 6 25890Google Scholar

    [19]

    Geisel I, Cordes K, Mahnke J, Jöllenbeck S, Ostermann J, Ertmer W, Klempt C 2013 Appl. Phys. Lett. 102 214105Google Scholar

    [20]

    Heinze G, Rudolf A, Beil F, Halfmann T 2010 Phys. Rev. A 81 053801Google Scholar

    [21]

    Palittapongarnpim P, Wittek P, Zahedinejad E, Vedaie S, Sanders B C 2017 Neurocomputing 268 116Google Scholar

    [22]

    Li C, de Celis Leal D R, Rana S, Gupta S, Sutti A, Greenhill S, Slezak T, Height M, Venkatesh S 2017 Sci. Rep. 7 5683Google Scholar

    [23]

    August M, Ni X 2017 Phys. Rev. A 95 012335Google Scholar

    [24]

    Ju S, Shiga T, Feng L, Hou Z, Tsuda K, Shiomi J 2017 Phys. Rev. X 7 021024

    [25]

    Mavadia S, Frey V, Sastrawan J, Dona S, Biercuk M J 2017 Nat. Commun. 8 14106Google Scholar

    [26]

    Tranter A D, Slatyer H J, Hush M R, Leung A C, Everett J L, Paul K V, Vernaz-Gris P, Lam P K, Buchler B C, Campbell G T 2018 Nat. Commun. 9 4360Google Scholar

    [27]

    Li H Q, Li Q F, Xu X B, Lu T B, Zhang J J, Li L 2009 IEEE Trans. Magn. 47 1094

    [28]

    李慧奇, 杨延菊, 邓聘 2012 电网与清洁能源 28 19Google Scholar

    Li H Q, Yang Y J, Deng P 2012 Power System and Clean Energy 28 19Google Scholar

    [29]

    Araneo R, Celozzi S 2003 IEEE Trans. Magn. 39 1046Google Scholar

    [30]

    Bergqvist A J 1996 IEEE Trans. Magn. 32 4213Google Scholar

    [31]

    Bastos J P A, Sadowski N 2003 Electromagnetic Modeling by Finite Element Methods (Boca Raton: CRC press) pp250-275

    [32]

    Hush M R, Slatyer H 2017 https://github.com/charmasaur/M-LOOP [2019-2-22]

    [33]

    Byrd R H, Lu P H, Nocedal J, Zhu C 1995 SIAM J. Sci. Comput. 16 1190Google Scholar

    [34]

    Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Ghemawat S 2015 tensorflow.org[2019-2-22]

    [35]

    Hart R A, Xu X, Legere R, Gibble K 2007 Nature 446 892Google Scholar

    [36]

    Wang B, Lü D S, Qu Q Z, Zhao J B, Li T, Liu L, Wang Y Z 2011 Chin. Phys. Lett. 28 63701Google Scholar

  • [1] 李策, 杨栋梁, 孙林锋. 基于二维层状材料的神经形态器件研究进展. 物理学报, 2022, 71(21): 218504. doi: 10.7498/aps.71.20221424
    [2] 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
    [3] 赵兴东, 张莹莹, 刘伍明. 光晶格中超冷原子系统的磁激发. 物理学报, 2019, 68(4): 043703. doi: 10.7498/aps.68.20190153
    [4] 院琳, 杨雪松, 王秉中. 基于经验知识遗传算法优化的神经网络模型实现时间反演信道预测. 物理学报, 2019, 68(17): 170503. doi: 10.7498/aps.68.20190327
    [5] 赵杰, 唐德礼, 许丽, 李平川, 张帆, 李建, 桂兵仪. 阳极磁屏蔽对阳极层霍尔推力器内磁极刻蚀的影响. 物理学报, 2019, 68(21): 215202. doi: 10.7498/aps.68.20190654
    [6] 林飞飞, 曾喆昭. 不确定分数阶时滞混沌系统自适应神经网络同步控制. 物理学报, 2017, 66(9): 090504. doi: 10.7498/aps.66.090504
    [7] 朱霖河, 赵洪涌. 时滞惯性神经网络的稳定性和分岔控制. 物理学报, 2014, 63(9): 090203. doi: 10.7498/aps.63.090203
    [8] 冯高平, 孙羽, 郑昕, 胡水明. 氦原子精密光谱实验中的精密磁场设计与测量. 物理学报, 2014, 63(12): 123201. doi: 10.7498/aps.63.123201
    [9] 吴长江, 阮军, 陈江, 张辉, 张首刚. 应用于铯原子喷泉钟的二维磁光阱研制. 物理学报, 2013, 62(6): 063201. doi: 10.7498/aps.62.063201
    [10] 赵永平, 王康康. 具有增加删除机制的正则化极端学习机的混沌时间序列预测. 物理学报, 2013, 62(24): 240509. doi: 10.7498/aps.62.240509
    [11] 张太宁, 孟春宁, 刘润蓓, 常胜江. 基于暗瞳图像的人眼视线估计. 物理学报, 2013, 62(13): 134204. doi: 10.7498/aps.62.134204
    [12] 曹明涛, 邱淑伟, 郭文阁, 刘韬, 韩亮, 刘昊, 张沛, 张首刚, 高宏, 李福利. 铷原子蒸汽中的光偏振旋转效应. 物理学报, 2012, 61(16): 164208. doi: 10.7498/aps.61.164208
    [13] 吴然超. 时滞离散神经网络的同步控制. 物理学报, 2009, 58(1): 139-142. doi: 10.7498/aps.58.139
    [14] 张 敏, 胡寿松. 不确定时滞混沌系统的自适应动态神经网络控制. 物理学报, 2008, 57(3): 1431-1438. doi: 10.7498/aps.57.1431
    [15] 楼旭阳, 崔宝同. 混沌时滞神经网络系统的反同步. 物理学报, 2008, 57(4): 2060-2067. doi: 10.7498/aps.57.2060
    [16] 王占山, 张化光. 时滞递归神经网络中神经抑制的作用. 物理学报, 2006, 55(11): 5674-5680. doi: 10.7498/aps.55.5674
    [17] 司马文霞, 刘 凡, 孙才新, 廖瑞金, 杨 庆. 基于改进的径向基函数神经网络的铁磁谐振系统混沌控制. 物理学报, 2006, 55(11): 5714-5720. doi: 10.7498/aps.55.5714
    [18] 张 强, 高 琳, 王 超, 许 进. 时滞双向联想记忆神经网络的全局稳定性. 物理学报, 2003, 52(7): 1600-1605. doi: 10.7498/aps.52.1600
    [19] 张 强, 高 琳, 王 超, 袁 涛, 许 进. 具有时滞的一阶细胞神经网络动态行为研究. 物理学报, 2003, 52(7): 1606-1610. doi: 10.7498/aps.52.1606
    [20] 于丽娟, 朱长纯. 用人工神经网络预测场发射开启电场. 物理学报, 2000, 49(1): 170-173. doi: 10.7498/aps.49.170
计量
  • 文章访问数:  8210
  • PDF下载量:  117
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-02-22
  • 修回日期:  2019-04-30
  • 上网日期:  2019-07-01
  • 刊出日期:  2019-07-05

/

返回文章
返回