基于自适应模拟退火的变频正弦混沌神经网络

doi:10.3969/j.issn.0372-2112.2019.03.014

摘要
图/表
参考文献(0)
相关文章 (5)

全文: PDF (1860 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对变频正弦混沌神经网络寻优精度与收敛速度无法兼顾的问题，通过分析暂态混沌神经网络的优化机制和现有的退火策略，提出了一种基于自适应模拟退火策略的变频正弦混沌神经网络模型.该模型可以根据混沌神经元的Lyapunov指数来确定合适的自反馈连接权值.给出了混沌神经元的倒分岔图、Lyapunov指数及不同退火函数的时间演化图，证明了自适应模拟退火策略能够自主选择合适的退火速度，更有效的利用混沌全局搜索能力，并加快非混沌态的演化时间.为了证明该模型的有效性，将其应用于函数优化和组合优化问题中.仿真实验表明：（1）对于该模型退火速度的选择，自适应模拟退火策略比现有的几种退火方法更具有灵活性和适应性；（2）该模型在寻优精度和速度上比暂态混沌神经网络及其他改进模型具有更好的兼顾性.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	胡志强
	李文静
	乔俊飞

关键词 ：变频正弦混沌神经网络, Lyapunov指数, 自适应模拟退火, 优化计算

Abstract：The frequency conversion sinusoidal chaotic neural network (FCSCNN) cannot consider search accuracy and convergence speed simultaneously.In order to solve the mentioned problem,a novel self-adaptive simulated annealing (SSA) strategy is proposed by analyzing the optimization mechanism of the transiently chaotic neural network (TCNN) and the existing annealing strategy.It can give appropriate self-feedback connection weights based on the characteristics of Lyapunov exponent.The reversed bifurcation,Lyapunov exponent and annealing function evolution diagram of the chaotic neuron are given and the dynamic characteristic is analyzed.It shows that the SSA strategy can choose appropriate annealing speed in different stages,which can not only make full use of chaotic global searching ability but also accelerate convergence speed.Based on the neuron model,a novel FCSCNN with SSA strategy (FCSCNN-SSA) is proposed and applied to nonlinear function optimization and combinational optimization problems.The simulation results show that:(1) The SSA strategy can targeted choose the appropriate annealing speed,which is superior to other several existing simulated annealing methods for pertinence and adaptability and can be expanded to other similar models with same optimization mechanism; (2)FCSCNN-SSA can converge with a fast speed and search accuracy simultaneously than TCNN,TCNN-SEA,I-TCNN,NCNN,BFS-TCNN,FCSCNN.

Key words： frequency conversion sinusoidal chaotic neural network Lyapunov exponent self-adaptive simulated annealing optimal computation

收稿日期: 2017-08-28

ZTFLH:

TP183

基金资助:国家自然科学基金重点项目（No.61533002）；国家自然科学基金青年科学基金（No.61603009）；北京市科技专项课题领军人才（No.Z1511000001315010）；北京工业大学日新人才计划（No.2017-RX（1）-04）

作者简介: 胡志强 男,1988年7月出生,山东省泰安人,2013年毕业于桂林电子科技大学获硕士学位,现为北京工业大学信息学部博士研究生.主要研究方向为混沌动力学、混沌神经网络、污水处理建模与仿真、智能优化算法等.E-mail:zacharyhu33@163.com;李文静 女,1985年出生,陕西西安人,2013年7月毕业于中国科学院自动化研究所获工学博士学位,现为北京工业大学副教授,硕士生导师.主要研究方向为神经计算,人工神经网络,模式识别、神经科学.E-mail:wenjing.li@bjut.edu.cn;乔俊飞 男,1968年出生,内蒙古鄂尔多斯人.1998年于东北大学获博士学位,现为北京工业大学教授,博士生导师,主要研究方向为智能控制理论及应用,神经网络分析与设计等.E-mail:junfeiq@bjut.edu.cn

引用本文:

胡志强, 李文静, 乔俊飞. 基于自适应模拟退火的变频正弦混沌神经网络[J]. 电子学报, 2019, 47(3): 613-622. HU Zhi-qiang, LI Wen-jing, QIAO Jun-fei. Frequency Conversion Sinusoidal Chaotic Neural Network Based on Self-adaptive Simulated Annealing. Acta Electronica Sinica, 2019, 47(3): 613-622.

链接本文:

http://www.ejournal.org.cn/CN/10.3969/j.issn.0372-2112.2019.03.014 或 http://www.ejournal.org.cn/CN/Y2019/V47/I3/613

[1] 胡志强,李文静,乔俊飞.变频正弦混沌神经网络及其应用[J].物理学报,2017,66(9):12-22.HU Zhi-qiang,LI Wen-jing,QIAO Jun-fei.Frequency conversion sinusoidal chaotic neural network and its application[J].Acta Physica Sinica,2017,66(9):12-22.(in Chinese)
[2] LIU W,WANG L.Minimizing interference in satellite communications using transiently chaotic neural networks[J].Computers & Mathematics with Applications,2009,57(6):1024-1029.
[3] 高军峰,司慧芳,余彬,等.基于脑电样本熵的测谎分析[J].电子学报,2017,45(8):1836-1841.GAO Jun-fei,SI Hui-fang,YU Bin,et al.Lie detection anlysis based on the sample entropy of EEG[J].Acta Electrica Sinica,2017,45(8):1836-1841.(in Chinese)
[4] 王登,苗夺谦,王睿智.一种新的基于小波包分解的EEG特征抽取与识别方法研究[J].电子学报,2013,41(1):193-198.WANG Deng,MIAO Duo-qian,WANG Rui-zhi.A new method of EEG classification with feature extraction based on wavelet packet decomposi-tion[J].Acta Electronica Sinica,2013,41(1):193-198.(in Chinese)
[5] ZHANG Q,XIE X,ZHU P,et al.Sinusoidal modulation control method in a chaotic neural network[J].Communications in Nonlinear Science & Numerical Simulation,2014,19(8):2793-2800.
[6] 张旭东,朱萍,谢小平,何国光.混沌神经网络的动态阈值控制[J].物理学报,2013,62(21):71-77.ZHANG Xu-dong,ZHU Ping,XIE Xiao-ping,HE Guo-guang.A dynamic threshold value control method for chaotic neural networks[J].Acta Physica Sinica,2013,62(21):71-77.(in Chinese)
[7] GARCIA L,TALAVAN P M,YANEZ J.Improving the Hopfield model performance when applied to the traveling salesman problem[J].Soft Computing,2017,21(14):3891-3905.
[8] MIRZAEI A,SAFABAKHSH R.Optimal matching by the transiently chaotic neural network[J].Applied Soft Computing,2009,9(3):863-873.
[9] 任海鹏,陈玲娟,韩崇昭.双混沌神经网络及其在优化问题中的应用[J].系统工程与电子技术,2009,31(6):1366-1371.REN Hai-peng,CHEN Ling-juan,HAN Chong-zhao.Neural network with double chaotic mechanism and its application in optimization[J].Systems Engineering and Electronics,2009,31(6):1366-1371.(in Chinese)
[10] 叶永刚,徐耀群.SLF混沌神经网络及其应用[J].计算机工程与应用,2015,51(21):74-79.YE Yong-gang,XU Yao-qun.SLF chaotic neural network model and its application[J].Computer Engineering and Applications,2015,51(21):74-79.(in Chinese)
[11] 于舒娟,宦如松,张昀,冯迪.基于混沌神经网络的盲检测改进新算法[J].物理学报,2014,63(6):117-123.Yu Shu-Juan,Huan Ru-Song,Zhang Yun,Feng Di.Novel improved blind detection algorithms based on chaotic neural networks[J].Acta Physica Sinica,2014,63(6):117-123.(in Chinese)
[12] XU N,LIU L J,XU Y Q.A novel chaotic neural network with radial basis function and their application to TSP[J].Applied Mechanics & Materials,2012,151:532-536.
[13] 王凌,郑大钟.一种基于退火策略的混沌神经网络优化算法[J].控制理论与应用,2000,17(1):139-142.WANG Ling,ZHANG Da-zhong.A kind of chaotic neural network optimization algorithm based on annealing strategy[J].Control Theory and Applications,2000,17(1):139-142.(in Chinese)
[14] FENG Y C,CAI X.Simulated annealing schemes in transiently chaotic neural network model[J].International Journal of Modern Physics B,2004,18(17n19):2579-2584.
[15] LI Y,ZONG H,MENG D,et al.Adaptive IA-TCNN multiuser detector based on simulated annealing of optimization[J].Energy Procedia,2012,17(17):588-594.
[16] XU X,TANG Z,WANG J.A method to improve the transiently chaotic neural network[J].Neurocomputing,2005,67:456-463.
[17] 修春波,刘向东,张宇河,等.一种新的混沌神经网络及其应用[J].电子学报,2005,33(5):868-870.XIU Chun-bo,LIU Xiang-dong,ZHANG Yu-he,TANG Yun-yu.A novel chaotic neural network and its application[J].Acta Electronica Sinica,2005,33(5):868-870.(in Chinese)
[18] 杨爱波,王基,刘树勇,等.基于空间栅格法的最大Lyapunov指数算法研究[J].电子学报,2012,40(9):1871-1875.YANG Ai-bo,WANG Ji,LIU Shu-yong,et al.An algorithm for computing the largest Lyapunov exponent based on space grid method[J].Acta Electronica Sinica,2012,40(9):1871-1875.(in Chinese)
[19] YANG G,YI J.Delayed chaotic neural network with annealing controlling for maximum clique problem[J].Neurocomputing,2014,127(3):114-123.
[20] KWOK T,SMITH K A.Experimental analysis of chaotic neural network models for combinatorial optimization under a unifying framework[J].Neural Networks,2000,13(7):731-744.
[21] LIU X,XIU C.A novel hysteretic chaotic neural network and its applications[J].Neurocomputing,2007,70(13):2561-2565.
[22] ZHAO L,SUN M,CHENG J H,et al.A novel chaotic neural network with the ability to characterize local features and its application[J].IEEE transactions on neural networks,2009,20(4):735-742.
[23] ZHAO Y,JI H,CHEN Z.Noisy chaotic neural network for resource allocation in high-speed train OFDMA system[J].Transactions of Tianjin University,2014,20(5):368-374.
[24] YE Y.Bessel function self-Feedback chaotic neural network model and applications[J].International Journal of Hybrid Information Technology,2014,7(4):19-28.