[1]毛华倩,孔颖.面向时变复数的模糊归零神经网络算法[J].浙江科技学院学报,2024,(01):49-58.[doi:10.3969/j.issn.1671-8798.2024.01.006 ]
 MAO Huaqian,KONG Ying.On fuzzy zeroing neural network algorithm for computing time-varying complex numbers[J].,2024,(01):49-58.[doi:10.3969/j.issn.1671-8798.2024.01.006 ]
点击复制

面向时变复数的模糊归零神经网络算法(/HTML)
分享到:

《浙江科技学院学报》[ISSN:1001-3733/CN:61-1062/R]

卷:
期数:
2024年01期
页码:
49-58
栏目:
出版日期:
2024-02-29

文章信息/Info

Title:
On fuzzy zeroing neural network algorithm for computing time-varying complex numbers
文章编号:
1671-8798(2024)01-0049-10
作者:
毛华倩孔颖
(浙江科技大学 信息与电子工程学院,杭州 310023)
Author(s):
MAO Huaqian KONG Ying
(School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, Zhejiang, China)
关键词:
复数归零神经网络 模糊逻辑系统 有限时间收敛 激活函数
分类号:
TP183
DOI:
10.3969/j.issn.1671-8798.2024.01.006
文献标志码:
A
摘要:
【目的】为了求解时变复数西尔维斯特方程(Sylvester equation),提出两种全新的复值模糊归零神经网络(fuzzy logic system for zeroing neural network,FLSVZNN)模型。【方法】首先,在两种复数归零神经网络(complex-valued zeroing neural network,CVZNN)模型的基础上,引入模糊逻辑系统(fuzzy logic system,FLS)来控制信号的处理,从而提出两种FLSVZNN模型; 然后,利用李亚普诺夫定理(Lyapunov's theorem)来分析模型的稳定性和收敛速度; 最后,通过仿真试验来进一步验证FLSVZNN的优越性能。【结果】在求解时变复数西尔维斯特方程时,相比传统的神经网络模型,使用改进的符号双幂(sign-bi-power,SBP)函数来激活的FLSVZNN模型具有更好的收敛性和稳定性,可使误差函数在0.3 s左右收敛至0。【结论】本研究提出的两种FLSVZNN模型能快速求解时变复数西尔维斯特方程,这可为神经网络模型的建立及工程应用提供参考。

参考文献/References:

[1] XIAO L, LIAO B, LI S, et al. Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations[J]. Neural Networks,2018,98:102.
[2] XIAO L, ZHANG Z, ZHANG Z, et al. Design, verification and robotic application of a novel recurrent neural network for computing dynamic Sylvester equation[J]. Neural Networks,2018,105:185.
[3] DAHIPHALE V, BANSOD G, ZAMBARE A, et al. Design and implementation of various datapath architectures for the ANU lightweight cipher on an FPGA[J]. Frontiers of Information Technology and Electronic Engineering,2020,21(4):615.
[4] SHEN Y, MIAO P, HUANG Y, et al. Finite-time stability and its application for solving time-varying Sylvester equation by recurrent neural network[J]. Neural Processing Letters,2015,42(3):767.
[5] WANG J. Recurrent neural networks for computing pseudoinverses of rank-deficient matrices[J]. SIAM Journal on Scientific Computing,1997,18(5):1479.
[6] WANG X, CHE M, WEI Y. Recurrent neural network for computation of generalized eigenvalue problem with real diagonalizablematrix pair and its applications[J]. Neurocomputing,2016,216:230.
[7] ZHANG Z, KONG L, ZHENG L, et al. Robustness analysis of a power-type varying-parameter recurrent neural network for solving time-varying QM and QP problems and applications[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems,2020,50(12):5106.
[8] LI W, MA X, LUO J, et al. A strictly predefined-time convergent neural solution to equality- and inequality-constrained time-variant quadratic programming[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems,2021,51(7):4028.
[9] YU F, LIU L, XIAO L, et al. A robust and fixed-time zeroing neural dynamics for computing time-variant nonlinear equation using a novel nonlinear activation function[J]. Neurocomputing,2019,350:108.
[10] PANDE A, GOEL V. Complex-valued neural network in image recognition:a study on the effectiveness of radial basis function[J].World Academy of Science,Engineering and Technolog,2007,26:220.
[11] ZHANG Y, ZHAN L, LI K. Complex-valued Zhang neural network for online complex-valued time-varying matrix inversion[J]. Applied Mathematics & Computation,2011,217(24):10066.
[12] 孔颖,孙明轩.Sylvester时变矩阵方程求解的终态神经网络算法[J].计算机科学,2018,45(10):6.
[13] LI S, CHEN S, LIU B. Accelerating a recurrent neural network to finite-time convergence for solving time-varying Sylvester equation by using a sign-bi-power activation function[J]. Neural Processing Letters,2013,37(2):189.
[14] 高畅,孔颖,胡汤珑.基于有限时间神经网络求解的时变复数矩阵方程[J].浙江科技学院学报,2022,34(5):409.
[15] 石辛民,郝整清.模糊控制及其MATLAB仿真[M].北京:清华大学出版社,2008.
[16] 孟廷豪.基于模糊控制的机器人避障研究[D].太原:中北大学,2013.
[17] ZHANG Z, YAN Z. An adaptive fuzzy recurrent neural network for solving the nonrepetitive motion problem of redundant robot manipulators[J]. IEEE Transactions on Fuzzy Systems,2020,28(4):684.

备注/Memo

备注/Memo:
收稿日期:2023-04-23
基金项目:浙江省自然科学基金项目(LZY22E050002)
通信作者:孔 颖(1980— ),女,浙江省杭州人,教授,博士,主要从事神经网络与机械臂轨迹规划研究。Email:kongying-888@163.com。
更新日期/Last Update: 2024-02-29