基于非线性激活函数的零化神经网络及其在动态问题求解中的应用
Nonlinear Activation Function and Its Application on Solving Dynamic Problems Based on Zeroing Neural Network
查看参考文献26篇
|
文摘
|
零化神经网络(zeroing neural network, ZNN)因其具有快速的收敛速度和较为出色的抗外界噪声干扰的能力,自被提出以来就有大量研究且广泛地应用于时变问题的求解.然而,目前所存在的零化神经网络模型的收敛速度和抗干扰能力仍然不尽如人意.因此,为进一步提高零化神经网络的性能,文章提出了一种固定时间收敛激活函数(fixed-time convergent activation function, FTCAF),然后,基于该激活函数建立了固定时间收敛的零化神经网络(fixed-time convergent zeroing neural network, FTCZNN)模型,并应用该模型对动态Sylvester方程(dynamic Sylvester equation, DSE)进行求解.理论分析证明了FTCZNN模型拥有固定的时间收敛上界和较为出色的抗外界噪声干扰的能力.此外,DSE数值仿真实验也证明了FTCZNN模型的优越性能.最后,FTCZNN模型被用于机械臂的轨迹跟踪实验,且实验结果再次证明了FTCZNN模型相较于传统ZNN模型拥有快速的收敛速度和较为出色的抗干扰能力,因此其实际应用能力也得到了验证. |
|
其他语种文摘
|
Zeroing neural network (ZNN) has been widely used to solve time-varying problems since it was proposed because of its fast convergence speed and ability to resist external noise interference. However, the convergence speed and anti-interference ability of the existing zeroing neural network models are still not satisfactory. Therefore, to further improve the performance of ZNN, a new fixed-time convergent activation function (FTCAF) is designed in this paper. Then, a fixed-time convergent zeroing neural network (FTCZNN) model is established based on the proposed activation function and this model is applied to solve dynamic Sylvester equation (DSE). Theoretical analysis proves that the FTCZNN model has a fixed time convergence upper limit and strong anti-interference ability. In addition, numerical simulation results also demonstrate the superior performance of the FTCZNN model. Finally, FTCZNN model is used to realize the trajectory tracking experiment of the robot manipulator. The experimental results once again prove that the FTCZNN model has fast convergence speed and strong anti-interference ability, and its practical application ability is also verified. |
|
来源
|
系统科学与数学
,2024,44(7):1870-1884 【核心库】
|
|
DOI
|
10.12341/jssms23172
|
|
关键词
|
零化神经网络
;
激活函数
;
动态Sylvester方程
;
机械臂轨迹跟踪
|
|
地址
|
1.
湖南电气职业技术学院风能工程学院, 湘潭, 411101
2.
湖南科技大学信息与电气工程学院, 湘潭, 411201
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1000-0577 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
湖南省自然科学基金
;
湖南省教育厅项目
|
|
文献收藏号
|
CSCD:7757620
|
参考文献 共
26
共2页
|
|
1.
Qi Y. Discrete computational neural dynamics models for solving time-dependent Sylvester equations with applications to robotics and MIMO systems.
IEEE Trans. Ind. Inf,2020,16(10):6231-6241
|
CSCD被引
5
次
|
|
|
|
|
2.
Shaker H R. Control configuration selection for bilinear systems via generalized Hankel interaction index array.
Int. J. Control,2015,88(1):30-37
|
CSCD被引
2
次
|
|
|
|
|
3.
Yan X. New zeroing neural network models for solving nonstationary Sylvester equation with verifications on mobile manipulators.
IEEE Trans. Ind. Inf,2019,15(9):5011-5022
|
CSCD被引
2
次
|
|
|
|
|
4.
Beik F P A. On the Krylov subspace methods based on tensor format for positive definite Sylvester tensor equations.
Numer. Linear Algebr. Appl,2016,23(3):444-466
|
CSCD被引
2
次
|
|
|
|
|
5.
Li S. A global variant of the COCR method for the complex symmetric Sylvester matrix equation AX + XB = C.
Comput. Math. Appl,2021,94:104-113
|
CSCD被引
1
次
|
|
|
|
|
6.
Zhang Z. Simulink comparison of varying parameter convergent-differential neuralnetwork and gradient neural network for solving online linear time-varying equations.
2016 12th World Congress on Intelligent Control and Automation (WCICA),2016:887-894
|
CSCD被引
1
次
|
|
|
|
|
7.
Zhang Y. On exponential convergence of nonlinear gradient dynamics system with application to square root finding.
Nonlinear Dyn,2015,79(2):983-1003
|
CSCD被引
2
次
|
|
|
|
|
8.
Jin J. A nonlinear zeroing neural network and its applications on time-varying linear matrix equations solving, electronic circuit currents computing and robotic manipulator trajectory tracking.
Comput. Appl. Math,2022,41:319
|
CSCD被引
1
次
|
|
|
|
|
9.
Xiao L. A parameter-changing and complex-valued zeroing neural-network for finding solution of time-varying complex linear matrix equations in finite time.
IEEE Trans. Ind. Inf,2021,17(10):6634-6643
|
CSCD被引
2
次
|
|
|
|
|
10.
Zhang Z. Varying-parameter convergent differential neural solution to time-varying overdetermined system of linear equations.
IEEE Trans. Autom. Control,2020,65:874-881
|
CSCD被引
2
次
|
|
|
|
|
11.
Jin J. A robust predefined-time convergence zeroing neural network for dynamic matrix inversion.
IEEE Trans. Cybern,2022
|
CSCD被引
1
次
|
|
|
|
|
12.
Xiao L. New error function designs for finite-time ZNN models with application to dynamic matrix inversion.
Neurocomputing,2020,402:395-408
|
CSCD被引
2
次
|
|
|
|
|
13.
Xiao L. Zeroing neural networks for dynamic quaternion-valued matrix inversion.
IEEE Trans. Ind. Inf,2022,18(3):1562-1571
|
CSCD被引
1
次
|
|
|
|
|
14.
Jiang Y. Composite learning-based adaptive neural control for dual-arm robots with relative motion.
IEEE Trans. Neural Netw. Learn. Syst,2022,33(3):1010-1021
|
CSCD被引
1
次
|
|
|
|
|
15.
Huang S. New discrete-time zeroing neural network for solving time-variant underdetermined nonlinear systems under bound constraint.
Neurocomputing,2022,487:214-227
|
CSCD被引
1
次
|
|
|
|
|
16.
Tan N. A New Noise-Tolerant Dual-Neural-Network Scheme for Robust Kinematic Control of Robotic Arms With Unknown Models.
IEEE/CAA J. Autom. Sinica,2022,9(10):1778-1791
|
CSCD被引
2
次
|
|
|
|
|
17.
Zhao L. Robust zeroing neural network for fixed-time kinematic control of wheeled mobile robot in noise-polluted environment.
Mathe. Comput. Simula,2021,185:289-307
|
CSCD被引
1
次
|
|
|
|
|
18.
Yang Y. Superior robustness of power-sum activation functions in zhang neural networks for time-varying quadratic programs perturbed with large implementation errors.
Neural Comput. Appl,2013,22:175-185
|
CSCD被引
1
次
|
|
|
|
|
19.
Li S. Accelerating a recurrent neural network to finite-time convergence for solving time-varying Sylvester equation by using a sign-bi-power activation function.
Neural Process. Lett,2013,37(2):189-205
|
CSCD被引
6
次
|
|
|
|
|
20.
Zhang Z. A new varying-parameter recurrent neural-network for online solution of time-varying Sylvester equation.
IEEE Trans. Cybern,2017,48(11):3135-3148
|
CSCD被引
5
次
|
|
|
|
|
了解气象卫星更多信息，请访问