计算机科学 ›› 2018, Vol. 45 ›› Issue (10): 207-211.doi: 10.11896/j.issn.1002-137X.2018.10.038
孔颖1,2, 孙明轩1
KONG Ying1,2, SUN Ming-xuan1
摘要: 为了更好地提高收敛的速度和精度,提出一种终态神经网络(TNN)及其加速形式(ATNN)的求解方法。该网络求解方法具有终态吸引特性,能够在有限的时间内得到时变矩阵的有效解。相比于具有渐近收敛动态特性的神经网络,该神经网络方法具有有限时间收敛性,不仅能够改变收敛速度,而且能达到较高的收敛精度。将3种不同的神经网络方法用于求解时变Sylvester动态方程;同时,以终态神经网络求解二次优化问题,实现冗余机械臂Katana6M180有限时间收敛的重复运动规划任务。仿真结果验证了终态神经网络方法的有效性。
中图分类号:
[1]BARTELS R H,STEWART G W.Solution of the matrix equation AX+XB=C[J].Communications of the Acm,1972,15(9):820-826. [2]LIU E D,JIN Y W,ZHANG S Y.Adaptive observer for nonli- near combinatorial systems based on dynamic neural networks[J].Control and Decision,2004,19(7):8764-8768.(in Chinese) 刘恩东,井元伟,张嗣瀛.基于动态神经网络的非线性组合系统自适应观测器[J].控制与决策,2004,19(7):8764-8768. [3]ZHU R J,CAI T Y.The observer of nonlinear system based on dynamic neural networks[J].Information and Control,1998,27(6):421-425.(in Chinese) 朱瑞军,柴天佑.基于动态神经网络的非线性系统曾一棒观测器设计[J].信息与控制,1998,27(6):421-425. [4]YANG J Y,JIA Y M.Adaptive observer for a class of nonlinear uncertain systems based on dynamic recurrent neural networks[J].Control and Decision,2002,17(1):81-91.(in Chinese) 杨晋勇,贾英民.基于动态递归神经网络的一类非线性不确定系统的自适应观测器[J].控制与决策,2002,17(1):89-91.[5]BAI J,LU R.Finite-time stability analysis of discrete-time fuzzy hopfield neural network[J].Neurocomputing,2015,159(2):263-267. [6]CAO Y.Dynamic modeling and neural network adaptive control of a deployable manipulator system[J].Journal of Guidance Control & Dynamics,2015,29(1):192-195. [7]ZHANG Y,CHEN D C,GUO D S.On exponential convergence of nonlinear gradient dynamics system with application to square root finding [J].Nonlinear Dynamics,2015,79(2):983-1003. [8]LI S.Accelerating a recurrent neural netwok 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):189-205. [9]WANG J.Analysis and design of a recurrent neural networks for linear programming[J].IEEE Transactions on Circuits and Systems,1993,40(9):613-618. [10]WHITNEY D E.Resolved motion rate control of manipulators and human prostheses[J].IEEE Transactions on Man Machine Systems,1969,10(2):467-453. [11]POLVERINI M,ZANCHETTIN A.A computationally efficient safety assessment for collaborative robotics applications [J].Robotics and Computer-Integrated Manufacturing,2017,46:25-37. [12]CHEN F T,SUN Y Y.Resolving manipulator redundancy under inequality constraints [J].IEEE Transactions on Robotics Automation,1994,10(1):65-71. [13]JIN L,ZHANG Y N.Neural network-based discrete-time Z-type model of high accuracy in noisy environments for solving dynamicsystem of linear equations[J].Neural Computing & Applications,2018,29(11):1217-1232. [14]LI Z P,SHAO X Y,ZHANG D X,et al.Steering System Control Strategy Based on Overview of Automotive Electric Power[J].Journal of Chongqing Institute of Technology,2015,29(8):6-11.(in Chinese) 李志鹏,邵宪友,张东兴,等.基于BP神经网络的电控发动机故障诊断研究[J].重庆理工大学学报(自然科学),2015,29(8):6-11. |
[1] | 孙明轩,翁丁恩,张钰. 有限值终态递归神经网络计算 Time-variant Neurocomputing with Finite-value Terminal Recurrent Neural Networks 计算机科学, 2020, 47(1): 212-218. https://doi.org/10.11896/jsjkx.181001898 |
[2] | 孔颖, 孙明轩. 基于终态神经网络的冗余机械臂重复运动规划 Repeatable Motion Planning of Redundant Manipulators Based on Terminal Neural Networks 计算机科学, 2018, 45(12): 201-205. https://doi.org/10.11896/j.issn.1002-137X.2018.12.033 |
|