谭营, 何振亚. 一种神经网络参数扰动算法及其在机械手控制中的应用[J]. 机器人, 1997, 19(6): 438-443..
TAN Ying, HE Zhenya. A PARAMETER DISTURBING ALGORITHM FOR NEURAL NETWORKS AND ITS APPLICATION TO MANIPULATOR CONTROL. ROBOT, 1997, 19(6): 438-443..
Abstract：In this paper, a parameter disturbing algorithm of neural networks which can overcome the local minima problem of Hopfield network is proposed on the basis of considering the gradient convergence of Hopfield network and the principle of stochastic simulated annealing developed by Kirpatrick. It is of similar characteristics of stochastic annealing with typical SA algorithm, whose performance is analysed in terms of digital simulations in detail. Finally, the proposed algorithm is successfully applied to the inverse kinematics problem of manipulator control, and then a neural network solver for the problem is established. It has been shown by digital simulations that the proposed neural network control method not only has fast control speed but also raises the control accuracy of manipulator.
1 Wampler C W.Manipulat or Inverse Kinematics Solutions Based on Vector Formulations and Damped Least-square Methods.IEEE Trans Syst Man Cybern,1986,SMC-16 2 Mayorga R V,Wong A K,Milano N.A Fast Procedure for Manipul ator Inverse Kinematics Evalution and Pseudoin verse Robustness.IEEE Trans Syst Man Cybern,1992,SMC-22(4):790～798 3 Hopfield J J,Tank D M.Neural Computation of Decisions in Optimization.Biological Cybernetics,1985,52:141～152 4 Kirpatri ck S,Gelatt C D,Vecchi M P.Optimization by Simulated An nealing.Science,1983,220(4598):671～680 5 Rutenbar R A.Simulated A nnealing Algorithms:An Over view.IEEE Circuit Devices Mag,1989,5(1):19～26 6 A be S.Global Convergence and Suppression of Spurious States of the Hop field Neural Net works.IEEE Trans Circuit and SystemI,1993,40:246～257 7 Tan Y,Deng C,He Z Y.A Chaotic Annealing Neural Network and Its Application to Direction Estimation of Spatial Signal Sources.Neural Networks for Signal Processing VII—Proceedings of the 1997 IEEE Work shop,Florida,USA,1997:56～65
