A Novel Stable Locally Recurrent Neural Network with Pole Assignment Projection Approach
-
摘要: 针对局部全局前馈递归动态神经网络的稳定性问题提出了一种新的采用极点配置稳定方法的局部递归全局前馈(Locally recurrent global forward, LRGF)神经网络. 由于动态神经元的极点有存在于实轴上和一对共轭复数极点两种情况, 为了避免神经元无限脉冲响应滤波器(Infinite impulse response filter, IIR)的系数投影到稳定区域的复杂性, 构造的神经网络将动态神经元分成实数极点IIR和共轭复数极点IIR两部分, 通过函数权值的方法将这两部分加权输出.同时针对这种新的神经网络采用了梯度下降的学习算法. 通过仿真对本文提出的神经网络的可靠性和有效性进行验证,并分析这种新的神经网络在稳定投影计算上的复杂度.
-
关键词:
- 动态神经网络 /
- 局部递归全局前馈神经网络 /
- 极点配置 /
- 稳定性投影
Abstract: This paper derives a new stable locally recurrent global forward (LRGF) neural network with pole assignment projection approach. The pole in the hidden neurons of the LRGF neural network can be classified into two situations. One case is that the pole is on the real axis, and the other case is that the pole is a conjugate complex. We divide the dynamic hidden neuron into two parts according to the kind of the pole, so that it can avoid the complexity of the projective computation. A weight function is used to fuse the two parts. The learning method is based on the gradient decent approach, which has been modified to be fit for the proposed neural network. At last, the simulation is given to demonstrate the reliability and effectiveness of the new neural network, and the complexity of the projection computation is also be analyzed. -
[1] Boely N, Botez R M. New Approach for the identification and validation of a nonlinear F/A-18 model by use of neural networks. IEEE Transactions on Neural Networks, 2010, 21(11): 1759-1765[2] Han Bing, Han Min. Nonlinear time delay systems identification based on dynamic BP algorithm. Journal of Dalian University of Technology, 2010, 50(5): 777-781(韩冰, 韩敏. 基于动态BP算法的非线性滞后系统辨识. 大连理工大学学报, 2010, 50(5): 777-781)[3] Nascimento C F, Oliveria A A, Goedtel A, Silva I N, Serni P J A. Neural network-based approach for identification of the harmonic content of a nonlinear load in a single-phase system. IEEE Latin America Transactions, 2010, 8(1): 65-73[4] Zhao H Q, Zeng X P, He Z Y. Low-complexity nonlinear adaptive filter based on a pipelined bilinear recurrent neural network. IEEE Transactions on Neural Networks, 2011, 22(9): 1494-1507[5] Barbounis T G, Theocharis J B. A locally recurrent fuzzy neural network with application to the wind speed prediction using spatial correlation. Neurocomputing, 2006, 70(7-9): 1525-1542[6] Park D C. Prediction of MPEG video traffic over ATM networks using dynamic bilinear recurrent neural network. Applied Mathematics and Computation, 2008, 205(2): 648-657[7] Ferrari S. Multiobjective algebraic synthesis of neural control systems by implicit model following. IEEE Transactions on Neural Networks, 2009, 20(3): 406-419[8] Park J H, Kim S H, Moon C J. Adaptive neural control for strict-feedback nonlinear systems without backstepping. IEEE Transactions on Neural Networks, 2009, 20(7): 1204-1209[9] Hou Z G, Gupta M M, Nikiforuk P N, Tan M, Cheng L. A recurrent neural network for hierarchical control of interconnected dynamic systems. IEEE Transactions on Neural Networks, 2007, 18(2): 466-481[10] Talebi H A, Khorasani K, Tafazoli S. A recurrent neural-network-based sensor and actuator fault detection and isolation for nonlinear systems with application to the satellite's attitude control subsystem. IEEE Transactions on Neural Networks, 2009, 20(1): 45-60[11] Cho H C, Knowles J, Fadali M S, Lee K S. Fault detection and isolation of induction motors using recurrent neural networks and dynamic Bayesian modeling. IEEE Transactions on Control Systems Technology, 2010, 18(2): 430-437[12] Mousapha A I, Selmic R R. Wireless sensor network modeling using modified recurrent neural networks: application to fault detection. IEEE Transactions on Instrumentation and Measurement, 2008, 57(5): 981-988[13] Tsoi A C, Back A D. Locally recurrent globally feedforward networks: a critical review of architectures. IEEE Transactions on Neural Networks, 1994, 5(2): 229-239[14] Zeng H B, Xiao S P, Liu B. New stability criteria for recurrent neural networks with a time-varying delay. International Journal of Automation and Computing, 2011, 8(1): 128-133[15] Shao H Y. Delay-dependent stability for recurrent neural networks with time-varying delays. IEEE Transactions on Neural Networks, 2008, 19(9): 1647-1651[16] Wang L S, Zhang R, Zhang Z B, Xu Z B, Peng J G. Some characterizations of global exponential stability of a generic class of continuous-time recurrent neural networks. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2009, 39(3): 763-772[17] Jin L, Nikiforuk P N, Gupta M M. Absolute stability conditions for discrete-time recurrent neural networks. IEEE Transactions on Neural Networks, 1994, 5(6): 954-963[18] Patan K. Stability analysis and the stabilization of a class of discrete-time dynamic neural networks. IEEE Transactions on Neural Networks, 2007, 18(3): 660-673[19] Namikawa J, Tani J. A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance. Neural Networks, 2008, 21(10): 1466-1475[20] Rankovic V M, Nikolic I Z. Identification of nonlinear models with feed forward neural network and digital recurrent network. FME Transactions, 2008, 36(2): 87-92[21] Juang C F, Lin C C. A recurrent self-organizing neural fuzzy inference network. IEEE Transactions on Neural Networks, 1999, 10(4): 828-845[22] Patan K. Artificial Neural Networks for the Modelling and Fault Diagnosis of Technical Processes. Berlin: Springer, 2008. 78-112
点击查看大图
计量
- 文章访问数: 1905
- HTML全文浏览量: 40
- PDF下载量: 1307
- 被引次数: 0