Generalized Predictive Control of Neural Network Based on LM Optimization

Article Preview

Abstract:

Starting from the establishment of generalized predictive model based on neural network, LM optimization algorithm is applied to the perdictive control model for study in order to solve these problems that the training speed of the BP network is slow and it is easy to trap into the local minimum.Generalized predictive control and neural network which has the capability of approaching any nonlinear function are combined to forecast the future outputs of the system.LM algorithm is used instead of gradient descent method to optimize controller parameters and it makes full use of Jacobian matrix information identified by neural network.The result of Matlab simulation indicates that the neural network using LM algorithm has the feature of fast convergence rate,model of high precision and good robustness,which is more suitable for real-time nonlinear control.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

2164-2169

Citation:

Online since:

July 2011

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2011 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Pan Li-deng. Advanced Control Technology and Application to online optimization[M]. Bei Jing: Mechanical Industry Press, 2009: 173-178.

Google Scholar

[2] S.J. Zhao Y.M. Xu. Levenberg-Marquardt Algorithm for Nonlinear Principal Component Analy- sis Neural Network through Inputs Training[C]. Intelligent Control and Automation, Fifth World Congress, 2004: 3278-3281.

DOI: 10.1109/wcica.2004.1343139

Google Scholar

[3] Zhang Yan, Wang Fan-zhen, Chen Zeng-qiang, etc. Recurrent Neural Networks-based Multiva- riable System Predictive Control[J]. Nan Kai Univercity, 2006, 39(1): 49-53.

Google Scholar

[4] Wang Wei. Generalized Predictive Control Theory and Application[M]. Bei Jing: Science Press, 1998: 150-151.

Google Scholar

[5] Zhen De-zhong, He Qun. A Kind of Adaptive Recursive Optimization Control Algorithm of Weighted Generalized Predictive Control[J]. Electronics, 2005, 33(8): 1442-1445.

Google Scholar

[6] Zhao Hong, Zhou Rui-xiang, Lin Ting-yin. Neural Network Supervisory Control Based on LM Algorithm[J]. Xi'an Jiaotong University, 2002, 36(5): 523-527.

Google Scholar