The Method Research of Grey Neural Network Control Based on Data

Abstract:

A control process based on data often contains large amounts of sample data. The accuracy of system is always influenced by the randomness of the initial data when the RBF neural network is used to predict model. However, the grey accumulated generating operation (AGO) can reduce the effect of randomness of the initial data, which is able to make data more regular. Based on the two points above, a new kind of method is proposed, which is called grey RBF neural network. This method not only can reduce the randomness, speed up the network convergence, but also improve the modeling accuracy. The grey RBF neural network can be proved to be feasible and effective by applying the grey RBF neural network to the synthetic ammonia decarburization process, and comparing the simulation results with the results which was only using RBF network.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 1131-1134
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.1131
• Online since: August 2014
• Authors: Yong Wei Li*, Zhi Gang Ye, Chao Chao Huo
• Keywords: Grey Accumulated Generating Operation, RBF Neural Network, Synthetic Ammonia Decarburization

References

[1] Shuhai Fan. The combination of grey system and BP neural network [J]. Macaronis and Automation, 2009 (8) 1267 – 1271.

[2] Meiqin Liu, Yi Shen, Xiao Liao. Application of a kind of RBF neural network in modeling of nonlinear systems [J]. Control and decision, 2011 (3) 277-281.

[3] Yurun Zhang. National distributed control system for carbonification process of process of soda asks manufacturing [J]. Control and instruments in chemical industry, 1997 (5) 48-51.

[4] Yanjun Li, Tiejun Wu, Mingwang Zhao. A Novel Nonlinear Dynamic System Modeling Approach Using Radial Basis Function Neural Networks [J]. Systems engineering theory & practice, 2010 (3) 64-69.

[5] Moody J, Darken C J. Learning with localized receptive fields. Proceedings Connectionist Models [M]. Mellon University. Morgan Kaufmann Publishers, 2008 133- 143.

[6] Shuhai Wang, Haichao Ran. The process control system based on the DCS for the synthetic ammonia decarburization [J]. Chinese Journal of scientific instrument, 2002 (23) 353-356.

[7] Tianbang Guo. Grey system theory and its application [M]. Beijing: Science Press, 2010 11-40.

[8] Furen Zhang. The application of the Synchronous improved grey-neural network model in predicting of oil-gas pipeline corrosion rate [J]. Natural Computation, 2010 (6) 1153-1156.

DOI: 10.1109/icnc.2010.5583668

[4] 郭天榜, 刘思锋, 等. 灰色系统理论及其应用[M]. 北京: 科学出版社, 2010: 11-40.

DOI: 10.7498/aps.46.1457

[5] Furen Zhang, Sun Jie. The application of synchronous improved gery neural network model in predicting of oil-gas pipeline corrosion rateNatural Computation, 2010(6): 1153-1156.

DOI: 10.1109/icnc.2010.5583668

[6] 何庆飞，陈桂明，陈小虎等. 基于灰色支持向量机的液压泵寿命预测方法. 系统工程理论与实践，2012（4）：73-76.

DOI: 10.26549/jxffcxysj.v2i3.1825

[9] Qingfei He, Xiaohu Chen et al. Hydraulic pump life gray prediction method based on support vector machine [J]. System engineering theory & practice, 2012 (4) 73-76.

[7] Qiongqin Jiang, Youfu Du. Shot-term Traffic Prediction Model Based on Grey Neural Network. 2009(8): 484-487.

[10] Wang Le , Li Qiu-wen, Wang Ke. The Short-Term Load Forecasting Based on Grey Theory and RBF Neural Network [J]. Power and Energy Engineering Conference, 2011 (4) 17-34.

DOI: 10.1109/appeec.2011.5748765