The application of modeling and prediction with MRA wavelet network

Abstract

As there are lots of non-linear systems in the real engineering, it is very important to do more researches on the modeling and prediction of non-linear systems. Based on the multi-resolution analysis (MRA) of wavelet theory, this paper combined the wavelet theory with neural network and established a MRA wavelet network with the scaling function and wavelet function as its neurons. From the analysis in the frequency domain, the results indicated that MRA wavelet network was better than other wavelet networks in the ability of approaching to the signals. An essential research was carried out on modeling and prediction with MRA wavelet network in the non-linear system. Using the lengthwise sway data received from the experiment of ship model, a model of offline prediction was established and was applied to the short-time prediction of ship motion. The simulation results indicated that the forecasting model improved the prediction precision effectively, lengthened the forecasting time and had a better prediction results than that of AR linear model. The research indicates that it is feasible to use the MRA wavelet network in the short-time prediction of ship motion.

Keywords

MAR wavelet network / non-linear system / short-time prediction / watercraft motion / AR model

References

[1] Bakshi R B, Stephanopoulos G. Wave-net: a mutiresolusion, hierarchical neuralnetwork with localized learning [J]. AIchE Journal, 1993, 3(1): 57-81

[2] Packard N, Crutchield J, Farmer D, et al. Geometry from a time serise [J]. Physical Review Letters, 1980, 45: 712-715

[3] Yao Hongxing, Sheng Zhaohan. Application of the wavelet neural network in the prediction of stock market [J]. Journal of Industrial Engineering and Engineering Management, 2002, 16(2): 32-37 (in Chinese)

[4] Peng Xueyan, Zhao Xiren, Lu shuping, et al. Prediction of big ship motion with wave survey[J]. Journal of System Simulation, 2002, 14(6): 809-814 (in Chinese)

[5] TAEKSOO S, INGOO H. Optimal signal multi-resolution by genetic algorithms to support artificial neural network for exchangerate forecasting. Expert System with Application, 2000 (18):257–269.

[6] Zhao Xiren. Application of Stochastic Processes[M]. 2003, Harbin: Publishing House of Harbin Engineering University, (in Chinese)

[7] Pati Y C, Krishnaprasad P S. Analysis and synthesis of feed forward neural network using discrete affine wavelet trans- formations. IEEE Trams on Neural Network, 1993, 4(1): 73-85