Abstract
The gradient descent momentum and adaptive learning rate TD-DBP algorithm can improve the training speed and stability of Elman network effectively. BP algorithm is the typical supervised learning algorithm, so neural network cannot be trained on-line by it. For this reason, a new algorithm (TD-DBP), which was composed of temporal difference (TD) method and dynamic BP algorithm (DBP), was proposed to overcome the restriction. TD-DBP algorithm can make Elman network train on-line incrementally. Using the collected real time data, the modified TD-DBP algorithm was able to realize direct multi-step predictions for vertical displacement of wave compensating platform.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chen, Y.: Experimental Study on a Heave Compensation System for Shipborne Helicopter Platform, pp. 90–104. South China University of Technology, Guangzhou (2007)
Wei, D., Ye, J., Chen, Y., Liang, Y.: Short time prediction for vertical displacement of wave compensating platform. Ship & Ocean Engineerin-G 06, 45–48 (2007)
Zhang, X., Peng, X., Zhaoxiren: Diagonal Recurrent Neural Network Algorithm for Extreme Short Prediction of Ship Motion. Journal Of System Simulation 05, 641–642 (2005)
Li, H., Guo, C., Li, X.: Time Series Prediction of Ship Rolling Based on Error Back Propagation Neural Network Humidity Measurement. Journal of Dalian Maritime University 02, 39–42 (2003)
Wang, H., Liu, W., Wang, H.: Short-term Prediction of Ship Motion Based on Neural Networks. Computer Simulation 05, 18–20 (2006)
Sutton, R.S.: Learning to Predict by the Methods of Temporal Difference. Machine Learning 03, 9–14 (1983)
Rumelhart, D.E.: Learning Representation by BP Errors. Nature 07, 149–154 (1986)
Han, W., Zhang, Y.: Estimation of DRE Grade by Improved alogrithm. System Engineering 09, 80–82 (2000)
Shen, Y.: On the Neural Network Theory and Its Application in Ship Motion Prediction, pp. 5–83. Harbin Engineering University, Harbin (2005)
Dong, C.: Matlab Neural Ntework and Application, pp. 1–76. National Defense Engineering Press, Beijing (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag GmbH Berlin Heidelberg
About this paper
Cite this paper
Zeng, Z. (2012). Multi-step Predictions Based on TD-DBP ELMAN Neural Network for Wave Compensating Platform. In: Jin, D., Lin, S. (eds) Advances in Computer Science and Information Engineering. Advances in Intelligent and Soft Computing, vol 169. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30223-7_67
Download citation
DOI: https://doi.org/10.1007/978-3-642-30223-7_67
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30222-0
Online ISBN: 978-3-642-30223-7
eBook Packages: EngineeringEngineering (R0)