Multi-step Predictions for Vertical Displacement of Wave Compensating Platform Based on ELMAN Neural Network
Circuits, Communications and Systems, Pacific-Asia Conference on (2009)
May 16, 2009 to May 17, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/PACCS.2009.7
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. The gradient descent momentum and adaptive learning rate TD-DBP algorithm can improve the training speed and stability of Elman network effectively. 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.
Elman neural network; TD-DBP method; wave motion compensation; prediction
Y. Jiawei and Z. Zhigang, "Multi-step Predictions for Vertical Displacement of Wave Compensating Platform Based on ELMAN Neural Network," 2009 Pacific-Asia Conference on Circuits, Communications and Systems (PACCS 2009)(PACCS), Chengdu, 2009, pp. 555-558.