Title :
Neural network prediction of the wave influence on the yaw motion of a ship
Author :
Nicolau, Viorel ; Aiordachioaie, Dorel ; Popa, Rustem
Author_Institution :
Dept. of Electron. & Telecommun., Dunarea de Jos Univ., Galati, Romania
Abstract :
Knowing the wave influence on the yaw motion of a ship, a more complex heading control law for autopilot system can be implemented. The time series prediction of the yaw angle´s measured values using neural networks has been investigated in this paper. Several neural networks are analyzed using different training data sets and noise conditions. The predictor is working well even if both the training and testing sets are affected by measurement noise.
Keywords :
motion control; neural nets; prediction theory; ships; time series; autopilot system; neural network prediction; ship; time series prediction; wave influence; yaw motion; Control systems; Electronic mail; Frequency; Function approximation; Marine vehicles; Motion control; Multi-layer neural network; Neural networks; Sea measurements; Telecommunication control;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1381100