8
An Improved Autoregressive Method with Kalman Filtering Theory for Vessel Motion Predication
Authors: Zhang Lin, Qiang Yang, Zhiqun Guo, Jun Li
Number of views: 961
It is significant and valuable to improve the time and the accuracy of ships’ motion predication. Autoregressive
time series analysis method (AR) with Kalman filtering theory is the mainstream currently and the effectiveness
for the prediction of ships’ motion attitudes have been fully validated. However, the algorithm fixes the order,
i.e. the length of the state vector once only, but forecasts the future data for multi-step, resulting in degradation of the
step length and the accuracy, especially when the ship sails in bad sea condition. In order to solve this issue, this paper
proposed a new autoregressive-multiple (ARm) method, which can determine the orders and the parameters of model
in real-time. The method was applied to forecast a ship’s motion attitudes in eight different situations. The simulative
results of autoregressive-multiple method show the validity and veracity compared with real value.