Short-term ship attitude prediction method based on empirical mode decomposition and support vector regression

Abstract

The invention discloses a short-term ship attitude prediction method based on empirical mode decomposition and support vector regression. The method comprises the steps that 1, when guidance instruction calculation is conducted for the first time, a convex optimization planning method is applied to conduct guidance instruction calculation, and a calculation result is stored; 2, after first onlinetrajectory planning is completed, in the same planning period, an online trajectory planning method based on convex optimization and a polynomial guidance method are applied in parallel, and guidanceinstructions uCVX and uIGM are obtained respectively; 3, when uCVX-uIGM is smaller than delta and the polynomial guidance planning precision meets the requirement, a polynomial guidance method is switched for guidance calculation, and otherwise, a guidance instruction calculated by a planning method based on convex optimization is adopted for flight; and 4, after switching to the polynomial guidance calculation guidance instruction, guidance instruction and the shutdown time are directly calculated by applying the polynomial guidance until landing. Through empirical mode decomposition and a support vector regression algorithm, the method can be effectively suitable for ship attitude prediction of marine navigation.

Description

technical field [0001] The invention belongs to the technical field of ships; in particular, it relates to a short-term ship attitude prediction method based on empirical mode decomposition and support vector regression. Background technique [0002] When a ship performs some special sea operations, such as the landing operation of an aircraft carrier, the deck of the ship is required to have good stability. However, when a ship is sailing at sea, due to the influence of some external environmental factors, such as sea wind and waves, it will inevitably produce six-degree-of-freedom swaying motion. This swaying motion will cause deck displacement and seriously interfere with the ship's offshore operations. , especially when encountering harsh sea conditions, it will pose a great safety hazard to the ship's offshore operations. If it is possible to predict the movement and posture of the ship in a short period of time in the future, it will be of great significance to improv...

AI Technical Summary

Problems solved by technology

Empirical Mode Decomposition (EMD) has strong versatility for dealing with non-stationary data. This method can reflect the physical characteristics of the original time series signal without pre-setting the basis function. However, due to the boundary effect of EMD, Using it directly in the prediction model will lead to larger prediction errors. For this reason, the present invention adopts the method of support vector regression and mirror symmetry combination to improve the boundary effect of EMD

Images