Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Ship motion forecasting method based on improved EMD-AR model

A technology of ship motion and model, which is applied in the field of ship and ocean engineering, can solve the problems of inability to realize online forecast of ship motion, reduce the accuracy of IMF, and reduce the accuracy of prediction, etc.

Active Publication Date: 2021-09-10
DALIAN MARITIME UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the Intrinsic Mode Function (IMF) obtained through mode decomposition will contain non-negligible noise, resulting in low prediction accuracy. Envelope, but the accuracy of the envelope from the first extreme point to the beginning and the last extreme point to the end of the time series is not high. This is called the endpoint effect, which will reduce the accuracy of the decomposed IMF. Reduced forecast accuracy
In addition, none of the above-mentioned forecasting methods can achieve online forecasting of ship motion

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Ship motion forecasting method based on improved EMD-AR model
  • Ship motion forecasting method based on improved EMD-AR model
  • Ship motion forecasting method based on improved EMD-AR model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be further described below in conjunction with the accompanying drawings. Such as figure 1 As shown, taking the rolling motion as an example:

[0066] A. Take T=1 second as the sampling period to collect ship rolling motion data, determine the length of the rolling time window n=500, and the rolling motion time series in the time window is x(t), t=1,2,... ,n;

[0067] B. Add and subtract k=5 normally distributed white noise sequences α to the rolling motion time series x(t) respectively q (t), q=1,2,...,k, form 2k new time series as follows:

[0068]

[0069] In the formula, k represents the number of white noise sequences;

[0070] C. Using the improved EMD algorithm for new time series For modal decomposition, such as figure 2 as shown,

[0071] Proceed as follows:

[0072] C1, create an empty array IMFs, make p=1, w=1;

[0073] C2, seeking All maxima sequences of and the sequence of minima is the position number of the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a ship motion forecasting method based on an improved EMD-AR model. The method can solve the problem of IMF modal aliasing obtained based on traditional empirical mode decomposition by adding and subtracting a plurality of white noises into and from a time sequence and performing empirical mode decomposition on a new time sequence, can enable IMF to be more accurate, and can improve the ship motion forecasting precision on the basis. According to the method, an SVR model is used for continuation of an upper envelope line and a lower envelope line of the ship motion time sequence, the two envelope lines from the first extreme point to the starting end and from the last extreme point to the tail end of the time sequence are reasonably obtained, the endpoint effect existing in traditional empirical mode decomposition is inhibited, the decomposed IMF is more accurate, and on the basis, the ship motion forecasting precision can be improved. The method is combined with an AR model and a rolling time window method, and an online iterative learning strategy of AR model coefficients is provided, so that high-precision online forecasting of ship motion can be achieved.

Description

technical field [0001] The invention relates to the technical field of ships and ocean engineering, in particular to a ship motion prediction method based on an improved Empirical Mode Decomposition-Autoregressive (EMD-AR) model. Background technique [0002] Affected by the marine environment such as wind, waves, and currents, the ship will produce motions in six degrees of freedom: roll, pitch, yaw, sway, surge, and heave, which will affect the safe operation of various on-board equipment. The sway, surge and yaw motion of the ship can be compensated by the anchor positioning or dynamic positioning system, while the roll, pitch and heave motion need to use the ship-mounted stabilization platform to isolate its influence on the equipment on board, so that the equipment Keep steady at all times, just like on land, reducing safety hazards. In order to perform synchronous compensation for the disturbance caused by the marine environment, it is necessary to carry out very shor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/20
CPCG06F30/20
Inventor 杜佳璐薛兴李健
Owner DALIAN MARITIME UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products