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

Short-term ship navigational speed prediction method based on time sequence random forest

A technology of random forest and forecasting method, applied in forecasting, computer components, instruments, etc., can solve the problem that the estimated value cannot meet the experimental needs, and achieve high accuracy and strong robustness

Pending Publication Date: 2022-04-12
DALIAN MARITIME UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] According to the above mentioned data, most of the estimated values ​​cannot meet the technical requirements of the experiment, and a short-term ship speed prediction method based on time-series random forest is provided

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
  • Short-term ship navigational speed prediction method based on time sequence random forest
  • Short-term ship navigational speed prediction method based on time sequence random forest
  • Short-term ship navigational speed prediction method based on time sequence random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] The present invention has carried out experimental comparison with autoregressive moving average model (ARMA), Kalman filter model (KF), long short-term memory artificial neural network model (LSTM) under the same data set, as shown in table 1, table 2. The model of the present invention is superior to other five models in terms of mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R^2) under single-step prediction and multi-step prediction modes.

[0070] Table 1 Comparison of single-step prediction experiment results

[0071]

[0072] Table 2 Comparison of multi-step prediction experiment results

[0073]

[0074] The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

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 provides a short-term ship navigational speed prediction method based on a time sequence random forest. The short-term ship navigational speed prediction method comprises the following steps of obtaining modeling data and performing data preprocessing; introducing the time sequence data into a random forest learner to construct a brand new prediction model framework; setting related parameters of the model; and predicting by using the model. According to the method, the short-term speed of the ship to water can be predicted by using the historical sailing speed of the ship and the marine weather forecast data, the phenomenon that the ship engine is directly used for monitoring the data in real time is avoided, the requirement for shipborne monitoring equipment is low, and meanwhile prediction and afterwards experimental analysis of the ship speed are achieved in advance. The mean absolute error (MAE), the root-mean-square error (RMSE) and the coefficient of determination (R2) of the model are superior to those of other three common models.

Description

technical field [0001] The present invention relates to the technical field of speed prediction, in particular, to a short-term ship speed prediction method based on time series random forest. Background technique [0002] Estimation and prediction of ship speed has always been a very important topic in the field of shipping. Compared with the speed estimation using observation data or reanalysis data, it is often more difficult to predict the speed of ships in the future, but it is more in line with actual needs. There are two main reasons why it is difficult to achieve high accuracy in speed prediction. First, in the prediction stage, the available data is very limited, usually only weather forecast data, static parameters of ships, and historical navigation data. Real-time monitoring data of ship engines or propellers cannot be obtained in advance for forecasting, but such data are very important for speed estimation. Secondly, the forecast data used for ship speed pred...

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
IPC IPC(8): G06Q10/04G06Q50/30G06F16/2458G06K9/62
Inventor 王怡洋郭雨寒王军
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com