Wave compensation prediction method based on random forest algorithm and Adam neural network

Abstract

The invention provides a wave compensation prediction method based on a random forest algorithm and an Adam neural network. The method comprises the following steps: S1, collecting historical data ofa ship, and carrying out the normalization of the data, and obtaining an original data set; s2, extracting samples by utilizing a Bootstrap resampling method to form a plurality of training set samples; s3, calculating feature importance according to the random forest, and performing attribute screening; s4, constructing a neural network model, and training the neural network model by using an Adam algorithm according to the screened attribute samples as input quantities and the ship prediction values as output quantities; and S5, inputting the real-time monitoring data into the Adam neural network model to obtain a predicted value.

Description

technical field [0001] The invention relates to the technical field of ship wave compensation, in particular to a random forest algorithm and an Adam neural network wave compensation prediction method. Background technique [0002] my country is a country with a large ocean, and there is great potential for the development and utilization of marine resources. With the acceleration of the development of the marine industry and the promotion of the development of the marine economy, offshore platforms or ships are operating at sea more and more frequently. In the marine industry chain, offshore platforms and ships are the most important means of production and transportation, but they are different from land, and the relative positions of ships will change due to rolling, pitching and heaving caused by wind and waves. At the same time, there will be problems such as low operating efficiency and hidden dangers to personnel safety. Therefore, in order to improve the safety of ...

AI Technical Summary

Problems solved by technology

However, these prediction methods only have good results in linear systems and are not suitable for nonlinear systems

Foreign experts Sidar and Dodin use Kalman filter to predict wave motion in real time, but the Kalman filter prediction method needs to know the precise state motion mathematical formula of the system motion

However, when the hydraulic parameters and the environment are changed, the state equation is difficult to give precisely

Therefore, although the Kalman filter can deal with interference and the calculation is simple, it is difficult to achieve the ideal effect in practical application

The Chinese patent with the publication number CN 107357170 A "A Sea Wave Model Prediction Method Based on Active Disturbance Rejection State Observer" uses Fourier transform to quickly process the heave displacement signal, but it is suitable for the state of signal stability. Doesn't work well when non-stationary

Images