Active Heave Compensation Prediction Research for Deep Sea Homework Crane based on KPSO-SVR
In order to reduce the wind and wave impact when the crane operate on the sea,crane heave compensation prediction technology plays an important role on crane safety and efficient operation.In this article,on account of the nonlinear characteristics of crane heave motion model,we present a new approach to overcome the deficiency in the traditional mathematics method and the neural network method.This is crane active heave prediction modeling method based on support vector machine for regression(SVR).First of all,the crane heave movement prediction model based on SVR is given; And then,in order to improve the prediction performance of SVR,using the particle swarm algorithm(KPSO),improved by kalman filter,to train the parameters of the SVR and predict control research; Simulation experiments proved that the method has high heave motion prediction accuracy.Compared with other methods,the method has a better adaptability and faster convergence speed.
Deep sea homework crane Heave compensation Prediction algorithm Particle swarm algorithm SVR
SHI Bu-hai XIAN Ling WU Qi-peng ZHANG You-liang
School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640
国际会议
The 33th Chinese Control Conference第33届中国控制会议
南京
英文
7637-7642
2014-07-28（万方平台首次上网日期，不代表论文的发表时间）