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.