Incorporation of ship motion prediction into active heave compensation for offshore crane operation

Ship motion has significant effects on certain maritime applications like offshore crane operation. In particular, the vertical heave motion is undesired for safe transferring, accurate positioning and subsea installation. In recent years, there have been growing tasks in utilizing ship motion data for online operation improvement based on the development of virtual simulation environment, digital twin and automatic remote-control systems. How to effectively utilize ship motion data is fundamental to these tasks. This paper presents a neural-network-based method to predict ship motion and use the prediction to improve active heave compensation (AHC) of offshore crane operation. A virtual prototype of the lifting system is developed including implementation of the proposed AHC algorithms. A multilayer perceptron model is trained to predict ship motion. By feeding the future motion of the ship into the controller, the lifting performance can be tested in the virtual environment and the result can be applied to its counterpart. Through simulation with measured sensor data, the proposed method is verified efficient in improving crane operation performance