Development of Dynamic Positioning System of Coupled Floating Bodies by Neural Networks

Recently, it is in a tendency that the ocean oil field development is expanded to the deep sea and/or severe external force areas asking for new petroleum resources. To maintain high operating rate of the floating oil production systems, which are promising in the deep-sea area, it is important to reduce relative horizontal distance and hawser tension between FSPO and the shuttle tanker at tandem offloading configuration even in the severe sea conditions. In this study, a neural network control technology, which enables to reduce hawser tension by controlling FPSO's yaw angle has been developed. The control algorithm has been verified to raise wave height limit of work from 3.5m to 4.5m through computer runs and model tests in an experimental tank.