Offshore vessels (OVs) often require precise station-keeping and some vessels, for example, vessels involved in geotechnical drilling, generally use Spread Mooring (SM) or Dynamic Positioning (DP) systems. Most of these vessels are equipped with both systems to cover all ranges of water depths. However, determining which system to use for a particular operational scenario depends on many factors and requires significant balancing in terms of cost-benefit. Therefore, this research aims to develop a platform that will determine the cost factors for both the SM and DP station-keeping systems. Operational information and cost data are collected for several field operations, and Artificial Neural Networks (ANN) are trained using those data samples. After that, the trained ANN is used to predict the components of cost for any given environmental situation, fieldwork duration and water depth. Later, the total cost is investigated against water depth for both DP and SM systems to determine the most cost-effective option. The results are validated using two operational scenarios for a specific geotechnical vessel. This decision-making algorithm can be further developed by adding up more operational data for various vessels and can be applied in the development of sustainable decision-making business models for OVs operators.
Globally Consistent 3D LiDAR Mapping with GPU-accelerated GICP Matching Cost Factors