Predicting the capability-polar-plots for dynamic positioning systems for offshore platforms using artificial neural networks

As the capability of polar plots becomes better understood, improved dynamic positioning (DP) systems are possible as the control algorithms greatly depend on the accuracy of the aerodynamic and hydrodynamic models. The measurements and estimation of the environmental disturbances have an important role in the optimal design and selection of a DP system for offshore platforms. The main objective of this work is to present a new method of predicting the Capability-Polar-Plots for offshore platforms using the combination of the artificial neural networks (NNs) and the capability polar plots program (CPPP). The estimated results from a case study for a scientific drilling vessel are presented. A trained artificial NN is designed in this work and is able to predict the maximum wind speed at which the DP thrusters are able to maintain the offshore platform in a station-keeping mode in the field site. This prediction for the maximum wind speed will be a helpful tool for DP operators in managing station-keeping for offshore platforms in an emergency situation where the automation of the DP systems is disabled. It is obvious from the obtained results that the developed technique has potential for the estimation of the capability-polar-plots for offshore platforms. This tool would be suitable for DP operators to predict the maximum wind speed and direction in a very short period of time.