Modeling and control of a SES in various operational modes
MetadataVis full innførsel
- Institutt for marin teknikk 
Accessibility and comfort of often go in compromise of cost efficiency of the vehicle foroffshore commutation. The Surface effect ship (SES) is one of the most cost-efficient andcomfortable vehicles currently available for offshore commutation. The Boarding ControlSystemTM (BCS) damps vertical motions on a SES to increase accessibility to offshorestructures for safe transfer of goods and personnel. Some of the controller parameters arecurrently tuned manually. This tuning process poses extra workload for the crew aboardand is a highly inefficient way of tuning the controller.This thesis presents a boarding control system where one (of two) control parameters areautonomously tuned as well as an extensive simulation model for a surface effect ship(SES) in zero forward speed and head-sea. The vessels heave and pitch motions are exclusivelyanalysed in this study. The control system presented in this thesis, is an extension ofthe BCS (Auestad et al. 2015), using a machine learning approach. The simulation modelis created by using the framework of Marine System Simulator MSS (Fossen & Perez2016 (accessed April, 2018) and extending the hydrodynamic part of existing mathematicalmodel of the SES with linear interpolation. Based on the simulation model, stochasticgradient descent is used for learning the system s response under various loading conditionsand creates a signal which automates one of the tuning parameters.Results of the simulation model captured essential dynamics of the system earlier disregardedin the literature. Linear interpolation proved to be a powerful way to expresstime-varying potential coefficients which earlier were assumed to be constant. The resultsfrom the semi-autonomous boarding control system showed that the SGD algorithm wassuccessful at creating a function that gives an adaptive tuning parameter, which enhancedthe performance of the BCS.The simulation model is still to be verified with model-scale and full-scale experiments.The automated boarding control system still lacks an extensive stability analysis. Influencesof unmodelled environments should also be considered for future research.