Date of Award
2020
Document Type
Open Access Master's Thesis
Degree Name
Master of Science in Mechanical Engineering (MS)
Administrative Home Department
Department of Mechanical Engineering-Engineering Mechanics
Advisor 1
Gordon Parker
Committee Member 1
Guy Meadows
Committee Member 2
Andrew Barnard
Abstract
Instrumented moorings are often used to measure characteristics, such as temperature and current, over the water column. However, the moorings deflect from the effects of currents and waves, which could lead to innacurate measurements. In this work, a computationally efficient method to compensate for mooring sensor position errors is developed. The two-step process first uses a hydrodynamic model of the buoy and mooring line system to create estimated mooring line deflections in a steady current. A neural network model is trained to approximate the hydrodynamic model’s mooring line displacement given the spatial location of the buoy and current profile measurements. The method is illustrated using the Mackinac Straits West buoy that is part of the Upper Great Lakes Observing System (UGLOS). Its mooring line is instrumented with 10 thermistors, attached to the mooring line at varying intervals. Since the approach naturally provides interpolation, it allows researchers, with access to publicly available UGLOS data, to request temperatures at any depth. While the vertical deflection compensation method is illustrated here is for a particular mooring system, the process involved is applicable to a wide class of instrumented mooring systems. It was found that access to the current data of a mooring line increases the accuracy of the Neural Network, but knowing the position of the buoy in relation to the anchor can still give adequate results.
Recommended Citation
Price, Tom, "A Neural Network Approach to Estimate Buoy Mooring Line Sensor Deflection", Open Access Master's Thesis, Michigan Technological University, 2020.