Real-time monitoring of unmanned FOWT by using sensors and algorithms

Author(s): MooHyun Kim, Woo Chul Chung
Texas A&M University, College Station, TX
International Journal of Smart Grid and Clean Energy, vol. 10, no. 3, July 2021: pp. 183-190
ISSN: 2315-4462 (Print)
ISSN: 2373-3594 (Online)
Digital Object Identifier: 10.12720/sgce.10.3.183-190

Abstract: The current line-monitoring technology in deep water is based on battery-powered sensors and post-processing of sensor signals, in which real-time monitoring is not possible. Even when real-time multiple-sensor signals are available, the robust algorithms for the real-time monitoring of profile, stress, and fatigue are very rare. In this paper, three new technologies are presented, i) real-time inverse estimate of incoming incident random wave by using adaptive Kalman filter, ii) real-time estimate of line profiles and stresses by using multiple inclinometers and robust algorithm, iii) real-time estimate of line profiles and stresses by using minimal number of inclinometers and ANN-based machine-learning algorithm. The first two items have been developed by authors as briefly demonstrated in this paper and the development for the third item is in progress, for which the first and second items are essential. The corresponding big data necessary for training the developed machine-learning algorithm is generated by the reliable turbine-floater-mooring-powerline coupled dynamics simulation program developed by authors.

Keywords: line monitoring, floating wind turbines, sensors, digital twins, machine learning, inclinometers, inverse wave estimate, Kalman filter, turbine-floater-mooring-powerline coupled dynamics simulation
Full Paper.pdf
Copyright © 2021 International Journal of Smart Grid and Clean Energy, All Rights Reserved