O&M optimization of OWT support structures
using digital twins
This research will provide a framework to minimize the expected operation and maintenance (O&M) cost of offshore wind turbine support structures by employing digital twins. The framework will define an optimal management strategy, quantifying the value of potential strategies through a pre-posterior decision analysis.
The offshore industry has been trending towards larger wind turbines, often located far offshore. The degradation of turbine support structures is accentuated in harsh marine environments whereas inspections and maintenance tasks are more complex and cost demanding. Therefore, an optimal and rational management of offshore wind substructures is becoming increasingly important.
This research aims to develop a decision-making framework for optimal management (inspection, monitoring, and maintenance) of offshore wind turbine support structures using digital twins. A “digital twin” is a virtual replica of physical assets on which simulations can be run to predict the behavior of the real structure. A wind turbine “digital twin” may become less and less accurate over time due to behavioral changes of the physical turbine. However, a “digital twin” can also be updated through on-site monitoring data. Since the uncertainties are significantly reduced, the “digital twin” again represents the real turbine more accurately and helps the decision maker to make more rational and informed decisions. In this context, the developed decision-making framework will not only provide optimal management (inspection, monitoring, and maintenance) policies but also identify when the “digital twin” needs to be updated.
This PhD research will minimize the total expected life-cycle cost of offshore wind turbines by controlling structural failure risk of support structures through optimal management (inspection, monitoring, and maintenance) policies.
University of Liège
Prof. Philippe Rigo/Pablo G. Morato (ULiège)
Prof. Christof Devriendt (VUB)
The effect of failure criteria on risk-based inspection planning of offshore wind support structures | Hlaing, N., Morato, P. G., Rigo, P., Amirafshari, P., Kolios, A., & Nielsen, J. S. (2020) | Life-Cycle Civil Engineering: Innovation, Theory and Practice -Proceedings of the 7th International Symposium on Life-Cycle Civil Engineering, IALCCE 2020 (p. 146-153)
Probabilistic Virtual Load Monitoring of Offshore Wind Substructures: A Supervised Learning Approach | Hlaing, N., Morato, P. G., Rigo, P | he 32nd International Ocean and Polar Engineering Conference, ISOPE 2022
Inspection and maintenance planning of offshore wind structural components: Integrating fatigue failure criteria with Bayesian networks and Markov decision processes | Hlaing, N., Morato, P. G., Nielsen, J. S., Amirafshari, P., Kolios, A., & Rigo, P. (2022) | Structure and Infrastructure Engineering (In press)
Optimal management of offshore wind structural systems via deep reinforcement learning and Bayesian networks | Pablo G. Morato, Charalampos P. Andriotis, Konstantinos G. Papakonstantinou, Nandar Hlaing & Philippe Rigo | Wind Energy Science Conference, WESC2021