Digital Twins-based integrated corrosion fatigue prognosis of wind turbines Towers in modular energy islands

点击翻译按钮获取中文摘要

Facing the goal of climate neural set by the EU Green Deal, the modular energy island is suggested to utilise the attractive windpower at the deep sea. As a matter of factor, a prominent structural challenge arises, i.e., the corrosion fatigue deterioration of windtowers under the combination of the harsh marine environment, prominent cyclic loads, and a copious number of weldedconnections. Thus, the TwinsTower action aims to develop new and practical contributions towards a better understanding of thecorrosion fatigue of wind towers in modular energy islands, with both the physical model, inspection result and monitoring dataintegrated. The experienced research (ER) will: (i) establish an integrated corrosion fatigue prediction model for wind towers in themodular energy island; (ii) construct a digital twins-based prognosis approach for wind towers in modular energy islands, with themonitoring and inspection result integrated.Implemented at the University of Birmingham, as supervised by the Chair Prof Charalampos Baniotopoulos, this action will enable theER to diversify his competence by developing his skills in wind energy research, data science, knowledge dissemination andexploitation, networking, supervision, teaching, research management and leadership. This action will also strongly benefit the ER'sinter-sectoral and interdisciplinary expertise and strengthen the international network considering a secondment at the Ruhr-Universität Bochum.A two-way transfer of knowledge is guaranteed since the action integrates the ER's experience in corrosion fatigue prediction,probabilistic modelling of deterioration, and engineering practises as well as the hosts' expertise in tower design and detailing, deeplearning, and SHM data exploitation. To sum, the TwinsTower action could contribute to the EU's knowledge-based society,policymakers and professionals by offering invaluable knowledge and a practical approach supporting the goal of climate neural.