Abstract: Complicated loads encountered by floating offshore wind turbines (FOWTs) in real sea conditions are crucial for future optimization of design, but obtaining data on them directly poses a challenge. To address this issue, we applied machine learning techniques to obtain hydrodynamic and aerodynamic loads of FOWTs by measuring platform motion responses and wave-elevation sequences. First, a computational fluid dynamics (CFD) simulation model of the floating platform was established based on the dynamic fluid body interaction technique and overset grid technology. Then, a long short-term memory (LSTM) neural network model was constructed and trained to learn the nonlinear relationship between the waves, platform-motion inputs, and hydrodynamic-load outputs. The optimal model was determined after analyzing the sensitivity of parameters such as sample characteristics, network layers, and neuron numbers. Subsequently, the effectiveness of the hydrodynamic load model was validated under different simulation conditions, and the aerodynamic load calculation was completed based on the D’Alembert principle. Finally, we built a hybrid-scale FOWT model, based on the software in the loop strategy, in which the wind turbine was replaced by an actuation system. Model tests were carried out in a wave basin and the results demonstrated that the root mean square errors of the hydrodynamic and aerodynamic load measurements were 4.20% and 10.68%, respectively.

基于长短周期记忆神经网络的浮式风电机组载荷测量方法

[1]BarooniM, AshuriT, Velioglu SogutD, et al., 2023. Floating offshore wind turbines: current status and future prospects. Energies, 16(1):2.

[2]ChenJH, HuZQ, LiuGL, et al., 2019. Coupled aero-hydro-servo-elastic methods for floating wind turbines. Renewable Energy, 130:139-153.

[3]ChenP, JiaCJ, NgC, et al., 2021. Application of SADA method on full-scale measurement data for dynamic responses prediction of Hywind floating wind turbines. Ocean Engineering, 239:109814.

[4]CiuriucA, RaphaJI, GuancheR, et al., 2022. Digital tools for floating offshore wind turbines (FOWT): a state of the art. Energy Reports, 8:1207-1228.

[5]DaiJC, HuW, YangX, et al., 2018. Modeling and investigation of load and motion characteristics of offshore floating wind turbines. Ocean Engineering, 159:187-200.

[6]FengXH, FangJY, LinYG, et al., 2023a. Coupled aero-hydro-mooring dynamic analysis of floating offshore wind turbine under blade pitch motion. Physics of Fluids, 35(4):045131.

[7]FengXH, LinYG, GuYJ, et al., 2023b. Preliminary stability design method and hybrid experimental validation of a floating platform for 10MW wind turbine. Ocean Engineering, 285:115401.

[8]JiangX, DayS, ClellandD, et al., 2019. Analysis and real-time prediction of the full-scale thrust for floating wind turbine based on artificial intelligence. Ocean Engineering, 175:207-216.

[9]LiL, GaoZ, YuanZM, 2019. On the sensitivity and uncertainty of wave energy conversion with an artificial neural-network-based controller. Ocean Engineering, 183:282-293.

[10]LiYJ, LiW, LiuHW, et al., 2020. Indirect load measurements for large floating horizontal-axis tidal current turbines. Ocean Engineering, 198:106945.

[11]LiuYC, LiSW, YiQ, et al., 2016. Developments in semi-submersible floating foundations supporting wind turbines: a comprehensive review. Renewable and Sustainable Energy Reviews, 60:433-449.

[12]MaG, JinCL, WangHW, et al., 2023. Study on dynamic tension estimation for the underwater soft yoke mooring system with LSTM-AM neural network. Ocean Engineering, 267:113287.

[13]MaesK, IliopoulosA, WeijtjensW, et al., 2016. Dynamic strain estimation for fatigue assessment of an offshore monopile wind turbine using filtering and modal expansion algorithms. Mechanical Systems and Signal Processing, 76-77:592-611.

[14]MicallefD, RezaeihaA, 2021. Floating offshore wind turbine aerodynamics: trends and future challenges. Renewable and Sustainable Energy Reviews, 152:111696.

[15]NoppeN, WeijtjensW, DevriendtC, 2018. Modeling of quasi-static thrust load of wind turbines based on 1 s SCADA data. Wind Energy Science, 3(1):139-147.

[16]PahnT, RolfesR, JonkmanJ, 2017. Inverse load calculation procedure for offshore wind turbines and application to a 5-MW wind turbine support structure. Wind Energy, 20(7):1171-1186.

[17]Pegalajar-JuradoA, BredmoseH, BorgM, et al., 2018. State-of-the-art model for the LIFES50+ OO-Star wind floater semi 10 MW floating wind turbine. Journal of Physics: Conference Series, 1104:012024.

[18]RenZR, ZhouHY, LiBB, et al., 2022. Localization and topological observability analysis of a moored floating structure using mooring line tension measurements. Ocean Engineering, 266:112706.

[19]RoddierD, CermelliC, AubaultA, et al., 2010. WindFloat: a floating foundation for offshore wind turbines. Journal of Renewable and Sustainable Energy, 2(3):33104.

[20]SongMM, ChristensenS, MoaveniB, et al., 2022. Joint parameter-input estimation for virtual sensing on an offshore platform using output-only measurements. Mechanical Systems and Signal Processing, 170:108814.

[21]WangZM, QiaoDS, YanJ, et al., 2022a. A new approach to predict dynamic mooring tension using LSTM neural network based on responses of floating structure. Ocean Engineering, 249:110905.

[22]WangZM, QiaoDS, TangGQ, et al., 2022b. An identification method of floating wind turbine tower responses using deep learning technology in the monitoring system. Ocean Engineering, 261:112105.

[23]WenBR, DongXJ, TianXL, et al., 2018. The power performance of an offshore floating wind turbine in platform pitching motion. Energy, 154:508-521.

[24]YangC, ChenP, ChengZS, et al., 2023. Aerodynamic damping of a semi-submersible floating wind turbine: an analytical, numerical and experimental study. Ocean Engineering, 281:114826.

[25]YangY, PengT, LiaoSJ, 2023. Predicting 3-DoF motions of a moored barge by machine learning. Journal of Ocean Engineering and Science, 8(4):336-343.