The objective of this research is to showcase the capacity of Artificial Neural Networks (ANNs) in modeling intricate non-linear systems, particularly focusing on offshore wind turbine towers. Instead of employing traditional Blade Element Momentum (BEM) theory, the authors utilize ANN to predict aerodynamic forces acting on wind turbine towers, leading to a significant reduction in computational time for wind turbine response analysis.

In addition to aerodynamic force prediction, this study incorporates ANNs into fatigue analysis methodologies for offshore wind turbine towers. By leveraging machine learning approaches, the computational burden associated with fatigue analysis, which typically entails numerous time history simulations, is substantially reduced compared to traditional methods. This enables more efficient and cost-effective assessments of wind turbine structural integrity over their operational lifespan.

Furthermore, a fragility analysis is conducted on the IEA-15MW offshore wind turbine, with a specific focus on evaluating the serviceability limit state associated with foundation tilt. The analysis underscores the criticality of considering Soil-Structure Interaction (SSI) effects in offshore wind turbine design, particularly in regions prone to significant environmental loading.

The findings of this research highlight the potential of ANN-based approaches to revolutionize computational methodologies in wind energy engineering. By integrating machine learning techniques into fatigue analysis, significant computational efficiencies are achieved, facilitating more expedient and accurate assessments of wind turbine structural reliability.

In conclusion, this study contributes to advancing the understanding of ANN applications in wind energy engineering, emphasizing their role in improving computational efficiency and accuracy in fatigue analysis. Additionally, the research underscores the importance of considering SSI effects in offshore wind turbine design to enhance structural integrity and performance.

Recently, a study on digital twin has been actively conducted to evaluate the structural intensity of ships and offshore structures. Previously, conservative structural safety was secured through design with a high safety factor and periodic inspections, but recently, using digital twin technology, it is possible to evaluate the structural intensity in real time. By synchronizing measured sensor data in real time with a digital twin model and performing simulation, evaluation of structural intensity such as structural response distribution, structural defect detection, actual fatigue life according to the sea state is performed, and further, accident prevention, maintenance plan can be established. Structural intensity evaluation through precise computational numerical analysis requires a lot of computational cost to use as a digital twin model that require faster simulation speeds. Therefore, a digital twin model is built by applying various techniques such as order reduction method and deep learning that can secure low computational costs. In this study, optimization of measured sensor placement was performed to improve prediction accuracy of reduction order model about ships and offshore structure. The target structure was a multi-linked floating offshore structure, and the bending stress was predicted by order reduction model based on distortion base mode. A structural response database was established through fluid-structure coupled analysis, and distortion base modes were selected using mode orthogonality and autocorrelation coefficients. Although it costs a lot of computational time to evaluate performance of all possible sensor placement combinations, the optimization technique saved about 8 times the time cost, and the root mean square error related in prediction accuracy with resulted in a sensor placement was reduced by about 84.0% compared to numerical analysis results. In addition, it was confirmed that the measured sensor data in the model test had a 28.6% improved prediction performance compared to the previously set sensor placement.

In this study, we present the results of a fatigue analysis conducted on a wind farm using NREL's state-of-the-art FAST.farm model, which have been developed to accurately simulate complex wind farm geometries and incorporate turbulence effects at the wind farm level. Leveraging these advanced models, we assessed the structural integrity and longevity of the wind farm under varying environmental conditions.

Through rigorous analysis, we investigated the fatigue accumulation patterns across turbines within the wind farm, considering the dynamic interaction of turbulent atmospheric conditions and wake effects. Our findings shed light on the critical factors influencing fatigue damage distribution and highlight the importance of comprehensive fatigue analysis for ensuring the reliability and durability of wind energy infrastructure.

Looking ahead, our future work will focus on leveraging these fast.farm models to generate synthetic datasets for training machine learning models, particularly Artificial Neural Networks (ANNs). By mapping external conditions to turbine loads, these ANN models will offer valuable insights into load prediction at the wind farm level.

While direct validation of load predictions remains a challenge due to data limitations, our approach will involve cross-checking power output predictions against Supervisory Control and Data Acquisition (SCADA) records. This verification process will provide an indirect validation method for assessing the accuracy and reliability of the ANN model's load predictions.

This ongoing research represents a significant advancement in the field of wind energy engineering, with a focus on enhancing predictive modeling capabilities for offshore wind farms. By integrating high-fidelity modeling techniques and machine learning methodologies, we aim to optimize operational efficiency and support informed decision-making in the renewable energy sector.

Owing to structural flexibility, floating offshore wind turbines (FOWTs) are prone to exhibit strong dynamic responses under severe wind-wave conditions, which can result in the accumulation of fatigue damage over time. As integrated with the high corrosivity of the offshore environment, FOWT deterioration accelerates and structural reliability further declines. The pitch control strategy for load reduction while remaining rated power generation at the above-rated wind speeds is considered a significant active control approach to mitigate fatigue damage and improve structural reliability. However, the current loading-reducing pitch controller focuses on lowering peak response or fatigue damage equivalent load (DEL) based on the linear fatigue damage accumulation theory, ignoring the corrosion influence and lacking a thorough reliability analysis. In this article, a comprehensive analysis framework combining pitch control strategy and C-F assessment is proposed to investigate the impact of pitch controller on the bolts’ C-F performance, and further evaluate the component-level structural reliability. Based on the DTU 10-MW reference turbine and the C-F deterioration model, a fatigue-reduction-oriented pitch controller, the low authority linear-quadratic-integral controller (LQI) controller, is compared against the baseline controller (BC) used by the high-fidelity offshore wind turbine simulator OpenFAST on the corrosion-fatigue (C-F) behaviour of the bolts in ring-flange range connection of the FOWT tower and component-level reliability under various wind-wave conditions. The results show that the LQI controller offers improved performance in relegating stress ranges in bolts while optimizing power production, further improving the C-F situation and structural reliability. This highlights the importance of control strategy in FOWT structures and its effects on condition-based maintenance.