Daeyong Lee

The mooring system is the dominant single point of failure on a floating offshore wind turbine, and inspecting it drives much of its operations and maintenance cost. Data-driven damage classifiers could ease that burden, but they are usually trained and tested on one sea-state distribution, so accuracy drops for the severe conditions that lie outside it. This work presents a domain-adversarial gated recurrent unit (GRU) that identifies eleven mooring conditions from the platform’s six rigid-body motions and transfers, under a semi-supervised protocol, to sea states for which no damage labels are available in training. The conditions span a healthy baseline, single-line and multi-line stiffness loss, non-uniform degradation, and two biofouling severities; all are sub-failure damage cases whose motion signatures are weak and easily confused. The model is trained on operational sea states and tested on unseen extreme storm states (22–26 m/s wind, 8.0–9.5 m significant wave height), simulated in OpenFAST with MoorDyn on the IEA 15 MW UMaine VolturnUS-S platform. A three-phase schedule combining a labeled intermediate near-target domain with adversarial alignment of the training and test feature distributions raises per-simulation macro-F1 across three seeds to 0.87, against 0.29 for a source-only model, 0.47 for the near-target bridge alone and 0.73 for adversarial alignment alone. Neither component reaches this level by itself: alignment supplies the larger share of the gain and the bridge stabilizes it, reducing seed-to-seed variability roughly fourfold. The gain persists under sensor noise up to 20% of the per-channel standard deviation, and a parameter-matched 1D-CNN backbone confirms it is not tied to the recurrent architecture. The setting is semi-supervised, with respect to which target domain labels are available for the source and the intermediate near-target range, while the target sea states contribute unlabeled windows only. Because it requires no labels at the target sea states and only the standard six-degree-of-freedom motion sensors, the method can be extended to the severe, unseen simulated sea states that an asset meets in service; labeled near-target simulations from a calibrated platform model are still required. The present study is a simulation-based feasibility study: all evidence derives from OpenFAST and MoorDyn simulations of a single platform, and validation against tank-test or field measurements remains to be carried out.

Modern offshore wind turbines require increasingly larger monopile foundations, often with low embedded length-to-diameter ratios that fall outside the calibration range of the conventional standard p–y approach. Consequently, existing code-based p–y methods may provide an incomplete representation of the three-dimensional soil–structure interaction mechanisms mobilized under lateral loading. This study presents a comprehensive assessment of current geotechnical design concepts for laterally loaded monopiles embedded in clay and sand. To this end, three-dimensional finite element (FE) analyses were performed and used as the benchmark for comparison. The analyses employed the NGI-ADP constitutive model to simulate clay and the HSsmall constitutive model to represent sand. The FE models were validated against the PISA field test results from the Cowden and Dunkirk sites prior to their use in the subsequent evaluation. The validated FE models were then used to extract PISA-based p–y curves, which were compared with the code-based formulations for sand and clay at both the local p–y level and the global load–displacement level using 1D Winkler analyses. In addition, a moment contribution ratio (MCR) analysis was carried out to quantify the relative contributions of the individual resistance mechanisms governing monopile behaviour in both sand and clay. FE-extracted PISA p–y curves consistently produced the closest predictions of monopile behaviour captured in the FE analysis, while conventional code-based p–y formulations underestimated resistance in clay and overestimated it in sand. MCR analysis confirmed that lateral p–y reaction is the dominant resistance component, but shaft friction and base shear are important for short monopiles, especially at small displacements; incorporating these components into FE-calibrated 1D Winkler models substantially improves agreement with 3D FE predictions while retaining computational efficiency.

Offshore wind turbine support structures are increasingly required to operate in deeper and more demanding marine environments, where cyclic loading, hydrodynamic forcing, corrosion, scour, soil-structure interaction, and limited long-term monitoring continue to challenge structural reliability and lifecycle performance. This review synthesizes current knowledge on the reliability, degradation mechanisms, and maintenance needs of major offshore wind support-structure concepts, including monopiles, jackets, gravity-based foundations, tripods, hybrid fixed-bottom systems, spars, semi-submersibles, and tension-leg platforms. The study integrates findings from global field observations, reported failure cases, industrial practice, and recent advances in structural health monitoring, digital twins, robotics-assisted inspection, and AI-supported predictive operation and maintenance. Particular emphasis is placed on how marine environmental conditions and offshore loading processes influence structural response, fatigue behavior, corrosion-scour progression, and maintenance demand across fixed and floating systems. The review also identifies key gaps in long-term field validation, unified reliability assessment, and integrated monitoring-to-maintenance frameworks. By combining structural, operational, and marine-environment perspectives, this paper provides a consolidated reference for improving the durability, safety, and sustainability of offshore wind support structures within the broader context of marine renewable energy development.

Wind turbines are increasingly deployed at larger scales and in harsher operating environments, leading to greater structural complexity, stronger load variability, and higher maintenance demands across both drivetrain and structural components. Reported field data indicate that gearboxes and bearings account for approximately 30–40% of total turbine downtime, while blade-related failures contribute roughly 20–25% of reported failure events, primarily through fatigue, delamination, leading-edge erosion, and lightning-induced defects. In parallel, large-scale and offshore turbines show increasing susceptibility to tower fatigue cracking, corrosion-assisted degradation, and flange joint bolt-preload loss under cyclic and environmental loading. This review provides a comprehensive applied-engineering synthesis of failure mechanisms, reliability challenges, and monitoring strategies for major wind turbine components, including gearboxes, bearings, blades, towers, and flange joints. A wide range of condition monitoring, structural health monitoring (SHM), and prognostics and health management (PHM) approaches is critically examined, including vibration analysis, acoustic emission, ultrasonic inspection, infrared thermography, impedance-based sensing, electromagnetic methods, machine vision, SCADA-based diagnostics, and artificial-intelligence-assisted fault classification. The review compares these techniques in terms of detectable damage types, spatial coverage, sensitivity, deployment practicality, and limitations under real operating conditions. In addition, statistical reliability methods and data-driven models are discussed to interpret failure trends and uncertainty. Recent AI-based studies have reported fault classification accuracies exceeding 90% under controlled or semi-controlled conditions; however, their field reliability remains constrained by data imbalance, domain shift, limited labeled failure datasets, model interpretability, and insufficient validation under realistic turbine operating environments. The main contribution of this review is an integrated applied synthesis that connects drivetrain and structural failure mechanisms with measurable monitoring indicators, diagnostic technologies, AI-enabled PHM limitations, and predictive-maintenance decision needs. The paper provides practical guidance for monitoring design, early fault detection, predictive maintenance, and long-term reliability improvement in next-generation wind turbine systems.

Predicting structural loads on offshore wind turbine support structures under varying environmental conditions is a complex yet critical task, particularly for large-capacity turbines such as the 15 MW offshore wind turbine. Current prediction methods often struggle with accuracy, especially for torsional moments, due to the non-linear interactions between wind parameters and structural responses. To address this challenge, present study develops a generalized load estimation framework using multivariable polynomial regression, leveraging 10,000 numerical simulations. The framework accounts for four critical variables: Extreme Wind Speed (30 to 40 m/s), Turbulence Intensity (12% to 16%), Flow Inclination Angle (−8° to +8°), and Shear Exponent (0.1 to 0.3). The proposed equations predict six key moment components at the tower base, including the bending moments about the y-axis, torsional moments about the z-axis, bending moments in the x-y, x-z, and y-z planes, and the resultant combined moment. The framework was validated using 2000 testing data points, achieving high accuracy with R² values exceeding 0.92 for all moments. Specifically, the prediction accuracy was highest for the resultant combined moment and y-z bending moment, with average absolute errors of 5.76% and 5.97%, respectively, while x-z bending moment had a slightly higher error of 13.91%, highlighting that torsional moments are inherently more challenging to predict. Heatmap and scatter plot analyses confirmed that the predicted moments align closely with the simulated values, particularly for the torsional moment about the z-axis and y-z bending moment, with standard deviation values as low as 4.85. By optimizing polynomial degrees between 2 and 4, the framework effectively balances prediction accuracy and computational efficiency. This approach provides engineers and scientists with a reliable tool for load estimation, facilitating improved design and analysis of offshore wind turbine support structures.

This study presents a numerical investigation into the structural behavior of a pile-in-pile (PIP) slip joint utilizing square hollow section (SHS) members, with a comparative assessment against conventional circular hollow sections (CHSs). A comprehensive finite element model was developed and validated against published CHS experimental results to evaluate key performance indicators, including stress distribution, buckling behavior, and load-carrying capacity under pure bending, axial compression, and diagonal lateral loads. The analysis revealed that SHS joints demonstrated distinct stress concentration patterns and higher capacity under axial compression, whereas CHS joints provided superior performance under bending due to their geometric symmetry. However, SHS corners were more vulnerable under diagonal loading, exhibiting localized buckling at relatively lower loads. These structural weaknesses can be mitigated through design improvements, such as increased wall thickness or corner strengthening. The findings highlight that while SHSs introduce certain vulnerabilities compared to CHSs, they also offer advantages in axial load resistance, supporting their potential as a viable alternative for offshore wind foundation connections.