Through the analysis of data from the SCADA system of a wind turbine unit in a specific offshore wind farm located in Zhanjiang, it was observed that the most prevalent type of fault is bearing alarms on the gearbox’s generator side. Considering the growing need for intelligent offshore wind turbine maintenance, this study employed GRA on SCADA data collected over a significant duration from a representative wind turbine unit. Relevant features were extracted, with temperature serving as the target parameter. To address the challenge of long-term dependencies in long-term time series forecasting tasks, this study uniquely combined the GRU with the advanced Transformer neural network which incorporates attention mechanisms, to predict the temperature trend of the gearbox’s generator-side bearing. Based on the prediction residuals obtained during normal operation and their subsequent analysis, the study devised an effective anomaly detection process to identify early abnormal states of the gearbox’s generator-side bearing. Comparative performance evaluations were conducted, comparing the combined model with its individual component models, as well as the traditional LightGBM, in terms of temperature time series prediction and their application in anomaly detection. The results unequivocally demonstrate that the combined model outperforms both the individual models and LightGBM in terms of time series prediction accuracy and anomaly detection effectiveness, indicating an enhanced ability to handle long-term memory challenges. Furthermore, the combined model exhibits great potential of practical application for the early warning of gearbox bearing anomalies during actual wind turbine daily operation and maintenance, providing a valuable solution for the offshore wind turbine industry.

The supervisory control and data acquisition (SCADA) system of wind turbines continuously collects a large amount of monitoring data during their operation. These data contain abundant information about the operating status of the turbine components. Utilizing this information makes it feasible to provide early warnings and predict the health status of the wind turbine. However, due to the strong coupling between the various components of the wind turbine, the data exhibits complex spatiotemporal relationships, multiple state parameters, strong non-linearity, and noise interference, which brings great difficulty to anomaly detection of the wind turbine. This paper proposes a new method for detecting abnormal operating conditions of wind turbines, based on a cleverly designed multi-layer linear residual module and the improved temporal convolutional network (TCN) with a new norm-linear-ConvNeXt architecture (NLC-TCN). Initially, the NLC-TCN deep learning reconstruction model is trained with historical data of normal behavior to extract the spatiotemporal features of state parameters under normal operational conditions. Subsequently, the condition score of the unit is determined by calculating the average normalized root mean square error between the reconstructed data and actual data. The streaming peaks-over-threshold real-time calculation of the anomaly warning threshold, based on extreme value theory, is then used for preliminary fault monitoring. Moreover, by shielding the fault alarm for low wind speeds and implementing a continuous delay perception mechanism, issues related to wind speed fluctuations and internal and external interference are addressed, enabling early warning for faulty units. Finally, the effectiveness and reliability of the proposed method are validated through comparative experiments using actual offshore wind farm SCADA data. The performance of the proposed method surpasses that of other compared methods. Additionally, the results of the proposed method were evaluated using the uniform manifold approximation and projection dimensionality reduction technique and kernel density estimation.

To investigate the internal flow characteristics of particles during hydraulic lifting in deep-sea mining risers, this study developed a three-dimensional curved riser multiphase flow model based on the Eulerian–Eulerian framework and the RNG k-ε turbulence model. The effects of particle distribution and pressure loss in the curved section, as well as the influence of curvature radius, were analyzed. Results indicate that particle distributions take concave circular or crescent-shaped patterns, becoming more uniform with larger curvature radii. Pressure on the extrados is consistently greater than on the intrados, with pressure loss increasing in the bend and peaking at the midpoint. A larger curvature radius leads to greater total pressure loss but lower frictional loss. Additionally, the bend experiences a restoring force toward the vertical position, which increases as the curvature radius decreases.

Large-eddy simulation was conducted on turbulent flow in toroidal pipes of various lengths to study the impact of streamwise fluctuation structures on the secondary motion and explore the origin of the swirl-switching phenomenon. Proper orthogonal decomposition analysis was carried out to identify the primary coherent structures in the flow field and determine the oscillation frequencies of the swirl switching. The results show that high-frequency switching (St > 0.05) is closely related to the spatial scale of very-large-scale motion (VLSM), and that its streamwise extension is approximately the characteristic length corresponding to the switching frequency. Conversely, the characteristic length of low-frequency switching (St ≤ 0.05) is significantly larger than the physical model, which is not attributed to the spatial scale of streamwise fluctuations but rather to the temporal oscillations of the VLSM. Due to the sensitivity of the VLSM structure, the alignment mechanism of VLSM changes under vertical excitation, leading to a reduction in the streamwise characteristic length and an increase in the frequency of swirl switching. The spatiotemporal variations of the VLSM feedback into the frequency of swirl switching, thus confirming the significant effect of streamwise fluctuation. Additionally, the wall shear stress exhibits oscillation frequencies associated with swirl switching and VLSM, indicating a correlation between flow field fluctuations and wall shear stress, which could potentially contribute to material erosion and local resonance.

During offshore wind turbine maintenance operations, maintenance vessels typically rely on transfer gangways to achieve safe transfer of personnel from the vessel to the wind turbine. With the development of offshore wind farms toward far sea areas, working sea state conditions have become increasingly complex. In recent years, the application of large-scale active wave compensation (AWC) transfer gangways has mitigated the adverse effects of ship motions on transfer operations to a certain extent, but the problem of limited motion ranges of each gangway joint has also emerged as a prominent issue. Under complex sea state conditions, if the station-keeping position of the maintenance vessel is improperly selected, joint limit violations may occur during the gangway compensation process, thereby posing safety risks. To address the above problems, this paper develops a novel geometric-envelope-based analytical method for operational sea states and ranges that explicitly accounts for gangway joint constraints and wave-induced vessel motions to meet the safety requirements of large-scale gangways. Subject to the motion constraints of gangway joints, to ensure that the initially selected station-keeping position of the vessel satisfies the requirements for safe gangway transfer, the feasible domain and motion range of the gangway base point under different sea states are obtained. By solving for the solutions where the motion range of the base point lies entirely within the feasible domain, feasible schemes for vessel station-keeping operations under different sea states are derived. The results show that the gangway can operate safely under sea states 3 and 4 but fails under sea state 5. The allowable height difference between the transfer point and the gangway base is [−2.7 m, 8.7 m] for sea state 3 and [1.8 m, 3.5 m] for sea state 4. The operational area on the horizontal plane presents a partial ring shape, and the ring width first increases and then decreases with increasing height difference. Finally, random numerical examples are designed to demonstrate the applicability and internal consistency of the proposed analytical method.