The efficient prediction of system performance is a critical aspect of engineering equipment design, with the traditional methods facing limitations such as high computational demands and precise experimental setups. In response to these limitations, neural network prediction models offer a promising solution due to their lightweight and efficient predictive capabilities. In this context, the evolution of deep learning and computer vision has significantly influenced engineering design applications, particularly in recognizing intricate three-dimensional (3D) structural features. This study addresses the challenges of rapidly and efficiently predicting the performance of horizontal axis tidal turbine (HATT) blades by leveraging artificial intelligence technology. The proposed solution, named TurbineNet, is a neural network specifically designed for predicting the hydrodynamic performance of complex 3D turbine blades. TurbineNet utilizes two descriptors to capture the mesh information and structural features, refining these features through mesh convolution layers. The model establishes a robust connection between the blade features and hydrodynamic performance parameters via two fully connected layers. Through extensive training and validation, TurbineNet demonstrates proficiency in processing and identifying intricate blade surface features, resulting in accurate predictions of HATT hydrodynamic performance. The study showcases the robustness of TurbineNet through extensive testing, revealing its ability to predict hydrodynamic parameters with a relative error of 2%. This exceptional performance positions TurbineNet as a valuable tool for predicting the hydrodynamic performance of complex 3D turbine blade structures, offering a reliable means for assessing engineering equipment performance.

This paper explores innovative approaches for reconstructing the wake flow field of yawed wind turbines from sparse data using data-driven and physics-informed machine learning techniques. The physics-informed machine learning wake flow estimation (WFE) integrates neural networks with fundamental fluid dynamics equations, providing robust and interpretable predictions. This method ensures adherence to essential fluid dynamics principles, making it suitable for reliable wake flow estimation in wind energy applications. In contrast, the data-driven machine learning wake flow estimation (DDML-WFE) leverages techniques such as proper orthogonal decomposition to extract significant flow features, offering computational efficiency and reduced reconstruction costs. Both methods demonstrate satisfactory performance in reconstructing the instantaneous wake flow field under yawed conditions. DDML-WFE maintains comparable performance even with reduced measurement resolution and increased noise, highlighting its potential for real-time wind turbine control. The study employs a limited number of measurement points to balance data collection challenges while capturing essential flow field characteristics. Future research will focus on optimizing turbine control strategies in wind farms by incorporating multi-scale modules and advanced data-driven techniques for temporal prediction of wake flow fields.

A precise and cost-effective prediction tool for fluid-structure interaction (FSI) analysis is crucial for optimizing the structural design of tidal turbine blades. However, the high computational costs associated with fluid dynamic analysis pose a significant challenge, as the current lack of efficient FSI prediction methods hinders the advancement of cutting-edge tidal turbine designs. To address this issue, this paper proposes a novel consolidated framework that integrates deep learning convolutional neural networks (CNN) with blade element momentum (BEM) theory and finite element method (FEM) to perform deformation analysis of turbine blade structures. The proposed CNN-BEM-FEM integrated framework efficiently identifies the geometric features and predicts the hydrodynamic parameters of turbine blades and thus, achieving accurate assessments of the structural behavior of tidal turbines. The study applies two-step verification procedures to validate the prediction accuracy of the CNN-BEM-FEM framework and the result demonstrates excellent agreement with experimental tests for hydrodynamic performance and blade deformation. When compared with the static one-way FSI calculated by Ansys Workbench software, the computational efficiency of CNN-BEM-FEM framework increases by more than 18 times, with discrepancies in blade deformation and equivalent stress calculations generally less than 5 %. By applying the proposed method to predict the FSI performance of tidal turbine blades with various shear web structures, the practical applicability for composite turbine blade design is successfully demonstrated. The results underscore the potential of the CNN-BEM-FEM framework as an efficient and accurate prediction tool for optimizing the structural design of tidal turbine blades.

Real-time acquisition of dynamic wake field information has garnered substantial attention in the wind farm industry, as it provides a crucial data source for intelligent wind farm monitoring and control. However, the existing wind measurement technologies, such as light detection and ranging (LiDAR), are limited to sparse data point measurements. This paper explores the utilization of a Physics-Informed Neural Network (PINN) to reconstruct wind turbine wake dynamics, specifically focusing on the influence of active wind turbine yaw operation on wake evolution. The methodology involves creating a tailored loss function that combines sparse wake measurement data with the Navier-Stokes (NS) equations. More precisely, the neural network incorporates the NS equations as constraints to guide the prediction of physical quantities in the output, including downwind velocity, crosswind velocity, and pressure. Taking the dynamic wake during yawing as a case study, the proposed method showcases remarkable universality and robustness across diverse scenarios involving varying scanning angle intervals, measurement point spacings, frequencies, and noise levels. It successfully captures the dynamic trends in wake evolution during yawing and accurately forecasts the wake trajectory and deflection. Even when tested with actual wake measurement data, the method can still effectively reconstruct the flow field, indicating significant potential for the real wind farm yaw control.

Horizontal axis tidal turbines (HATT) are promising candidates for hydroelectric power extraction in coastal urban applications. Currently, concerns around the fluid-structure interaction (FSI) performance of turbines limit their industrial deployment while an efficient FSI prediction model can mitigate these concepts. In this paper, we present an innovative predictive model, TurbineNet, designed to accurately forecast the FSI characteristics of diverse composite tidal turbine blade structures, thereby facilitating its performance optimization. The TurbineNet model utilizes blade mesh information as input to predict HATT performance through a neural network framework. By integrating mesh convolution and fully connected layers, the model delineates the hydrodynamic behavior of deformed blades which then couples with the finite element method (FEM) for a comprehensive dynamic FSI analysis of composite material blades. Through the generation and training of a database of deformed blades, the new TurbineNet/FEM model is capable of precisely predicting the hydrodynamic performance under various structural parameters. This approach significantly streamlines the computational process associated with traditional FSI models, reducing prediction times by nearly 18 times compared to static FSI calculations using established platforms like Ansys Workbench, while maintaining high accuracy. Based on the innovative TurbineNet/FEM model, we analyzed the FSI characteristics of three different web structures. The incorporation of web structures can substantially reduce local stress and enhance the structural stability of the blades, thus preventing vibrations. Our high-efficiency predictive FSI tool and results can aid HATTs in increasing their much-needed contribution to stability optimization design. It has the potential to significantly optimize energy conversion in tidal turbines by refining blade designs to efficiently convert the kinetic energy of tidal currents into electrical energy.

Hydrofoils play a crucial role in enhancing the efficiency of fluid machinery designed for ocean environments, reducing lift-induced drag and contributing to improved overall performance. To optimize hydrofoil design, a profound comprehension of the complex fluid flows around the hydrofoil structure is essential. In fluid mechanics, a precise and continuous representation of flow dynamics is essential for analysis and control purposes. Thus, obtaining a complete flow field, either through computational fluid dynamics (CFD) or experimental testing is of great significance. Nevertheless, the rigorous requirements of flow field tests render it impractical to directly measure complete flows around the airfoil using current instrumentation, especially for those with complex physical geometries. To tackle this issue, a novel deep learning framework is proposed to reconstruct the complete flow field by leveraging incomplete complementary flow data. As the representative benchmark problems, the flows around the Clark-Y hydrofoil at Re = 7 x 105 and the experimental NACA0012 2D hydrofoil at Re = 1800 have been investigated under different missing-flow scenarios of varying proportions, locations and orientations. Results demonstrate a remarkable agreement between the reconstructed flow field and the ground truth data, indicating the excellent performance of the proposed deep-learning model for missing flow reconstruction. A sensitivity analysis assesses the impact of the snapshot number and the latent space, revealing the method's robustness in selecting these parameters and simplifying its implementation in practical applications. This deep learning method offers the advantage of being implemented using paired incomplete flow fields, without the need for pre-known ground truth results as labels, holding the potential for addressing more complex full-field reconstruction problems in the future.

Wind turbine wake poses a significant challenge in wind farm operations, affecting power generation efficiency. This study introduces a Dynamic Wake Flow Estimation (DWFE) framework designed to predict wind turbine wake evolution from sparse measurement data. The framework integrates Gaussian Process Regression (GPR), Proper Orthogonal Decomposition (POD), and Long Short-Term Memory (LSTM) networks. Specifically, GPR plays a pivotal role in DWFE by enabling the transformation of flow fields discrete sensor signals into coherent, low-dimensional flow fields which is crucial for accurate flow field predictions, while POD aids in dimensionality reduction and LSTM forecasts temporal wake dynamics, improving both predictive accuracy and computational efficiency. Parametric analysis demonstrates that the robustness and adaptability of the framework improve prediction accuracy with increased sensor density and flexible POD modes. The DWFE framework demonstrates high accuracy in wake flow estimation even with limited data, effectively capturing dynamic wake behavior. Future work will extend this approach to various topographic and climatic conditions, optimizing computational efficiency, and improving interpretability. These advancements will expand the framework's applicability in wind energy and other engineering fields requiring precise flow prediction, emphasizing DWFE's potential in advancing wind farm design, operation and renewable energy optimization.

A comprehensive understanding of wind turbine wake characteristics is vital, particularly in the context of expanding large offshore wind farms. Existing wake measurement techniques provide only spatially sparse wake measurement data, limiting their utility in precise wind turbine design and control. This paper introduces a data-driven approach that combines proper orthogonal decomposition (POD) with machine learning (ML) techniques, designing a Reduced Order Modeling-based Wake Flow Estimation (ROM-WFE) framework. This framework establishes a nonlinear mapping between sensor measurements and low-dimensional POD coefficients. Two distinct sensor placements, wall-mounted and wake-mounted, are investigated for real measurement scenarios. The results highlight the effectiveness of the proposed wake flow estimation method in reconstructing a complete flow field from exceptionally sparse sensor data, with both wall-mounted and wake-mounted strategies, exhibiting promising results with maximum relative errors of 6.37% and 4.51%, respectively. From the reliability assessments considering various configurations of POD modes and sensor numbers, the ROM-WFE framework demonstrates its capability to estimate wake flow effectively, offering a cost-effective tool for practical applications. Furthermore, the framework maintains accuracy even with high-noise and low-frequency data, demonstrating robustness and generalization. This method significantly contributes to wind turbine wake prediction controller design, promising accurate and robust wake flow field estimation, potentially revolutionizing active wake control and enhancing wind farm operational efficiency.

In order to reduce the upsprung weight, cardan shaft is used in Chinese high-speed vehicles CRH5 to transmit torque from the motor to the wheel pair. The cardan shaft becomes misaligned due to worn wear pads in the cardan joint and shifting of the cross shafts. The misalignment results in inertia force and affects the vibration of the wheel pair and the carriage. A dynamic model of the vehicle including cardan shafts is proposed in this study to analyze the effects of the misalignment on dynamic performance of the vehicle. A route is designed based on European Railway Standard EN14316 to perform the simulation. Effects of the misalignment on wheel-rail contact force and acceleration of the carriage are investigated through simulations. Dynamic performances including driving safety and riding comfort of the vehicle under different shifting lengths of cross shafts are studied through the calculation of the derailment coefficient and the riding comfort index. Transmission efficiency of the cardan shaft with respect to different shifting lengths of the cross shafts under different speeds of the vehicle are studied. Threshold of shifting length of the cross shaft is determined in this study to avoid reduction of riding quality of the vehicle based on the standard of riding comfort index of vehicles, and the spectral amplitude of acceleration of the motor with respect to rotating frequency of the cardan shaft are calculated for maintenance of the cardan shaft.

The paper proposes a novel cost-effective framework that combines deep learning convolutional neural network (CNN) and blade element momentum (BEM) models for optimizing the performance of three-dimensional (3D) horizontal axis tidal turbines (HATTs). The framework employs signed distance function (SDF) to reconstruct the three-dimensional blade geometry, utilizes CNN to identify the hydrodynamic performance of each blade section, and ultimately predicts the performance of HATT using BEM. On top of the new CNN-BEM model, the rotor blade geometrical optimization by multi-objective non-dominated sorting genetic algorithm (NSGA-II) is carried out to obtain a better trade-off solution with the maximal power coefficient of turbine and minimal hydrodynamic load exerted on the blades. The results show that the CNN-BEM model has good agreement with experimental data and reduces prediction time by 46.7% compared to the conventional Xfoil-BEM model, while reducing general optimization time by 20.1%. The new model's cost-efficiency allows for a better trade-off solution with reduced hydrodynamic load while maintaining the power coefficient. Thus, the proposed model has the capability to deliver both accurate and fast prediction and optimization of HATT performance, making it a valuable tool for guiding the design of tidal turbines.

Obtaining reliable flow data is essential for the fluid mechanics analysis and control, and various measurement techniques have been proposed to achieve this goal. However, imperfect data can occur in experimental scenarios, particularly in the particle image velocimetry technique, resulting in insufficient flow data for accurate analysis. To address this issue, a novel machine learning-based multi-scale autoencoder (MS-AE) framework is proposed to reconstruct missing flow fields from imperfect turbulent flows. The framework includes two missing flow reconstruction strategies: complementary flow reconstruction and non-complementary flow reconstruction. The former requires two independent measurements of complementary paired flow fields, posing challenges for real-world implementation, whereas the latter requires only a single measurement, offering greater flexibility. A benchmark case study of channel flow with ordinary missing configuration is used to assess the performance of the MS-AE framework. The results demonstrate that the MS-AE framework outperforms the traditional fused proper orthogonal decomposition method in reconstructing missing turbulent flow, irrespective of the availability of complementary paired faulty flow fields. Furthermore, the robustness of the proposed MS-AE approach is assessed by exploring its sensitivity to various factors, such as latent size, overlap proportion, reconstruction efficiency, and suitability for multiscale turbulent flow structures. The new method has the potential to contribute to more effective flow control in the future, thanks to its characteristic that eliminates the requirement for complementary flow fields.

The reconstruction of accurate and robust unsteady flow fields from sparse and noisy data in real-life engineering tasks is challenging, particularly when sensors are randomly placed. To address this challenge, a novel Autoencoder State Estimation (AE-SE) framework is introduced in this paper. The framework integrates sensor measurements into a machine learning-based reduced-order model (ROM) by leveraging the low-dimensional representation of flow fields. The proposed approach is tested on two direct numerical simulation benchmark examples, namely, circular and square cylinders and wake flow fields at Re = 100. The results demonstrate satisfactory performance in terms of accuracy and reconstruction efficiency. It achieves the same accuracy as traditional methods while improving reconstruction efficiency by 70%. Moreover, it preserves essential physical properties and flow characteristics even in the noisy data, indicating its practical applicability and robustness. Experimental data validation confirms a relative error below 5% even at a noise level of 12%. The flexibility of the model is further evaluated by testing it with a trained ROM under varying Reynolds numbers and benchmark cases, demonstrating its ability to accurately estimate and recognize previously unseen flow fields with appropriate training datasets. Overall, the proposed AE-SE flow reconstruction method efficiently and flexibly leverages ROM for the low-dimensional representation of complex flow fields from sparse measurements. This approach contributes significantly to the development of downstream applications such as design optimization and optimal control.

Complete and clear global wind turbine wake data is very important for the study of wind turbine wake characteristics in increasingly large offshore wind farms. Existing wake measurement techniques can only obtain local high-resolution (HR) wake flow field, or sacrifice accuracy to obtain larger measurement area, which is insufficient for accurate modeling of wake effect. To overcome this challenge, this paper proposes a novel super-resolution (SR) reconstruction approach that can reconstruct the global HR wake flow field from low-resolution (LR) wake flow field measurement data effectively. The proposed approach utilizes a deep learning framework called down-sampled skip-connection and multi-scale network. The performance of the SR approach is evaluated by enhancing the resolution of the wake flow field at different scale factors, and its potential application is demonstrated by assessing the prediction accuracy of three typical wake models. The results indicate that the resolution of the global wind turbine wake can be improved by 16 times using the SR model, and the reconstructed global SR wake flow fields are consistent with the ground truth in terms of both the spatial distribution and the temporal variation. By comparing the prediction results of three different wake models with the LR or SR wake data, it is shown that the SR flow reconstruction method can be applied to more accurately evaluate the wake model prediction performance, which has the potential to improve wake models. Overall, this study presents an innovative solution to the problem of incomplete and inaccurate wake flow measurement in the wind energy industry, which could reduce the workload of experimental measurements and the cost burden of accurate measuring equipment for engineering applications.

A tidal turbine can benefit from exquisitely designed morphing blades with a flexible trailing edge by mitigating up to 90% of the load fluctuation in harsh ocean environments, which reduces the overall cost of tidal energy. However, existing fluid–structure interaction (FSI) methods of resolving flow-induced deformation of the blades is computationally expensive, which poses an important challenge to effective morphing blade design. This paper presents a novel static FSI tool based on deep learning to cost-efficiently analyze the fluid–structure coupling of a hydrofoil. Specifically, adopting a convolutional neural network (CNN) to predict the fluid force and finite element method (FEM) to solve the solid structure response, a new CNN-FEM framework with an iterative scheme for solving the FSI problem is developed to achieve equilibrium between the fluid and structural forces. The new framework is used to predict the elastic deformation of the flexible blade section of the hydrofoil to demonstrate its effectiveness in the FSI evaluation. Comparison of the results to those produced by commercially developed software (i.e., Ansys Workbench) shows that this method yields extremely close prediction results of average equivalent stress and an accuracy of more than 92%. Moreover, it is 100 times more computationally efficient than the commercial Ansys Workbench software, requiring less than 3s for one-way FSI calculation. Taking advantage of this cost-effectiveness, the CNN-FEM can be used to achieve the accurate prediction of the deformation characteristics of the flexible hydrofoil under various flow scenarios that lay a foundation for advanced morphing blade design in the future.

In this paper, the effectiveness of three machine/deep learning algorithms, namely, the artificial neural network (ANN), convolutional neural network (CNN) and U-shape neural network (Unet), in constructing wind turbine wake modeling is investigated. In order to enhance the performance of different neural networks, the spatial-segmentation technique for wake flow field is adopted which aims to divide the original wake field configuration (4D x 50D, D is the rotor diameter) into several small pieces (each with 4D x 6.25D). This is followed by separately training the subdivided small piece of wake flow fields and the resultant sub-models are consolidated to predict the whole wake flow field. Both wake velocity field and turbulence intensity field are predicted by the wake model to facilitate its applications to alleviate both wind turbine power losses and fatigue loads caused by wake interactions. Through comparative study, it is found that by using the spatial-segmentation technique it can significantly reduce the prediction error of the wake velocity but not for the prediction of turbulence intensity. Among the three selected network structures, ANN has the best prediction performance yielding the wake model with the maximum error of 11.6 % near to the rotor place, while for other regions it is generally below 8 %. By dividing the wake flow field into pieces, the maximum error located right behind the rotor reduces to 7.2 % with others less than 6 %. Through further repetitive training analysis, it proves a better and robust wake model can be achieved by ANN with the spatial segmentation. In comparison, the prediction error of turbulence intensity field is higher, but still fairly accurate for the far wake prediction with the error less than 5 %.

Crumb rubber incorporation is widely deemed to deteriorate the compressive strength of concrete. One of the dominant reasons for this strength reduction is known as the inferior bonding or weak interfacial transition zones (ITZ) between the crumb rubber and hardened cement paste. While Styrene-butadiene (SBR)latex is being used as a bonding agent in concrete manufacturing, the SBR latex usage holds the potential to compensate for the strength reduction from crumb rubber incorporation. This study focuses on evaluating the sole and combined effect of crumb rubber and SBR latex on the compressive strength, one optimum combination of latex modified rubberised mix (LMCRC) that had achieved 55.5 MPa of 28 days’characteristic strength was chosen to compare its impact resistance and stress-strain response to a plain concrete (PC) with similar characteristic strength. Experimental results showed both crumb rubber and SBR latex incorporation induced a compressive strength reduction in the concrete. The optimum latex modified rubberised mix with w/c of 0.32, crumb rubber replacement of 20kg/m3, and 3% latex additives had outperformed the control mix with w/c ratio of 0.38 by 66.7% and 293% in the 400mm span impact test and 200mm span impact test, respectively. Besides, the latex modified rubberised mix showed higher Poisson’s ratio, and higher compressive strain which indicates more ductile behaviour as compared to the plain concrete.

Convolutional Neural Network (CNN) is a commonly used deep learning algorithm due to its excellent capability in identification of structural features and parameter predictions in many domains. In addition, it has incomparable advantages of high analysis efficiency and generalization performance. However, it has been questioned in the research community on whether CNN method can be applied to effectively predict hydrofoil performance for hydraulic machinery design. To this end, this paper demonstrates a novel optimization platform using CNN for hydrofoil performance prediction, which can effectively and accurately obtain the optimized hydrofoils results in aid of the structural design of tidal turbine. The prediction model uses signed distance function (SDF) to graphically represent the shape of the hydrofoil which is subsequently imported into CNN as the network input. Three different hydrofoil performance properties including the lift coefficient, drag coefficient and pressure coefficient of surface are used as output to train the neural network. In order to guarantee the accuracy of the forecasting model, Computational Fluid Dynamics (CFD) method characterized by high precision is applied to generate the dataset for neural network training. The results show that it can accurately predict the hydrodynamic parameters at a lower angle of attack with extremely short period of time. On top of the established hydrofoil performance prediction model, the Pareto curve of the optimized hydrofoils is obtained and applied to the design of 3D horizontal axis tidal turbine (HATT) blades. It proves that the optimization platform is effective and versatile in a manner that achieves both accurate and rapid prediction/optimization of the hydrofoil, which greatly facilitates to apply it for the tidal turbine rotor design.

The existing decentralized wind farm control incorporating the wind turbine wake interaction has almost all concentrated on the condition of fixed wind speed/direction without considering the variability of wind in nature. Meanwhile, most of the current wake models cannot meet the requirement for wind turbine control optimization research with the high demand of wake calculation speed and accuracy. In this paper, a novel decentralized control strategy, named the wind-interval-based (WIB) control which adopts the uniform operation among the same interval of variable wind speeds/directions, is proposed for the control optimization study of in-line two scaling wind turbines for demonstration. To prove the effectiveness of the new control mechanism, the ideal instantaneous control is introduced for the comparative study. At the same time, a wake model incorporating the two directly controllable parameters (i.e., the tip speed ratio λ and pitch angle γ) is established based on artificial neural network (ANN). The comparative results show that the total power output applying the instantaneous control and the new WIB control mechanisms are increased by 0.1%–4.1% and 0.45%–3.9% depending on the tested wind scenarios, respectively. By comparing the optimized power output with the two controls, it is found that the error between them is generally lower than 3%, while the proposed WIB control reduces the operational difficulty to a large extent facilitating its application to the real wind turbine operation in reality. In summary, this paper shows that the new proposed WIB control not only reduces the difficulties of the wind turbine control mechanism, but maintains the control effectiveness by achieving a comparable total power output with respect to the traditional instantaneous control, which is of great significance to the wind farm developer.