Dynamic multi-turbines spatiotemporal correlation model enabled digital twin technology for real-time wind speed prediction

Li, Yang; Shen, Xiaojun; Zhou, Chongcheng

doi:10.1016/j.renene.2022.12.121

Cited by 8 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this means that the estimation of normalized maxima might not be fully converged, meaningful comparisons and results relative to the effect of blade‐pitch faults and shutdown can still be achieved because all fault cases use the same time histories of wind and wave loads for each load case considered. The use of single seed comparisons, that is, comparisons from identical dynamic states, is also common practice in the relevant literature, particularly within concept verification and parametric analysis 53–59 . Future work will perform a detailed structural design of the two‐rotor floating wind system, where full coverage of the stochastic variability and quantification of converged maxima will be included.…”

Section: Methodsmentioning

confidence: 99%

“…The use of single seed comparisons, that is, comparisons from identical dynamic states, is also common practice in the relevant literature, particularly within concept verification and parametric analysis. [53][54][55][56][57][58][59] Future work will perform a detailed structural design of the two-rotor floating wind system, where full coverage of the stochastic variability and quantification of converged maxima will be included. 13 In the table, LC stands for the load case prefix, U W is the mean wind speed at the hub height, H S is the significant wave height, T P is the wave period, t f is the time at which the fault occurs, and t d is the time delay from the occurrence of fault to the shutdown initiation.…”

Section: Numerical Simulationmentioning

confidence: 99%

See 1 more Smart Citation

Load response of a two‐rotor floating wind turbine undergoing blade‐pitch system faults

2023

View full text Add to dashboard Cite

Multi‐rotor floating wind turbines are among the innovative technologies proposed in the last decade in the effort to reduce the cost of wind energy. These systems are able to offer advantages in terms of smaller blades deployed offshore, cheaper operations, fewer installations, and sharing of the floating platform. As the blade‐pitch actuation system is prone to failures, the assessment of the associated load scenarios is commonly required. Load assessment of blade‐pitch fault scenarios has only been performed for single‐rotor solutions. In this work, we address the effect of blade‐pitch system faults and emergency shutdown on the dynamics and loads of a two‐rotor floating wind turbine. The concept considered employs two NREL 5‐MW baseline wind turbines and the OO‐Star semi‐submersible platform. The blade‐pitch faults investigated are blade blockage and runaway, that is, the seizure at a given pitch angle and the uncontrolled actuation of one of the blades, respectively. Blade‐pitch faults lead to a significant increase in the structural loads of the system, especially for runaway fault conditions. Emergency shutdown significantly excites the platform pitch motion, the tower‐bottom bending moment, and tower torsional loads, while suppressing the faulty blade flapwise bending moment after a short peak. Shutdown delay between rotors increases significantly the maxima of the torsional loads acting on the tower. Comparison of blade loads with data from single‐rotor spar‐type study show great similarity, highlighting that the faulty blade loads are not affected by (1) the type of platform used and (2) the multi‐rotor deployment.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Numerical Simulationmentioning

confidence: 99%

Load response of a two‐rotor floating wind turbine undergoing blade‐pitch system faults

2023

View full text Add to dashboard Cite

show abstract

“…Multi-wind speed prediction is based on the distribution structure and historical information of a certain wind farm to calculate the future wind speed [20]. The input-output relationship is shown in Figure 1.…”

Section: Multi-wind Turbine Wind Speed Prediction Problem Descriptionmentioning

confidence: 99%

Multi-Wind Turbine Wind Speed Prediction Based on Weighted Diffusion Graph Convolution and Gated Attention Network

Qiao,

Chen,

2024

Energies

View full text Add to dashboard Cite

The complex environmental impact makes it difficult to predict wind speed with high precision for multiple wind turbines. Most existing research methods model the temporal dependence of wind speeds, ignoring the spatial correlation between wind turbines. In this paper, we propose a multi-wind turbine wind speed prediction model based on Weighted Diffusion Graph Convolution and Gated Attention Network (WDGCGAN). To address the strong nonlinear correlation problem among multiple wind turbines, we use the maximal information coefficient (MIC) method to calculate the correlation weights between wind turbines and construct a weighted graph for multiple wind turbines. Next, by applying Diffusion Graph Convolution (DGC) transformation to the weight matrix of the weighted graph, we obtain the spatial graph diffusion matrix of the wind farm to aggregate the high-order neighborhood information of the graph nodes. Finally, by combining the DGC with the gated attention recurrent unit (GAU), we establish a spatio-temporal model for multi-turbine wind speed prediction. Experiments on the wind farm data in Massachusetts show that the proposed method can effectively aggregate the spatio-temporal information of wind turbine nodes and improve the prediction accuracy of multiple wind speeds. In the 1h prediction task, the average RMSE of the proposed model is 28% and 33.1% lower than that of the Long Short-Term Memory Network (LSTM) and Convolutional Neural Network (CNN), respectively.

show abstract

A transferable diagnosis method with incipient fault detection for a digital twin of wind turbine

Hu,

Jiao,

Liu

et al. 2024

Digital Engineering

View full text Add to dashboard Cite

Dynamic multi-turbines spatiotemporal correlation model enabled digital twin technology for real-time wind speed prediction

Cited by 8 publications

References 31 publications

Load response of a two‐rotor floating wind turbine undergoing blade‐pitch system faults

Load response of a two‐rotor floating wind turbine undergoing blade‐pitch system faults

Multi-Wind Turbine Wind Speed Prediction Based on Weighted Diffusion Graph Convolution and Gated Attention Network

A transferable diagnosis method with incipient fault detection for a digital twin of wind turbine

Contact Info

Product

Resources

About