Wind Power Engineering (Japan)

Gearboxes represent a key feature of wind turbines, fulfilling the function of connecting and transmitting power. The analysis of gearbox health assessment has the capacity to predict the failure time of the wind turbine with both timeliness and accuracy, thus providing guidance for subsequent maintenance and repair. In this paper, a gearbox health assessment method based on an adversarial network is proposed. The transition from normal to fault conditions facilitates the early detection of faults. The residual between the original signal and the predicted signal is utilised to indicate whether the gearbox operating state is normal. The deviation from the normal data to the abnormal data is quantified through the deviation index and the technique of change. This is then converted into a probability value to obtain the health index of a single variable. The overall health index (HI) of the gearbox is composed of a single variable index. The experimental findings demonstrate the efficacy of the proposed method in conducting health assessments of wind turbine gearboxes, thereby substantiating its wide-ranging applicability.

<strong class="journal-contentHeaderColor">Abstract.</strong> Wind turbines are a key technology for producing clean energy, but the noise they generate can create environmental concerns. This study explores how serrated edges on turbine blades influence noise, structural safety, and energy output. A prototype wind turbine was equipped with serrated blades and tested at a field site in China. Measurements showed that the serrated design reduced aerodynamic noise by nearly four decibels. At the same time, computer simulations revealed that this design caused a small increase in structural loads and a slight decrease in annual electricity generation. The findings suggest that serrated blades can help reduce the noise impact of wind turbines, but they also highlight the need to carefully weigh the trade-offs between quieter operation, safety margins, and efficiency.

This paper presents a multi-fidelity validation for control surface modeling using FlightStream® on a fixed-wing Group 1 unmanned aerial vehicle, with the goal of advancing its use in control law development. Predictions from high-fidelity computational fluid dynamics (CFD) and experimental load cell measurements using a WindShape® multi-fan array wind generator are integrated in this study and serve as independent benchmarks for comparison to evaluate aileron deflection loads. Both full-model and strip theory approaches derived using FlightStream® are implemented and provide mid-fidelity aerodynamic predictions. CFD simulations and WindShape® testing data–obtained through static analysis and system identification–are compared to FlightStream® predictions to assess the accuracy and applicability of mid-fidelity aerodynamic analysis for use in control law development. The results showed promising agreement with CFD and WindShape data, validating both full-model and strip theory control surface derivative estimates. The FlightStream® strip theory model was then tested in a series of piloted commands to verify flight performance.

To enhance the accuracy of short-term wind power prediction, this paper proposes a novel two-stage forecasting framework that integrates Sequential Variational Mode Decomposition (SVMD), Bayesian Optimization (BO), and a CNN-BiLSTM-Attention model. In the first stage, the preprocessed wind power historical data is decomposed into several modal components via SVMD. These components serve as inputs to the CNN-BiLSTM-Attention model, whose hyperparameters—including the learning rate, number of hidden units, and regularization coefficient—are automatically tuned using the BO algorithm. The output of this stage is the initial power prediction. In the second stage, the prediction error sequence from the first stage is analyzed and similarly processed (decomposed and modeled) to generate an error compensation term. The final prediction is obtained by summing the initial power prediction and the predicted error compensation. Results show that compared with the CNN-BiLSTM-Attention model, the MAE, MAPE and RMSE values of the improved CNN-BiLSTM-Attention two-stage prediction model decreased by 85.7%, 75.2% and 77.3%, respectively, demonstrating the effectiveness of the two-stage short-term wind power prediction method of the improved CNN-BiLSTM-Attention model studied in this paper. 为了提升短期风电功率预测的准确性，本文研究了一种基于逐次变分模态分解（SVMD）方法、贝叶斯优化（BO）算法和CNN-BiLSTM-Attention模型结合的两阶段短期风电功率预测方法。该方法具体原理为：在第一阶段，利用SVMD方法对经过数据预处理后的风电功率数据进行分解，将得到的模态分量作为CNN-BiLSTM-Attention短期功率预测模型的输入，然后引入BO算法对预测模型的学习率、隐含层节点和正则化参数进行调优，利用训练好的模型进行预测，得到初始风电功率预测值；在第二阶段，采用预测模型对误差序列进行误差补偿预测，得到初始误差功率预测数据，将初始预测功率和误差预测功率求和得到最终的风电功率预测结果。结果表明：相比于CNN-BiLSTM-Attention模型，改进CNN-BiLSTM-Attention模型两阶段预测模型的MAE值、MAPE值和RMSE值分别下降了85.7%、75.2%和77.3%，表明了本文研究的改进CNN-BiLSTM-Attention模型的两阶段短期风电功率预测方法的有效性。