融合时空特征与孪生网络的风机叶片结冰预测

Prediction of ice accretion on wind turbine blades using spatiotemporal features and siamese networks

摘要:

为实现对风机叶片结冰状态的精准预测,保障风力发电系统的安全与稳定运行,针对风机叶片结冰预测中存在的特征提取不足、多维传感器分布信息不明确,以及小样本学习中类别不平衡的问题,本文提出一种基于残差图注意力与时空双向序列孪生网络（residual graph attention network bidirectional LSTM siamese network,ResGAT-BiLSTM-SN）的风机叶片结冰预测方法。首先,通过数据清洗、滑动窗口采样和特征工程,对监控与数据采集系统（supervisory control and data acquisition,SCADA）的数据进行处理,构建适用于不同小样本学习任务的风机叶片结冰数据集。其次,基于19个关键变量,通过互信息（mutual information,MI）和权重矩阵构建一个非完全连接的无向图,用以反映传感器数据的空间分布与相关性。最后,结合图注意力网络（graphical attention network,GAT）和双向长短时记忆网络（bidirectional long short-term memory networks,BiLSTM）对SCADA数据进行时空特征提取,构建ResGAT-BiLSTM-SN模型对所构造的风机叶片结冰数据集进行未来24 h的结冰预测。选用2017年工业大数据创新竞赛平台中15号和21号风力机数据进行仿真,验证实验结果表明,在3种小样本学习场景下,ResGAT-BiLSTM-SN模型的F1分数均达到0.9以上,显著优于其他对比模型。相较于GAT-BiLSTM-SN模型,ResGAT-BiLSTM-SN模型在预测性能上有明显提升,验证了本文所提预测模型的有效性与优越性。

Abstract:

The accurate prediction of wind turbine blade icing is essential for the safe and stable operation of wind power systems. To address the challenges of insufficient feature extraction, unclear distribution of multi-dimensional sensors, and class imbalance in few-shot learning scenarios, this paper proposes a prediction method based on a residual graph attention network-bidirectional LSTM-siamese network (ResGAT-BiLSTM-SN). First, the supervisory control and data acquisition (SCADA) data is processed through data cleaning, sliding-window sampling, and feature engineering, resulting in a blade-icing dataset suitable for various few-shot learning tasks. Second, based on 19 key variables, a non-fully connected undirected graph is built using mutual information (MI) and a weight matrix to capture the spatial distribution and correlations among sensor data. By integrating the graph Attention network (GAT) and the bidirectional long short-term memory network (BiLSTM) to extract spatiotemporal features, the ResGAT-BiLSTM-SN model is developed to perform 24-hour-ahead icing prediction on the constructed dataset. Simulation experiments are conducted using the data from turbines No.15 and No.21 provided by the 2017 Industrial Big Data Innovation Competition platform. The experimental results show that the ResGAT-BiLSTM-SN model achieves F1 scores above 0.9 across three few-shot learning scenarios, significantly outperforming other baseline models. Compared to the GAT-BiLSTM-SN model, the proposed model demonstrates clear improvements in predictive performance, validating its effectiveness and superiority.