该文研究了对风电机组进行载荷预测的问题,主要从两个方面展开：SCADA数据增强与使用多级特征提取框架做载荷预测。首先采用生成对抗网络（WGAN-GP）进行数据增强。在载荷预测方面,不同于传统的Transformer模型应用于文本数据,该文使用风电机组运行时的结构化数据,且为提高特征提取能力,提出一种多级特征提取器进行特征提取。最后使用改进的Transformer模型和DNN、ResNet等模型的结果进行对比,发现多级特征提取模型对于与目标特征相关性较高的数据有较好的预测效果,同时对于相关性较低的数据也具有较好的非线性提取能力。
Abstract
In this paper, load prediction for wind turbines is studied from two aspects： SCADA data enhancement and multi-stage feature extraction framework for load prediction. Firstly, Generative adversarial network （WGAN-GP） is used for data enhancement. In terms of load prediction, different from the traditional Transformer model applied to text data, this paper uses the structured data of wind turbine operation, and in order to improve feature extraction capability, a multistage feature extractor is proposed for feature extraction. Finally, the improved Transformer model is compared with the results of DNN, ResNet and other models, and it is found that the multistage feature extraction model has better prediction effect for data with high correlation with target features, and has better nonlinear extraction ability for data with low correlation.
关键词
风电机组 /
Transformer /
特征提取 /
生成对抗网络 /
载荷预测 /
数据增强
Key words
wind turbines /
Transformer /
feature extraction /
generative adversarial network /
load prediction /
data enhancement
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 付德义, 张晓东, 王瑞明, 等. 特定场址条件下风电机组载荷适应性评估[J]. 太阳能学报, 2021, 42(6): 425-431.
FU D Y, ZHANG X D, WANG R M, et al.Wind turbine load adaptability assessment under specific site conditions[J]. Acta energiae solaris sinica, 2021, 42(6): 425-431.
[2] OBDAM T S, RADEMAKERS L W M M, BRAAM H. Flight leader concept for wind farm load counting and performance assessment[R].ECN-M-09-054, 2009.
[3] 董礼, 廖明夫, KUEHN M, 等. 风力机等效载荷的评估[J]. 太阳能学报, 2008, 29(12): 1456-1459.
DONG L, LIAO M F, KUEHN M, et al.Estimation of equivalent load for a horizontal axis wind turbine[J]. Acta energiae solaris sinica, 2008, 29(12): 1456-1459.
[4] 许扬, 蔡安民, 张林伟, 等. 基于BP神经网络和多因素权重法的风电机组载荷预测和分析[J]. 热力发电, 2022, 51(8): 42-49.
XU Y, CAI A M, ZHANG L W, et al.Load prediction and analysis of wind turbine based on BP neural network and multi-factor weight method[J]. Thermal power generation, 2022, 51(8): 42-49.
[5] 薛磊, 王灵梅, 孟恩隆, 等. 基于SCADA数据和改进BP神经网络的塔筒应力预测[J]. 噪声与振动控制, 2021, 41(1): 95-102.
XUE L, WANG L M, MENG E L, et al.Stress prediction of wind turbine tower drums based on SCADA data and improved BP neural network[J]. Noise and vibration control, 2021, 41(1): 95-102.
[6] 周士栋, 薛扬, 马晓晶, 等. 基于SCADA数据的风电机组关键载荷预测[J]. 农业工程学报, 2018, 34(2): 219-225.
ZHOU SD, XUE Y, MA XJ, et al.Prediction of wind turbine key load based on SCADA data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(2): 219-225.
[7] 周庆梅, 温钊, 张会阳, 等. 基于数字孪生的风电机组叶根载荷预测[C]//第四届水下无人系统技术高峰论坛. 西安, 中国, 2021: 156-160.
ZHOU Q M, WEN Z, ZHANG H Y et al. Blade root load prediction of wind turbine based on digital twin[C]//The Fourth Underwater Unmanned System Technology Summit Forum. Xi'an, China, 2021: 156-160.
[8] 廖圣瑄, 马晓明, 韩中合, 等. 基于组合模型的风电机组轮毂载荷预测方法研究[J]. 中国测试, 2021, 47(5): 39-45.
LIAO S X, MA X M, HAN Z H, et al.Research on prediction method of wheel hub load of wind turbine based on combined model[J]. China measurement & test, 2021, 47(5): 39-45.
[9] IEC 61400-13:2015, Wind turbines - Part 13: Design requirements for noise measurement and prediction[S].
[10] 滕伟, 丁显, 史秉帅, 等. 基于WGAN-GP的风电机组传动链故障诊断[J]. 电力系统自动化, 2021, 45(22): 167-173.
TENG W, DING X, SHI B S, et al.Fault diagnosis of wind turbine drivetrain based on Wasserstein generative adversarial network-gradient penalty[J]. Automation of electric power systems, 2021, 45(22): 167-173.
[11] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[12] ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein GAN[DB/OL]. (2017-12-06)[]https://arxiv.org/abs/1701.07875.
[13] ARJOVSKY M, BOTTOU L. Towards principled methods for training generative adversarial networks[DB/OL]. (2017-01-17)[]https://arxiv.org/abs/1701.04862.
[14] VASWANI A, SHAZEER N, PARMAR N,et al.Attention Is All You Need[J].arXiv, 2017.DOI:10.48550/arXiv.1706.03762.
[15] HAN Z .Dyna: A method of momentum for stochastic optimization[J]. 2018.DOI:10.48550/arXiv.1805.04933.
[16] ZABINSKY Z B.Stochastic methods for practical global optimization[J]. Journal of Global Optimization, 1998, 13: 433-444.
[17] HE K M, ZHANG X Y, REN S Q, et al.Identity mappings in deep residual networks[M]//LEIBE B, MATAS J, SEBE N, et al, eds. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2016: 630-645.
PDF(23032 KB)
