基于WD-LSTM的风电机组叶片结冰状态评测

刘杰; 杨娜; 谭玉涛; 孙兴伟

doi:10.19912/j.0254-0096.tynxb.2021-0505

PDF(3382 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (8) : 399-408. DOI: 10.19912/j.0254-0096.tynxb.2021-0505

基于WD-LSTM的风电机组叶片结冰状态评测

刘杰, 杨娜, 谭玉涛, 孙兴伟

作者信息 +

ASSESSMENT OF ICING STATE OF WIND TURBINE BLADES BASED ON WD-LSTM

Liu Jie, Yang Na, Tan Yutao, Sun Xingwei

Author information +

文章历史 +

摘要

为有效识别叶片结冰状态,尽早采取除冰措施,提出基于小波去噪的长短期记忆神经网络（WD-LSTM）的评测方法。首先基于过采样与欠采样相结合的方法解决SCADA系统数据中的类别不平衡问题,通过对叶片结冰相关的26项指标进行分析,并从结冰机理和数据探索的角度筛选特征量,小波去噪处理后建立WD-LSTM模型,进一步完成模型的训练和测试。分别以15号和21号风电机组为例进行模型验证,通过与LSTM、概率神经网络（PNN）模型和BP神经网络模型进行对比。结果表明,WD-LSTM方法在风电机组叶片结冰评测中的准确率可达98%,优于其他方法。

Abstract

An assessment method based on wavelet denoising long short term memory（WD-LSTM） was proposed in the paper to effectively identify the icing state of blades and take deicing measures as soon as possible. The problem of category imbalance in the SCADA system data was solved based on the combination of over-sampling and under-sampling. The 26 indicators related to blade icing were analyzed, and characteristic quantities were selected from the perspective of icing mechanism and data exploration. The WD-LSTM model was established after wavelet denoising to further complete the training and testing of the model. The No. 15 wind turbine and No. 21 wind turbine were taken as examples respectively for model verification compared with LSTM, Probabilistic Neural Network （PNN） model and BP neural network model. The results show that the accuracy rate of the WD-LSTM method reaches 98% in the assessment process of the wind turbine blades, which is better than other methods. It provides new ideas for the prediction of blade icing.

导出引用

刘杰, 杨娜, 谭玉涛, 孙兴伟. 基于WD-LSTM的风电机组叶片结冰状态评测[J]. 太阳能学报. 2022, 43(8): 399-408 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0505

Liu Jie, Yang Na, Tan Yutao, Sun Xingwei. ASSESSMENT OF ICING STATE OF WIND TURBINE BLADES BASED ON WD-LSTM[J]. Acta Energiae Solaris Sinica. 2022, 43(8): 399-408 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0505

中图分类号： TM315

参考文献

[1] NEIL N D, PIERRE P, ANDREA N H, et al.Identifying and characterizing the impact of turbine icing on wind farm power generation[J]. Wind energy, 2016, 19(8): 1503-1518.
[2] 孙少华, 徐洪雷, 符鹏程, 等. 叶片覆冰对风电机组的影响[J]. 风能, 2014(9): 100-103.
SUN S H, XU H L, FU P C, et al.The effect of blade icing on wind turbines[J]. Wind energy, 2014(9): 100-103.
[3] LIANG Y, FANG R M.An online wind turbine condition assessment method based on SCADA and support vector regression[J]. Automation of electric power systems, 2013, 37: 7-12, 31.
[4] ZHANG Z Y, WANG K S.Wind turbine fault detection based on SCADA data analysis using ANN[J]. Advances in manufacturing, 2014(1): 70-78.
[5] 谭海辉, 李录平, 靳攀科, 等. 风力机叶片超声波除冰理论与方法[J]. 中国电机工程学报, 2010, 30(35): 112-117.
TAN H H, LI L P, JIN P K, et al.Ultrasonic de-icing theory and method for wind turbine blades[J]. Proceedings of the CSEE, 2010, 30(35): 112-117.
[6] OUYANG T H, KUSIAK A, HE Y S.Modeling wind turbine power curve: a data partitioning and mining approach[J]. Renewable energy, 2017, 102: 1-8.
[7] 李宁波, 闫涛, 李乃鹏, 等. 基于SCADA数据的风机叶片结冰检测方法[J]. 发电技术, 2018, 39(1): 59-62.
LI N B, YAN T, LI N P, et al.Ice detection method by using SCADA data on wind turbine blades[J]. Power generation technology, 2018, 39(1): 59-62.
[8] 叶春霖, 邱颖宁, 冯延晖. 基于数据挖掘的风电机组叶片结冰故障诊断[J]. 噪声与振动控制, 2018, 38(S2): 285-289.
YE C L, QIU Y N, FENG Y J.Faults diagnosis of wind turbine blade icing based on data mining[J]. Noise and vibration control, 2018, 38(S2): 285-289.
[9] NEIL N D, OYUIND B, ANDREA H, et al.Ice detection on wind turbines using the observed power curve[J]. Wind energy, 2016, 19(6): 999-1010.
[10] 风机运行脱敏数数据[EB/OL].[2017-07-15][2021-05-10].http://www.industrial-bigdata.com.
Desensitization data of fan operation[EB/OL]. [2017-07-15][2021-05-10].http://www.industrial-bigdata.com.
[11] 高欣, 纪维佳, 赵兵, 等. 不平衡数据集下基于CVAE-CNN模型的智能电表故障多分类方法[J]. 电网技术, 2021, 3(2): 1-9.
GAO X, JI W J, ZHAO B, et al.Multi-classification method of smart meter fault types based on CVAE-CNN model under imbalanced dataset[J]. Power system technology, 2021, 3(2): 1-9.
[12] BUSTILLO A, RODRIGUEZ J J.Online breakage detection of multitooth tools using classifier ensembles for imbalanced data[J]. International journal of systems science, 2014, 45(12): 2590-2602.
[13] 赵小强,刘梦依. 基于不平衡数据集的主动学习分类算法[J]. 控制工程, 2019, 26(2): 314-319.
ZHAO X Q, LIU M Y.An active learning algorithm based on imbalanced datasets[J]. Control engineering of China, 2019, 26(2): 314-319.
[14] 黎楚阳, 朱孟兆, 焦健, 等. 基于大数据分析的风机叶片结冰故障诊断[J]. 自动化与仪器仪表, 2020(3): 12-16.
LI C Y, ZHU M Z, JIAO J, et al.Fault diagnosis of wind turbine blade ice based on large data analysis[J]. Automation & instrumentation, 2020(3): 12-16.
[15] MAKKONEN L.Models for the growth of rime, glaze, icicles and wet snow on structures[J]. Philosophical transactions mathematical physical & engineering sciences, 2000, 358(1776): 2913-2939.
[16] WONG P K, YANG Z X, VONG C M, et al.Real-time fault diagnosis for gas turbine generator systems using extreme learning machine[J]. Neurocomputing, 2014, 128: 249-257.
[17] 刘勇, 贺生国, 杨清勇, 等. 一种新的摆度信号去噪方法及其应用[J]. 振动·测试与诊断, 2019, 39(5): 1053-1060, 1136.
LIU Y, HE S G, YANG Q Y, et al.A new method of de-noising of pendulum signal and its application[J]. Journal of vibration, measurement & diagnosis, 2019, 39(5): 1053-1060,1136.
[18] 孟乾泰, 张玉登, 王玉磊, 等. 基于小波阈值去噪的煤粉静电信号参数的研究[J]. 国外电子测量技术, 2020, 39(5): 138-142.
MENG Q T, ZHANG Y D, WANG Y L, et al.Study on the electrostatic signal parameters of pulverized coal based on wavelet threshold denoising[J]. Foreign electronic measurement technology, 2020, 39(5): 138-142.
[19] 陶恺, 陶煌. 一种基于深度学习的文本分类模型[J]. 太原师范学院学报(自然科学版), 2020, 19(4): 45-51.
TAO K, TAO H.A text classification model based on deep-learning[J]. Journal of Taiyuan Normal University(natural science edition), 2020, 19(4): 45-51.
[20] 韩亮, 黄谦, 蒲秀娟, 等. 使用深度长短期记忆网络的心冲击伪迹抑制方法[J]. 仪器仪表学报, 2021, 41(11): 198-206.
HAN L, HUANG Q, PU X J, et al.A ballistocardiogram artifact removal method utilizing deep-LSTM network[J]. Chinese journal of scientific instrument, 2021, 41(11): 198-206.
[21] SANTOS P, MAUDES J, BUSTILLO A.Identifying maximum imbalance in datasets for fault diagnosis of gearboxes[J]. Journal of intelligent manufacturing, 2018, 29(2): 333-351.
[22] 郑若楠. 数据驱动的风电机组叶片结冰在线检测方法[J]. 分布式能源, 2019, 4(1): 1-7.
ZHENG R N.On-line detection method of ice on wind turbine blade driven by data[J]. Distributed energy, 2019, 4(1): 1-7.
[23] YAN K, LI W, JI Z W, et al.A hybrid LSTM neural network for energy consumption forecasting of individual households[J]. IEEE access, 2019, 7: 157633-157642.