基于PCA-KNN融合算法的风力机变桨角度故障诊断方法

doi:10.11930/j.issn.1004-9649.202009083

中国电力 ›› 2021, Vol. 54 ›› Issue (11): 190-198.DOI: 10.11930/j.issn.1004-9649.202009083

基于PCA-KNN融合算法的风力机变桨角度故障诊断方法

陈茜¹, 李录平¹, 刘瑞¹, 杨波², 邓子豪¹, 李重桂¹

1. 长沙理工大学能源与动力工程学院,湖南长沙 410014;
2. 广州特种承压设备检测研究院,广东广州 510663

收稿日期:2020-09-09 修回日期:2020-12-10 出版日期:2021-11-05 发布日期:2021-11-16
作者简介:陈茜(1997-),女,硕士研究生,从事动力机械状态检测与故障诊断研究,E-mail:chenxichangsha@163.com;李录平(1963-),男,通信作者,教授,从事动力机械状态检测与故障诊断研究,E-mail:cs_liluping@163.com
基金资助:
广东省质量技术监督局科技项目(基于SCADA数据信息融合的风力机叶片覆冰诊断与预测技术，2018CT28)；湖南省研究生科研创新项目(基于SCADA系统的大功率风电机组故障诊断及报告自动生成技术，CX20190687)

Fault Diagnosis Method of Wind Turbine Pitch Angle Based on PCA-KNN Fusion Algorithm

CHEN Xi¹, LI Luping¹, LIU Rui¹, YANG Bo², DENG Zihao¹, LI Zhonggui¹

1. College of Energy and Power Engineering, Changsha University of Science and Technology, Changsha 410014, China;
2. Guangzhou Special Pressure Equipment Inspection and Research Institute, Guangzhou 510663, China

Received:2020-09-09 Revised:2020-12-10 Online:2021-11-05 Published:2021-11-16
Supported by:
This work is supported by Science and Technology Project of Bureau of Quality and Technical Supervision of Guangdong Province (Wind Turbine Blade Icing Diagnosis and Prediction Technology Based on SCADA Data Information Fusion, No.2018CT28) and Research & Innovation Project of Graduate Students in Hunan Province (High Power Wind Turbine Fault Diagnosis and Report Automatic Generation Technology Based on SCADA System, No.CX20190687)

摘要/Abstract

摘要： 针对风力机变桨系统变桨角度4种主要故障类型，基于机组SCADA数据分析，提出一种基于非参数核密度估计和Relief-F特征参数提取数据处理，以及PCA-KNN融合算法故障诊断的风力机变桨角度异常状态识别方法。首先，对风力机SCADA数据进行非参数核密度估计预处理，运用Relief-F算法提取变桨角度故障的7类（13个）特征参数；然后，通过PCA-KNN融合算法对变桨角度故障状态进行识别，结果表明：该方法能够准确识别变桨角度4种主要的故障类型。最后，将改进的PCA-KNN融合算法与常用的KNN算法、PCA-KNN算法和BP神经网络进行对比，结果表明：改进的PCA-KNN融合算法具有更为准确的识别率。

关键词: 风力机, 变桨角度故障, SCADA数据, 非参数核密度估计, Relief-F算法, PCA-KNN融合算法

Abstract: With regard to the four main fault types of the pitch angle of a wind turbine pitch system and the data analysis of the wind turbine, an identification method of abnormal pitch angles of a wind turbine is proposed, depending on nonparametric kernel density estimation and Relief-F based feature extraction for data processing and the PCA-KNN fusion algorithm for fault diagnosis. Firstly, the SCADA data is preprocessed according to nonparametric kernel density estimation, and seven categories (thirteen) of characteristic parameters of pitch angle faults are extracted by the Relief-F algorithm. Then, the PCA-KNN fusion algorithm is used to identify the state of pitch angle faults, and the results show that the proposed method can accurately identify the four main fault types of pitch angles. Finally, the improved PCA-KNN fusion algorithm is compared with the KNN algorithm, the PCA-KNN algorithm and BP neural network, which proves that the improved PCA-KNN fusion algorithm has a higher recognition rate.

Key words: wind turbine, pitch angle fault, SCADA data, nonparametric kernel density estimation, Relief-F algorithm, PCA-KNN fusion algorithm

陈茜, 李录平, 刘瑞, 杨波, 邓子豪, 李重桂. 基于PCA-KNN融合算法的风力机变桨角度故障诊断方法[J]. 中国电力, 2021, 54(11): 190-198.

CHEN Xi, LI Luping, LIU Rui, YANG Bo, DENG Zihao, LI Zhonggui. Fault Diagnosis Method of Wind Turbine Pitch Angle Based on PCA-KNN Fusion Algorithm[J]. Electric Power, 2021, 54(11): 190-198.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202009083

https://www.electricpower.com.cn/CN/Y2021/V54/I11/190

参考文献

[1] 樊帅, 唐群先. 基于AdaBoost-SAMME的风力发电机组变桨异常识别系统[J]. 电力系统保护与控制, 2020, 48(21): 31–40
FAN Shuai, TANG Qunxian. Wind turbine pitch anomaly recognition system based on AdaBoost-SAMME[J]. Power System Protection and Control, 2020, 48(21): 31–40
[2] 张镇, 关书强. 风电机组故障统计分析研究[J]. 风能, 2013(8): 68–71
ZHANG Zhen, GUAN Shuqiang. An analysis of wind turbine fault statistics[J]. Wind Energy, 2013(8): 68–71
[3] 陈茜, 李录平, 刘瑞, 等. 大功率风电机组变桨系统故障诊断方法与技术研究进展[J]. 电站系统工程, 2020, 36(1): 1–7
CHEN Xi, LI Luping, LIU Rui, et al. Review on research progress of fault diagnosis method and technology for variable pitch system of high power wind generating set[J]. Power System Engineering, 2020, 36(1): 1–7
[4] YANG W X, COURT R, JIANG J S. Wind turbine condition monitoring by the approach of SCADA data analysis[J]. Renewable Energy, 2013, 53: 365–376.
[5] 童超, 郭鹏. 基于特征选择和BP神经网络的风电机组故障分类监测研究[J]. 动力工程学报, 2014, 34(4): 313–317
TONG Chao, GUO Peng. Wind turbine fault classification based on BP neural network and feature selection algorithm[J]. Journal of Chinese Society of Power Engineering, 2014, 34(4): 313–317
[6] 李伟昌, 张磊. 基于风力发电系统的风电机组变桨距故障诊断[J]. 计算机仿真, 2015, 32(9): 147–151
LI Weichang, ZHANG Lei. Faults diagnosis of wind turbine pitch system based on ANFIS[J]. Computer Simulation, 2015, 32(9): 147–151
[7] YU D, CHEN Z M, XIAHOU K S, et al. A radically data-driven method for fault detection and diagnosis in wind turbines[J]. International Journal of Electrical Power & Energy Systems, 2018, 99: 577–584.
[8] 高峰, 邓星星, 刘强, 等. 大型风电机组电动变桨系统变桨角度故障诊断[J]. 太阳能学报, 2020, 41(5): 98–106
GAO Feng, DENG Xingxing, LIU Qiang, et al. Fault diagnosis of electric pitch system for mW wind turbine[J]. Acta Energiae Solaris Sinica, 2020, 41(5): 98–106
[9] 黄景林, 彭显刚, 简胜超, 等. 基于深度学习与不平衡样本集的输电线路故障分类[J]. 智慧电力, 2021, 49(2): 114–119
HUANG Jinglin, PENG Xiangang, JIAN Shengchao, et al. Transmission line fault classification based on deep learning and imbalanced sample set[J]. Smart Power, 2021, 49(2): 114–119
[10] 熊中杰, 邱颖宁, 冯延晖, 等. 基于机器学习的风电机组变桨系统故障研究[J]. 太阳能学报, 2020, 41(5): 85–90
XIONG Zhongjie, QIU Yingning, FENG Yanhui, et al. Fault analysis of wind turbine pitch system based on machine learning[J]. Acta Energiae Solaris Sinica, 2020, 41(5): 85–90
[11] 褚景春, 王飞, 汪杨, 等. 基于故障树和概率神经网络的风电机组故障诊断方法[J]. 太阳能学报, 2018, 39(10): 2901–2907
CHU Jingchun, WANG Fei, WANG Yang, et al. Fault diagnosis method of wind turbine based on fault tree and probabilistic neural network[J]. Acta Energiae Solaris Sinica, 2018, 39(10): 2901–2907
[12] 赵俊杰. 基于特征加权的KNNFP改进算法及在故障诊断中的应用[J]. 电子技术应用, 2011, 37(4): 113–116, 121
ZHAO Junjie. A novel feature weighted KNNFP algorithm and application of its fault diagnosis[J]. Application of Electronic Technique, 2011, 37(4): 113–116, 121
[13] 童超. 基于数据挖掘方法的风电机组状态监测研究[D]. 北京: 华北电力大学, 2014.
TONG Chao. Research on wind turbine condition monitoring based on data mining[D]. Beijing: North China Electric Power University, 2014.
[14] REZAMAND M, KORDESTANI M, CARRIVEAU R, et al. A new hybrid fault detection method for wind turbine blades using recursive PCA and wavelet-based PDF[J]. IEEE Sensors Journal, 2020, 20(4): 2023–2033.
[15] 戴巨川, 曹俊伟, 张帆, 等. 风电场SCADA数据预处理方法及评价策略[J]. 太阳能学报, 2017, 38(9): 2597–2604
DAI Juchuan, CAO Junwei, ZHANG Fan, et al. Data pre-processing method and its evaluation strategy of scada data from wind farm[J]. Acta Energiae Solaris Sinica, 2017, 38(9): 2597–2604
[16] WU Z D, WANG X L, JIANG B C. Fault diagnosis for wind turbines based on ReliefF and eXtreme gradient boosting[J]. Applied Sciences, 2020, 10(9): 3258.
[17] 李辉, 杨超, 李学伟, 等. 风机电动变桨系统状态特征参量挖掘及异常识别[J]. 中国电机工程学报, 2014, 34(12): 1922–1930
LI Hui, YANG Chao, LI Xuewei, et al. Conditions characteristic parameters mining and outlier identification for electric pitch system of wind turbine[J]. Proceedings of the CSEE, 2014, 34(12): 1922–1930
[18] 朱丽娜, 王学杰, 张进杰. 基于ReliefF-PCA和SVM的发动机故障诊断方法研究[J]. 北京化工大学学报(自然科学版), 2018, 45(1): 55–59
ZHU Lina, WANG Xuejie, ZHANG Jinjie. An engine fault diagnosis method based on ReliefF-PCA and SVM[J]. Journal of Beijing University of Chemical Technology (Natural Science Edition), 2018, 45(1): 55–59
[19] 朱向利. 基于KNN算法的柴油机故障诊断方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2016.
ZHU Xiangli. Study on the diesel engine fault diagnosis method based on KNN algorithm[D]. Harbin: Harbin Engineering University, 2016.
[20] 冯立伟, 张成, 李元, 等. 基于标准距离k近邻的多模态过程故障检测策略[J]. 控制理论与应用, 2019, 36(4): 553–560
FENG Liwei, ZHANG Cheng, LI Yuan, et al. Fault detection strategy of standard-distance-based k nearest neighbor rule in multimode processes[J]. Control Theory & Applications, 2019, 36(4): 553–560
[21] POZO F, VIDAL Y, SALGADO Ó. Wind turbine condition monitoring strategy through multiway PCA and multivariate inference[J]. Energies, 2018, 11(4): 749.
[22] LAHDHIRI H, ELAISSI I, TAOUALI O, et al. Nonlinear process monitoring based on new reduced Rank-KPCA method[J]. Stochastic Environmental Research and Risk Assessment, 2018, 32(6): 1833–1848.
[23] 刘发升, 董清龙, 李文静. 变精度粗糙集的加权KNN文本分类算法[J]. 计算机工程与设计, 2019, 40(5): 1339–1342, 1364
LIU Fasheng, DONG Qinglong, LI Wenjing. Weighted KNN text classification algorithm for variable precision rough sets[J]. Computer Engineering and Design, 2019, 40(5): 1339–1342, 1364
[24] 陈自强, 程健, 季文强, 等. 基于深度置信网络风电机组变桨系统的故障诊断[J]. 测控技术, 2019, 38(5): 18–22
CHEN Ziqiang, CHENG Jian, JI Wenqiang, et al. Fault diagnosis of wind turbine pitch system based on deep belief network[J]. Measurement & Control Technology, 2019, 38(5): 18–22
[25] 龚妙. 基于BP神经网络的风力机叶片覆冰状态诊断技术研究[D]. 长沙: 长沙理工大学, 2019.
GONG Miao. Research on diagnosis technology of ice accretion on wind turbine blades based on BP neural network[D]. Changsha: Changsha University of Science & Technology, 2019.

基于PCA-KNN融合算法的风力机变桨角度故障诊断方法

Fault Diagnosis Method of Wind Turbine Pitch Angle Based on PCA-KNN Fusion Algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

[1]	许小明, 袁志强, 李庆煜, 颜顺林, 黄宸武, 杨科. 基于CFD与风洞实验的缩比风力机三维效应修正公式效果分析[J]. 中国电力, 2020, 53(2): 92-98.
[2]	吴正人, 李非, 路婷婷, 刘梅. 风力机尾流扰动对大气底层边界层的影响[J]. 中国电力, 2018, 51(6): 144-149.
[3]	崔双喜，王维庆. 风力机独立桨距角鲁棒自适应跟踪控制[J]. 中国电力, 2015, 48(6): 14-19.
[4]	吴振威, 蒋小平, 马会萌, 马速良, 高志强. 基于非参数核密度估计法的光伏出力随机分布模型[J]. 中国电力, 2013, 46(9): 126-130.

模态框（Modal）标题

基于PCA-KNN融合算法的风力机变桨角度故障诊断方法

Fault Diagnosis Method of Wind Turbine Pitch Angle Based on PCA-KNN Fusion Algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics