基于K-means和BPNN的风机状态识别

doi:10.11930/j.issn.1004-9649.202203070

中国电力 ›› 2023, Vol. 56 ›› Issue (6): 158-166,175.DOI: 10.11930/j.issn.1004-9649.202203070

基于K-means和BPNN的风机状态识别

杨晓峰¹, 方逸航², 赵鹏臻², 王承民², 谢宁²

1. 龙源电力集团（上海）风力发电有限公司，上海 200122;
2. 上海交通大学电子信息与电气工程学院，上海 200240

收稿日期:2022-03-24 修回日期:2023-05-06 发布日期:2023-07-04
作者简介:杨晓峰（1992—），男，助理工程师，从事风力发电运营维护，E-mail：12023643@chnenergy.com.cn;方逸航（1998—），男，硕士研究生，从事大数据技术在电力系统中应用研究，E-mail：fwl126126@126.com;赵鹏臻（1998—），男，硕士研究生，从事大数据技术在电力系统中应用研究，E-mail：809563642@qq.com;王承民（1970—），男，博士，教授，从事电力系统安全稳定分析、电力系统经济运行、电网规划和电力市场等研究，E-mail：wangchengmin@sjtu.edu.cn;谢宁（1973—），女，通信作者，博士，副教授，从事电力系统安全稳定分析、电力系统经济运行、电网规划和智能电网等研究，E-mail：xiening@sjtu.edu.cn
基金资助:
国家重点研发计划资助项目（城市综合能源智慧物联管控技术研究及应用示范， 2020YFB2104500）。

State Recognition of Wind Turbines Based on K-means and BPNN

YANG Xiaofeng¹, FANG Yihang², ZHAO Pengzhen², WANG Chengmin², XIE Ning²

1. Longyuan Power Group (Shanghai) Wind Power Co., Ltd., Shanghai 200122, China;
2. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2022-03-24 Revised:2023-05-06 Published:2023-07-04
Supported by:
This work is supported by National Key Research and Development Program of China(Research and Application Demonstration of Intelligent IOT Control Technology for Urban Comprehensive Energy, No.2020YFB2104500).

摘要/Abstract

摘要： 为实现“双碳”目标，必须大力发展风力发电技术。而随着电网规模越来越大，运行越来越复杂，对风机等电力设备的状态实时检测和精确评估也成为一个越来越重要的问题。随着大数据技术的发展以及电力设备数据监测技术的完善使电力设备状态监测使用机器学习等数据驱动技术成为了可能。与传统方法相比，该方法不依赖于准确的经验阈值和定量模型，对数据海量化和复杂化的情况具有更强的适应能力。因此，分别以无监督（K-means）和有监督（BP神经网络）的机器学习方法对风机状态进行识别，并探究对原始数据采用降维算法后风机状态识别的准确性及计算效率的变化。结果显示：2种机器学习方法在风机状态识别中的应用均具备有效性，而降维方法在有限的精度损失下较为明显地提高了计算效率。

关键词: 风机状态识别, 非机理性建模, 机器学习, 神经网络, 降维

Abstract: In order to achieve the goal of “double carbon”, the development of wind power generation technology is essential. At the same time, with the increasing complexity of power grid, the real-time detection and accurate evaluation of the state of wind turbines and other power equipment are becoming increasingly important. In recent years, the development of big data technology and the improvement of power equipment data monitoring technology makes possible the application of big data technology in power equipment state recognition. Compared with the conventional methods, the above-mentioned methods are independent of accurate empirical thresholds or quantitative models, and have better adaptability to the rapid increase and variability of data. Thus, this paper applies the unsupervised (K-means) and supervised (BPNN) machine learning methods to state recognition of wind turbines, while exploring the variation of accuracy and computational efficiency after the application of dimensionality reduction methods. The results show that both machine learning methods are effective in state recognition of wind turbines, while the dimensionality reduction method can effectively improve the computational efficiency with limited accuracy loss.

Key words: state recognition of wind turbine, non-mechanstic modeling, machine learning, neural network, dimensionality reduction

杨晓峰, 方逸航, 赵鹏臻, 王承民, 谢宁. 基于K-means和BPNN的风机状态识别[J]. 中国电力, 2023, 56(6): 158-166,175.

YANG Xiaofeng, FANG Yihang, ZHAO Pengzhen, WANG Chengmin, XIE Ning. State Recognition of Wind Turbines Based on K-means and BPNN[J]. Electric Power, 2023, 56(6): 158-166,175.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202203070

https://www.electricpower.com.cn/CN/Y2023/V56/I6/158

参考文献

[1] 刘文君, 董明, 徐元孚, 等. 电力设备运行状态大数据标签体系与关键技术[J]. 中国电力, 2022, 55(1): 126–132
LIU Wenjun, DONG Ming, XU Yuanfu, et al. Structure and key technologies of big data labeling system for power equipment operation status[J]. Electric Power, 2022, 55(1): 126–132
[2] 李清义. 风力发电技术基础[M]. 中国电力出版社, 2020.
[3] 李俊卿, 胡晓东, 马阳硕, 等. 基于合作博弈和区间划分的风电机组状态评价[J]. 智慧电力, 2022, 50(1): 7–13
LI Junqing, HU Xiaodong, MA Yangshuo, et al. State assessment of wind turbines based on cooperative game and interval partition[J]. Smart Power, 2022, 50(1): 7–13
[4] 王楠, 孙善武. 基于半监督聚类分析的无人机故障识别[J]. 计算机科学, 2019, 46(B06): 192–195
WANG Nan, SUN Shanwu. UAV fault recognition based on semi-supervised clustering[J]. Computer Science, 2019, 46(B06): 192–195
[5] 王浙超, 曾九孙, 谢磊, 等. 基于去噪自编码器的故障隔离与识别方法[J]. 信息与控制, 2021, 50(6): 641–650
WANG Zhechao, ZENG Jiusun, XIE Lei, et al. Fault isolation and identification method based on denoising autoencoder[J]. Information and Control, 2021, 50(6): 641–650
[6] LE Q V. Building high-level features using large scale unsupervised learning[C]//2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, BC, Canada. IEEE, 2013: 8595–8598.
[7] 易京. 基于深度收缩自编码网络的机械设备故障诊断研究[D]. 北京: 北京邮电大学, 2019.
YI Jing. Research on mechanical equipment fault diagnosis based on deep shrinkage self-coding network[D]. Beijing: Beijing University of Posts and Telecommunications, 2019.
[8] 曲岳晗, 赵洪山, 马利波, 等. 多深度神经网络综合的电力变压器故障识别方法[J]. 中国电机工程学报, 2021, 41(23): 8223–8230
QU Yuehan, ZHAO Hongshan, MA Libo, et al. Multi-depth neural network synthesis method for power transformer fault identification[J]. Proceedings of the CSEE, 2021, 41(23): 8223–8230
[9] 夏添梁, 张玉敏, 杨明, 等. 联合长短期记忆神经网络和粒子滤波的配电网预测辅助鲁棒状态估计方法[J]. 高电压技术, 2022, 48(4): 1343–1355
XIA Tianliang, ZHANG Yumin, YANG Ming, et al. Robust forecasting-aided state estimation method of distribution network based on long-short term memory neural network and particle filter[J]. High Voltage Engineering, 2022, 48(4): 1343–1355
[10] 张鑫淼. 基于SCADA数据的风电机组性能分析及健康状态评估[D]. 北京: 华北电力大学(北京), 2017.
ZHANG Xinmiao. Performance analysis and health status evaluation of wind turbine based on SCADA data[D]. Beijing: North China Electric Power University, 2017.
[11] 李重桂, 李录平, 刘瑞, 等. 风电机组智能状态评估与故障预测研究进展[J]. 电站系统工程, 2020, 36(4): 1–6, 11
LI Chonggui, LI Luping, LIU Rui, et al. Review on research progress of wind turbine intelligent state assessment and fault prediction[J]. Power System Engineering, 2020, 36(4): 1–6, 11
[12] 段震清. 基于大数据分析的风电机组运行状态评估及故障诊断[D]. 太原: 山西大学, 2018.
DUAN Zhenqing. Wind turbine operation state evaluation and fault diagnosis based on big data analysis[D]. Taiyuan: Shanxi University, 2018.
[13] 刘海涛, 陈俊, 黄迪, 等. 外转子风机轴向振动及故障机理研究[J]. 振动与冲击, 2022, 41(6): 271–280
LIU Haitao, CHEN Jun, HUANG Di, et al. On the axial vibration and the failure of outer-rotor fans[J]. Journal of Vibration and Shock, 2022, 41(6): 271–280
[14] 邹宜金, 连应华, 黄新宇, 等. 基于声纹的高泛化性风机叶片异常检测方法研究[J]. 电子科技大学学报, 2021, 50(5): 795–800
ZOU Yijin, LIAN Yinghua, HUANG Xinyu, et al. High generalization in anomaly detection of wind turbine generator based on voiceprint[J]. Journal of University of Electronic Science and Technology of China, 2021, 50(5): 795–800
[15] ZAHER A, MCARTHUR S D J, INFIELD D G, et al. Online wind turbine fault detection through automated SCADA data analysis[J]. Wind Energy, 2009, 12(6): 574–593.
[16] LI J, LEI X, LI H, et al. Normal behavior models for the condition assessment of wind turbine generator systems[J]. Electric Power Components and Systems, 2014, 42(11): 1201–1212.
[17] 刘军, 汪继勇. 基于风电机组健康状态的风电场功率分配研究[J]. 电力系统保护与控制, 2020, 48(20): 106–113
LIU Jun, WANG Jiyong. Research on power distribution of a wind farm based on the healthy state of wind turbines[J]. Power System Protection and Control, 2020, 48(20): 106–113
[18] 肖桂雨, 向健平, 凌永志, 等. 基于小波神经网络的风力发电机故障预测方法[J]. 电力科学与技术学报, 2019, 34(2): 195–202
XIAO Guiyu, XIANG Jianping, LING Yongzhi, et al. Prediction of wind turbine faults based on wavelet neural networks[J]. Journal of Electric Power Science and Technology, 2019, 34(2): 195–202
[19] 向玲, 王朋鹤, 李京蓄. 基于CNN-LSTM的风电机组异常状态检测[J]. 振动与冲击, 2021, 40(22): 11–17
XIANG Ling, WANG Penghe, LI Jingxu. Abnormal state detection of wind turbines based on CNN-LSTM[J]. Journal of Vibration and Shock, 2021, 40(22): 11–17
[20] 李振恩, 张新燕, 胡威, 等. 基于健康指数的风电机组高速轴轴承状态评估与预测[J]. 太阳能学报, 2021, 42(10): 290–297
LI Zhen'en, ZHANG Xinyan, HU Wei, et al. State accessment and prediction of wind turbine high speed shaft bearing based on health index[J]. Acta Energiae Solaris Sinica, 2021, 42(10): 290–297
[21] 雍彬, 陈进, 张方红, 等. 基于门控循环网络融合多源数据的风电齿轮箱状态预警方法[J]. 太阳能学报, 2021, 42(8): 421–425
YONG Bin, CHEN Jin, ZHANG Fanghong, et al. State warning of wind turbine gearbox based on gated recurrent unit network fusing multi-source data[J]. Acta Energiae Solaris Sinica, 2021, 42(8): 421–425
[22] 杨茂, 张强. 基于相关向量机的风电功率实时预测研究[J]. 中国电力, 2016, 49(8): 64–68
YANGMao, ZHANG Qiang. Real time prediction of wind power based on relevance vector machine[J]. Electric Power, 2016, 49(8): 64–68
[23] 董兴辉, 张鑫淼, 郑凯, 等. 基于组合赋权和云模型的风电机组健康状态评估[J]. 太阳能学报, 2018, 39(8): 2139–2146
DONG Xinghui, ZHANG Xinmiao, ZHENG Kai, et al. Health status assessment of wind turbine based on combination weighting and cloud model[J]. Acta Energiae Solaris Sinica, 2018, 39(8): 2139–2146
[24] 江顺辉, 方瑞明, 尚荣艳, 等. 采用动态劣化度的风电机组运行状态实时评估[J]. 华侨大学学报(自然科学版), 2018, 39(1): 86–91
JIANG Shunhui, FANG Ruiming, SHANG Rongyan, et al. Real-time wind turbine operating assessment using dynamic inferior degree[J]. Journal of Huaqiao University (Natural Science), 2018, 39(1): 86–91
[25] 孙海蓉, 王皓茹, 王瑞珈, 等. 基于云模型的风电机组运行状态评价[J]. 电力科学与工程, 2020, 36(8): 57–62
SUN Hairong, WANG Haoru, WANG Ruijia, et al. Wind turbine operation status evaluation based on cloud model[J]. Electric Power Science and Engineering, 2020, 36(8): 57–62

基于K-means和BPNN的风机状态识别

State Recognition of Wind Turbines Based on K-means and BPNN

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 15

编辑推荐

Metrics

[1]	高志远, 庄卫金, 李峰, 于芳, 张鸿, 王艳, 夏旻. 调控领域人工智能应用的高复用性验证平台[J]. 中国电力, 2025, 58(3): 142-150.
[2]	吴小忠, 肖立华, 童超, 夏向阳, 袁翎, 甘星, 江志文, 黄湘源. 基于传递熵与JS-BP神经网络的锂离子电池容量预测模型[J]. 中国电力, 2025, 58(2): 186-192, 215.
[3]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[4]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[5]	叶煜明, 钱琪琪, 万正东, 张继钢. 基于嵌入法与集成学习的线路工程造价预测[J]. 中国电力, 2024, 57(5): 251-260.
[6]	邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57(4): 162-170.
[7]	陈巳阳, 韩利, 方济中, 丁五行, 成诚, 李文, 张源, 钱勇. 基于不确定参数的变电站碳储量预估方法[J]. 中国电力, 2024, 57(4): 200-210.
[8]	娄奇鹤, 李荣盛, 谭捷, 袁铁江. 基于卷积神经网络的暂稳极限功率计算[J]. 中国电力, 2024, 57(4): 211-219.
[9]	马汝括, 董杰, 王雅湉, 伊国鑫, 丁祥浩, 马乐. 基于神经网络的高寒地区CF₄和SF₆/CF₄检测[J]. 中国电力, 2024, 57(3): 103-112.
[10]	阎洁, 杨佳琳, 王航宇, 卢姣阳, 刘永前, 张磊. 基于风况预测误差自适应的海上风电场尾流偏转控制方法[J]. 中国电力, 2024, 57(3): 190-196.
[11]	张博智, 张茹, 焦东翔, 王龙宇, 周一凡, 周丽霞. 基于VMD-SAST的电能质量扰动分类识别方法[J]. 中国电力, 2024, 57(2): 34-40.
[12]	李卓, 王胤喆, 叶林, 罗雅迪, 宋旭日, 张振宇. 从感知-预测-优化综述图神经网络在电力系统中的应用[J]. 中国电力, 2024, 57(12): 2-16.
[13]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[14]	陈来恩, 曾小勇, 曾子豪, 成采辰, 孙耀科. 基于物理信息与深度神经网络的锂离子电池温度预测[J]. 中国电力, 2024, 57(11): 18-25.
[15]	薛松萍, 高德荃, 赵子岩, 林彧茜, 广泽晶, 张大卫. 基于业务差异化传输需求下的电力通信网路由算法[J]. 中国电力, 2024, 57(11): 183-190.

模态框（Modal）标题

基于K-means和BPNN的风机状态识别

State Recognition of Wind Turbines Based on K-means and BPNN

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 15

编辑推荐

Metrics