针对当前亟待解决的风电叶片断裂无损监测与预警问题,提出在监视控制与数据采集（SCADA）系统的基础上结合非线性状态估计技术（NSET）实现风电叶片断裂监测及预警的方法。首先,提出通过卡方检验及误差贡献率分析对参数进行筛选,即对SCADA数据进行降维消冗,得到与叶片运行状态有关的SCADA参数。然后,利用NSET将筛选出的参数进行数据融合,通过建模输出的相似度曲线对叶片断裂进行判断。最后,利用某风场1.5 MW风电机组叶片断裂数据验证该方法的有效性并确定断裂预警阈值,当相似度到达0.26时进行叶片断裂预警可提前3.93 h预警。试验结果表明,所提方法可对叶片断裂进行有效无损监测,并可为风电叶片断裂预警阈值提供参考。
Abstract
In order to solve the problem of non-destructive monitoring and early warning of wind power blade breakage, a method of monitoring and early warning of wind power blade breakage was proposed based on monitoring control and data acquisition system and nonlinear state estimation technology. Firstly, it was proposed to screen parameters through Chi-square test and error contribution rate analysis, which involved dimensionality reduction and redundancy reduction of SCADA data to obtained SCADA parameters related to blade operation status.Then, NSET was used to fuse the selected parameters, and the blade fracture was judged by the similarity curve of modeling output. Finally, the blade fracture data of 1.5 MW wind turbine in a wind farm was used to verify the effectiveness of the method and the fracture warning threshold was determined.When the similarity reaches 0.26, the blade fracture warning can be conducted 3.93 h in advance.The experimental results show that the proposed method can effectively nondestructive monitoring of blade breakage, and provide a reference for the early warning threshold of wind power blade breakage.
关键词
卡方检验 /
非线性状态估计 /
风电叶片 /
断裂监测 /
SCADA /
无损监测
Key words
Chi-square test /
nonlinear state estimate /
wind turbine blade /
fracture monitoring /
SCADA /
non-destructive testing
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈雪峰, 郭艳婕, 许才彬, 等. 风电装备故障诊断与健康监测研究综述[J]. 中国机械工程, 2020, 31(2): 175-189.
CHEN X F, GUO Y J, XU C B, et al.Review of fault diagnosis and health monitoring for wind power equipment[J]. China mechanical engineering, 2020, 31(2): 175-189.
[2] 张华强, 刘林, 秦昌礼, 等. 基于惯性网络的兆瓦级风电叶片形变测量算法研究[J]. 太阳能学报, 2022, 43(10): 186-191.
ZHANG H Q, LIU L, QIN C L, et al.Research on deformation measurement algorithm of megawatt wind turbine blade based on inertial network[J]. Acta energiae solaris sinica, 2022, 43(10): 186-191.
[3] 金晓航, 许壮伟, 孙毅, 等. 基于SCADA数据分析和稀疏自编码神经网络的风电机组在线运行状态监测[J]. 太阳能学报, 2021, 42(6): 321-328.
JIN X H, XU Z W, SUN Y, et al.Online condition monitoring for wind turbines based on SCADA data analysis and sparse auto-encoder neural network[J]. Acta energiae solaris sinica, 2021, 42(6): 321-328.
[4] 戴巨川. 叶片断裂事故条件下直驱式风电机组动态特性分析[J]. 机械工程学报, 2013, 49(2): 190-198.
DAI J C.Dynamic characteristics analyzed of large scale directly-driven wind turbines under blade fracture accident condition[J]. Journal of mechanical engineering, 2013, 49(2): 190-198.
[5] CHEN X.Fracture of wind turbine blades in operation: Part I: a comprehensive forensic investigation[J]. Wind energy, 2018, 21(11): 1046-1063.
[6] 魏书荣, 张鑫, 符杨, 等. 基于GRA-LSTM-Stacking模型的海上双馈风力发电机早期故障预警与诊断[J]. 中国电机工程学报, 2021, 41(7): 2373-2383.
WEI S R, ZHANG X, FU Y, et al.Early fault warning and diagnosis of offshore wind DFIG based on GRA-LSTM-stacking model[J]. Proceedings of the CSEE, 2021, 41(7): 2373-2383.
[7] CHEN H G, XIE C, DAI J C, et al.SCADA data-based working condition classification for condition assessment of wind turbine main transmission system[J]. Energies, 2021, 14(21): 7043.
[8] 廖志伟, 陈琳韬, 黄杰栋, 等. 基于特征空间变换与LSTM的中短期电煤价格预测[J]. 东北大学学报(自然科学版), 2021, 42(4): 483-493.
LIAO Z W, CHEN L T, HUANG J D, et al.Medium and short-term electricity coal price forecast based on feature space transformation and LSTM[J]. Journal of Northeastern University (natural science), 2021, 42(4): 483-493.
[9] 尹诗, 余忠源, 孟凯峰, 等. 基于非线性状态估计的风电机组变桨控制系统故障识别[J]. 中国电机工程学报, 2014, 34(增刊1): 160-165.
YIN S, YU Z Y, MENG K F, et al.Fault identification of wind turbine variable rotor control system based on nonlinear state estimation[J]. Proceedings of the CSEE, 2014, 34(Sup 1): 160-165.
[10] WU X, SU L C.Wind turbine modeling research based on the combination of SCADA and vibration signals[C]//2017 4th International Conference on Information Science and Control Engineering (ICISCE). Changsha, China, 2017: 1331-1335.
[11] 王梓齐, 刘长良, 刘帅. 基于集成NSET和模糊软聚类的风电机组齿轮箱状态监测[J]. 仪器仪表学报, 2019, 40(7): 138-146.
WANG Z Q, LIU C L, LIU S.Condition monitoring of wind turbine gearbox based on ensemble nonlinear state estimation technique and soft fuzzy clustering[J]. Chinese journal of scientific instrument, 2019, 40(7): 138-146.
基金
国家自然科学基金面上项目（52175105; 52175079); 沈阳市科学技术计划（23-407-3-21）; 辽宁省科学技术基础研究计划（2022JH2/101300204）
PDF(5133 KB)
