随着风电机组装机容量的不断攀升,同时带来并网发电率低、机组故障率高等缺点,导致风电机组整体利用率较低。为此提出一种基于数据融合的风电变桨系统故障预警方法。首先结合SCADA系统中的运行统计信息和历史数据,采用Relief特征参数选择方法筛选出与风电变桨系统故障相关的特征参数;然后采用数据融合的方法,建立基于MSET技术的风电变桨系统故障预测模型,并采用滑动窗口法进行故障预警阈值的确定;最后以上海某风场1.5 MW双馈异步风电机组进行实例分析,结果表明该方法可提前发现风电变桨系统故障征兆,实现对风电变桨系统的早期故障预警。
Abstract
With the increasing installed capacity of wind turbines, the disadvantages of low grid-connected generation rate and high unit failure rate have resulted in low overall utilization rate of wind turbines. For this reason, this paper proposes a wind power pitch system early fault warning method based on data fusion. First, combined with the operating statistics and historical data in the SCADA system, the Relief characteristic parameter selection method is used to screen out the characteristic parameters related to the wind power pitch system failure; then the data fusion method is used to establish the wind power pitch system fault prediction model based on the MSET technology and the sliding window method is used to determine the fault warning threshold. Finally, a 1.5 MW doubly-fed asynchronous wind turbine in a wind farm in Shanghai is taken as an example. The results show that this method can detect the fault signs of the wind power pitch system in advance, and realize the early warning of the wind power pitch system failure.
关键词
风电机组 /
数据融合 /
变桨系统 /
MSET /
滑动窗口法 /
故障预警
Key words
wind turbines /
data fusion /
pitch system /
MSET /
sliding window method /
fault warning
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 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 Z J, QIU Y N, FENG Y H, et al.Research on faults of wind turbine pitch system based on machine learning[J]. Acta energiae solaris sinica, 2020, 41(5): 85-90.
[2] 王进花, 朱恩昌, 曹洁, 等. 基于修正IMM的风机变桨系统故障诊断方法[J]. 北京航空航天大学学报, 2020, 46(8): 1460-1468.
WANG J H, ZHU E C, CAO J, et al.Fault diagnosis method of wind turbine pitch system based on modified IMM[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(8): 1460-1468.
[3] 梁涛, 钱思琦, 姜文, 等. 基于SCADA和支持向量回归的风机状态监测[J]. 控制工程, 2020, 27(8): 1317-1323.
LIANG T, QIAN S Q, JIANG W, et al.Fan status monitoring based on SCADA and support vector regression[J]. Control engineering, 2020, 27(8): 1317-1323.
[4] 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 H, YANG C, LI X W, et al.Mining and abnormal identification of state characteristic parameters of wind turbine electric pitch system[J]. Proceedings of the CSEE, 2014, 34(12): 1922-1930.
[5] 李大中, 毛小丽, 尹鹏娟, 等. 基于NSET的风力发电机后轴承温度预警方法[J]. 科学技术与工程, 2016, 16(24): 205-209.
LI D Z, MAO X L, YIN P J, et al.NSET-based warning method for rear bearing temperature of wind turbines[J]. Science technology and engineering, 2016, 16(24): 205-209.
[6] 陈茜, 李录平, 刘瑞, 等. 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(11): 190-198.
CHEN Q, LI L P, LIU R, et al.Wind turbine pitch angle fault diagnosis method based on PCA-KNN fusion algorithm[J]. China electric power, 2021(11): 190-198.
[7] 刘长良, 王梓齐. 基于MSET和集成学习的风电机组齿轮箱故障预警[J]. 太阳能学报, 2020, 41(11): 228-233.
LIU C L, WANG Z Q.Wind turbine gearbox fault warning based on MSET and integrated learning[J]. Acta energiae solaris sinica, 2020, 41(11): 228-233.
[8] 胡杰, 唐静, 谢仕义. 基于实时动态基线的运行设备多元状态估计方法[J]. 热力发电, 2021, 50(2): 125-131.
HU J, TANG J, XIE S Y.A method for multiple state estimation of operating equipment based on real-time dynamic baseline[J]. Thermal power generation, 2021, 50(2): 125-131.
[9] 赵劲松, 王梓齐, 刘长良. 基于Bagging集成策略和多元状态估计的风电机组齿轮箱状态监测[J]. 科学技术与工程, 2020, 20(20): 8180-8186.
ZHAO J S, WANG Z Q, LIU C L.Wind turbine gearbox condition monitoring based on Bagging integration strategy and multivariate state estimation[J]. Science technology and engineering, 2020, 20(20): 8180-8186.
[10] 郑玉巧, 魏剑峰, 朱凯, 等. 风力机主轴承故障监测方法[J]. 振动测试与诊断, 2021, 41(2): 341-347, 415.
ZHENG Y Q, WEI J F, ZHU K, et al.Monitoring method for main bearing failure of wind turbine[J]. Vibration test and diagnosis, 2021, 41(2): 341-347, 415.
基金
上海市“科技创新行动计划”地方院校能力建设专项项目（19020500700）
PDF(1712 KB)
