Evaluation of Wind Turbine Gearbox State with Fusion of SCADA Data
-
摘要: 为对风机齿轮箱状态进行准确评估,提出一种基于核主成分(KPCA)与最小二乘支持向量机(LS-SVM)结合的齿轮箱数据融合故障预测模型。鉴于SCADA系统中数据信息质量的不确定性和冗余性,该模型首先对监测数据预处理(4分位法剔除异常数据等),对齿轮箱特征因素进行相关性分析,利用该预测方法对齿轮箱典型状态特征(振动、温度特征等)进行预测,利用统计过程控制原理(SPC)分析残差,以实现齿轮箱异常状态的预测。最后,以齿轮箱油温预测为例,验证了该模型的准确性和有效性。Abstract: For an accurate evaluation of wind turbine gearbox condition, a kind of based on the kernel principal component analysis (KPCA) and least squares support vector machines (LS-SVM) combined with gearbox data fusion fault prediction model is put forward, in terms of the uncertainty of SCADA system data in the information quality and redundancy, firstly the model for monitoring data preprocessing (quartile method, a method to eliminate abnormal data), the correlation analysis was carried out on the gear box characteristic factors, by using the forecast method of gearbox typical state characteristics (vibration, temperature characteristics, etc.). By using the theory of statistical process control (SPC) analysis of the residual, the abnormal condition of gear box is predicted. Finally, the model for the accuracy and effectiveness are verified by taking the oil temperature prediction of gearbox as an example.
-
表 1 齿轮箱油温相关变量系数
变量名 相关系数 环境温度 0.773 输出功率 0.525 齿轮箱轴端温度 0.958 叶轮转速(接近开关1) 0.129 叶轮转速(接近开关2) 0.130 风速sp1 0.512 风速sp2 0.506 发电机转速 0.133 齿轮箱加速度峰值 0.668 齿轮箱润滑油压力 -0.787 齿轮箱减速比 0.009 表 2 齿轮箱相关变量原始数据
序号 V1 V2 V3 V4 V5 V6 V7 1 26.1 874.14 35.7 7.51 7.45 0.06 3.85 2 26.1 894.63 35.7 7.7 7.71 0.07 3.81 3 26.1 863.9 35.5 7.54 7.57 0.07 3.84 ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ 3199 27.2 1345.6 61.3 8.47 8.2 0.36 5.7 3200 27 1282.9 61.3 8.11 8.4 0.2 5.63 表 3 综合变量X1, X2
序号 X1 X2 1 879.326 2 4.077 2 2 899.748 4 3.304 4 3 869.470 3 4.298 8 ⋮ ⋮ ⋮ 3 200 1 282.597 0 8.922 5 表 4 3种预测方法预测误差
预测方法 EMS EMA EMR KPCA-LS-SVM 0.6623 0.6368 0.0123 BP神经网络 1.4729 0.9959 0.0191 LS-SVM 2.3439 1.1644 0.0218 -
[1] Kusiak A, Verma A. Analyzing bearing faults in wind turbines:a data-mining approach[J]. Renewable Energy, 2012, 48:110-116 http://cn.bing.com/academic/profile?id=726e6648b2fba7205ab4fb4b3b53a7f0&encoded=0&v=paper_preview&mkt=zh-cn [2] 曾军, 陈艳峰, 杨苹, 等.大型风力发电机组故障诊断综述[J].电网技术, 2018, 42(3):849-860 http://d.old.wanfangdata.com.cn/Periodical/jzgcjsysj201820481Zeng J, Chen Y F, Yang P, et al. Review of fault diagnosis methods of large-scale wind turbines[J]. Power System Technology, 2018, 42(3):849-860(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jzgcjsysj201820481 [3] Wang J J, Gao R X, Yan R Q. Integration of EEMD and ICA for wind turbine gearbox diagnosis[J]. Wind Energy, 2014, 17(5):757-773 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1002/we.1653 [4] Wang Y, Infield D. Supervisory control and data acquisition data-based non-linear state estimation technique for wind turbine gearbox condition monitoring[J]. IET Renewable Power Generation, 2013, 7(4):350-358 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=785d85dce89d5f92497b3bf95d449e90 [5] 杭俊, 张建忠, 程明, 等.风力发电系统状态监测和故障诊断技术综述[J].电工技术学报, 2013, 28(4):261-271 http://d.old.wanfangdata.com.cn/Periodical/dgjsxb201304036Hang J, Zhang J Z, Cheng M, et al. An overview of condition monitoring and fault diagnostic for wind energy conversion system[J]. Transactions of China Electrotechnical Society, 2013, 28(4):261-271(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/dgjsxb201304036 [6] Adams D, White J, Rumsey M, et al. Structural health monitoring of wind turbines:method and application to a HAWT[J]. Wind Energy, 2011, 14(4):603-623 http://cn.bing.com/academic/profile?id=83e36bc773ca90c901b1e89608f865d6&encoded=0&v=paper_preview&mkt=zh-cn [7] 赵洪山, 郭伟, 邵玲, 等.基于子空间方法的风机齿轮箱故障预测算法[J].电力自动化设备, 2015, 35(3):27-32 http://d.old.wanfangdata.com.cn/Periodical/dlzdhsb201503005Zhao H S, Guo W, Shao L, et al. Gearbox fault prediction algorithm based on subspace method for wind turbine[J]. Electric Power Automation Equipment, 2015, 35(3):27-32(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/dlzdhsb201503005 [8] 郭鹏, 李淋淋, 马登昌.基于IPSO-BP的风电机组齿轮箱状态监测研究[J].太阳能学报, 2012, 33(3):439-445 http://d.old.wanfangdata.com.cn/Periodical/tynxb201203017Guo P, Li L L, Ma D C. Wind turbine gearbox condition monitoring with IPSO-BP[J]. Acta Energiae Solaris Sinica, 2012, 33(3):439-445(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/tynxb201203017 [9] 赵洪山, 胡庆春, 李志为.基于统计过程控制的风机齿轮箱故障预测[J].电力系统保护与控制, 2012, 40(13):67-73 http://d.old.wanfangdata.com.cn/Periodical/jdq201213012Zhao H S, Hu Q C, Li Z W. Failure prediction of wind turbine gearbox based on statistical process control[J]. Power System Protection and Control, 2012, 40(13):67-73(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jdq201213012 [10] 郭鹏, Infield D, 杨锡运.风电机组齿轮箱温度趋势状态监测及分析方法[J].中国电机工程学报, 2011, 31(32):129-136 http://d.old.wanfangdata.com.cn/Periodical/zgdjgcxb201132020Guo P, Infield D, Yang X Y. Wind turbine gearbox condition monitoring using temperature trend analysis[J]. Proceedings of the CSEE, 2011, 31(32):129-136(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zgdjgcxb201132020 [11] 李大中, 常城, 许炳坤.基于样本优化的风电机组齿轮箱轴承温度预测[J].系统仿真学报, 2017, 29(2):374-380 http://d.old.wanfangdata.com.cn/Periodical/xtfzxb201702019Li D Z, Chang C, Xu B K. Wind turbine gearing temperature prediction based on sample optimization[J]. Journal of System Simulation, 2017, 29(2):374-380(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/xtfzxb201702019 [12] 栗然, 陈倩, 徐宏锐.考虑相关因素的最小二乘支持向量机风速预测方法[J].电力系统保护与控制, 2010, 38(21):146-151 http://d.old.wanfangdata.com.cn/Periodical/jdq201021030Li R, Chen Q, Xu H R. Wind speed forecasting method based on LS-SVM considering the related factors[J]. Power System Protection and Control, 2010, 38(21):146-151(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jdq201021030 [13] 朱霄珣, 韩中合.基于PSO参数优化的LS-SVM风速预测方法研究[J].中国电机工程学报, 2016, 36(23):6337-6342 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgdjgcxb201623004Zhu X X, Han Z H. Research on LS-SVM wind speed prediction method based on PSO[J]. Proceedings of the CSEE, 2016, 36(23):6337-6342(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgdjgcxb201623004 [14] 陈伟, 吴布托, 裴喜平.风电机组异常数据预处理的分类多模型算法[J].电力系统及其自动化学报, 2018, 30(4):137-143 http://d.old.wanfangdata.com.cn/Periodical/dlxtjqzdhxb201804023Chen W, Wu B T, Pei X P. Classification multi-model algorithm for abnormal data preprocessing in wind turbines[J]. Proceedings of the CSU-EPSA, 2018, 30(4):137-143(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/dlxtjqzdhxb201804023 [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 http://d.old.wanfangdata.com.cn/Periodical/tynxb201709038Dai J C, Cao J W, Zhang F, 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(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/tynxb201709038 [16] 赵永宁, 叶林, 朱倩雯.风电场弃风异常数据簇的特征及处理方法[J].电力系统自动化, 2014, 38(21):39-46 http://d.old.wanfangdata.com.cn/Periodical/dlxtzdh201421007Zhao Y N, Ye L, Zhu Q W. Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms[J]. Automation of Electric Power Systems, 2014, 38(21):39-46(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/dlxtzdh201421007 [17] 贾新章, 游海龙, 顾铠, 等.统计过程控制理论与实践[M].北京:电子工业出版社, 2017Jia X Z, You H L, Gu K, et al. Statistical process control theory and practice[M]. Beijing:Publishing House of Electronics Industry, 2017(in Chinese) [18] 胡庆春.基于支持向量机和统计过程控制的风电机组故障预测算法的研究[D].北京: 华北电力大学, 2011: 28-29Hu Q C. Research of fault prediction algorithm of wind turbine based on support vector machine and statistical process control[D]. Beijing: North China Electric Power University, 2011: 28-29(in Chinese)