基于状态曲线的风电机组运行工况异常检测
|
摘要
为了提高风电机组的利用率和发电量,减少风电机组维修和更换费用,需要对其运行工况进行监测。本文首先对机组的风速-功率、风速-转速、风速-桨距角、转速-功率、转速-桨距角5种状态曲线进行理论介绍,然后结合实际运行数据对其进行了分析。结果表明:由于风速的随机性和风电机组的惯性,前3种曲线不能很好地区分机组的正常运行状态和故障状态,而转速-功率、转速-桨距角能够对机组的异常情况进行准确的监测;以转速-功率、转速-桨距角状态曲线为基础,分析了机组不同运行工况在状态曲线上的分布,对各个不同工况分别建立相应的评价体系,通过故障实例分析,表明本文方法能提前感知异常情况,有效提高系统的状态监测精度。
In order to improve the utilization rate and power generation of wind turbines, and reduce the cost of maintenance and replacement of wind turbines, it is necessary to monitor the operating conditions. In this paper, five state curves of the unit, including the wind speed-power curve, the wind speed-rotor speed curve, the wind speed-pitch angle curve, the rotor speed-power curve, and the rotor speed-pitch angle curve, are introduced theoretically. Then, they are analyzed combining with the actual operational data. The results show that, due to the randomness of wind speed and the inertia of wind turbines, the first three curves does not allow the wind turbine to distinguish normal operation status from a fault status. However, the rotor speed-power curve and rotor speed-pitch angle curve are able to accurately monitor the abnormal conditions of the wind turbine. On the basis of the last two state curves, the distribution of different operating conditions of the unit is analyzed, and corresponding evaluation systems are established for each operating condition. The fault case study indicates that, this method can sense the unit's abnormal situation in advance, and effectively improve the state monitoring accuracy of the system.
In order to improve the utilization rate and power generation of wind turbines, and reduce the cost of maintenance and replacement of wind turbines, it is necessary to monitor the operating conditions. In this paper, five state curves of the unit, including the wind speed-power curve, the wind speed-rotor speed curve, the wind speed-pitch angle curve, the rotor speed-power curve, and the rotor speed-pitch angle curve, are introduced theoretically. Then, they are analyzed combining with the actual operational data. The results show that, due to the randomness of wind speed and the inertia of wind turbines, the first three curves does not allow the wind turbine to distinguish normal operation status from a fault status. However, the rotor speed-power curve and rotor speed-pitch angle curve are able to accurately monitor the abnormal conditions of the wind turbine. On the basis of the last two state curves, the distribution of different operating conditions of the unit is analyzed, and corresponding evaluation systems are established for each operating condition. The fault case study indicates that, this method can sense the unit's abnormal situation in advance, and effectively improve the state monitoring accuracy of the system.
引文
[1]陈雪峰,李继猛,程航,等.风力发电机状态监测和故障诊断技术的研究与进展[J].机械工程学报, 2011,47(9):45-52.CHEN Xuefeng, LI Jimeng, CHENG Hang, et al. Research and application of condition monitoring and fault diagnosis technology in wind turbines[J]. Journal of Mechanical Engineering, 2011, 47(9):45-52.
[2] ZHOU Q, XIONG T T, WANG M B, et al. Diagnosis and early warning of wind turbine faults based on cluster analysis theory and modified ANFIS[J]. Energies, 2017,10(7):898.
[3] CHEN B, MATTHEWS P, TAVNER P. Automated on-line fault prognosis for wind turbine pitch systems using supervisory control and data acquisition[J]. IET Renewable Power Generation, 2014, 9(5):503-513.
[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 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.
[5] BI R, ZHOU C, HEPBURN D M, et al. A NBM based on P-N relationship for DFIG wind turbine fault detection[C].2015 International Conference on Smart Grid and Clean Energy Technologies(ICSGCE). IEEE, 2016.
[6]董兴辉,闫慧丽,张晓亮.基于FDA贡献图的风电机组变桨系统故障定位[J].可再生能源, 2017, 35(1):93-100.DONG Xinghui, YAN Huili, ZHANG Xiaoliang. Fault location of pitch system based on FDA contribution diagram[J]. Renewable Energy Resources. 2017, 35(1):93-100.
[7]肖成,刘作军,张磊.基于SCADA系统的风电变桨故障预测方法研究[J].可再生能源, 2017, 35(2):278-284.XIAO Cheng, LIU Zuojun, ZHANG Lei. Variable pitch fault prediction of wind power system based on SCADA system[J]. Renewable Energy Resources, 2017, 35(2):278-284.
[8]巨林仓,史贝贝,杨清宇,等.基于LM算法建立风电机组神经网络故障预警诊断模型[J].热力发电, 2010,39(12):44-49.JU Lincang, SHI Beibei, YANG Qingyu, et al.Establishment of fault warning diagnosis model for wind power units based on lm algorithm of neural network[J].Thermal Power Generation, 2010, 39(12):44-49.
[9]徐创学,刘鲁清,谢云明,等.基于实时数据的风力发电机组性能在线评价[J].热力发电, 2015, 44(4):88-91.XU Chuangxue, LIU Luqing, XIE Yunming, et al.Real-time data based online evaluation of output performance for wind turbine units[J]. Thermal Power Generation, 2015, 44(4):88-91.
[10] WANG Y, INFIELD D, STEPHEN B, et al. Copulabased model for wind turbine power curve outlier rejection[J]. Wind Energy, 2014, 17(11):1677-1688.
[11] KUSIAK A, VERMA A. Monitoring wind farms with performance curves[J]. IEEE Transactions on Sustainable Energy, 2013, 4(1):192-199.
[12]邢作霞,张鹏飞,李媛.基于CFD技术的风电机组功率特性评估方法[J].太阳能学报, 2015, 36(12):2882-2887.XING Zuoxia, ZHANG Pengfei, LI Yuan. Evaluation method of power characteristics of wind turbine based on CFD technology[J]. Acta Energiae Solaris Sinica, 2015,36(12):2882-2887.
[13]陈警钰,陈玉航.基于INNER-DBSCAN和功率曲线模型的风机异常状态检测[J].电力科学与工程, 2017,33(8):27-34.CHEN Jingyu, CHEN Yuhang. Condition monitoring for wind turbines based on INNER-DBSCAN and power curve pattern[J]. Electric Power Science and Engineering, 2017,33(8):27-34.
[14]张家安,刘宁,吴林林,等.基于风力机功率特性的风资源评估?指标体系[J].太阳能学报, 2017, 38(2):498-502.ZHANG Jiaan, LIU Ning, WU Linlin, et al.?index system for wind resource assessment based on power characteristics of wind turbine[J]. Acta Energiae Solaris Sinica, 2017, 38(2):498-502.
[15]夏长亮.双馈风力发电系统设计与并网运行[M].北京:科学出版社, 2014:22-23.XIA Changliang. The design and grid-connected operations for double fed wind power generation system[M]. Beijing:Science Press, 2014:22-23.
[16]王明军.风电机组功率曲线问题及争议浅析[J].风能,2016(5):42-45.WANG Mingjun. Power curve problem and dispute analysis of wind turbines[J]. Wind Energy, 2016(5):42-45.
[17]王明军,高原生.风电机组实际运行功率曲线影响因素分析[J].风能, 2013(4):74-79.WANG Mingjun, GAO Yuansheng. An analysis of influence factors on wind turbine’s actual power curve[J]. Wind Energy, 2013(4):74-79.
[18]吴双群.风力发电原理[M].北京:北京大学出版社,2011:77.WU Shuangqun. Principle of the wind driven generator[M].Beijing:Peking University Press, 2011:77.
[19]赵振宙.风力机原理[M].北京:中国水利水电出版社,2016:45.ZHAO Zhenzhou. Principle of wind turbine[M]. Beijing:China Water&Power Press, 2016:45.
[2] ZHOU Q, XIONG T T, WANG M B, et al. Diagnosis and early warning of wind turbine faults based on cluster analysis theory and modified ANFIS[J]. Energies, 2017,10(7):898.
[3] CHEN B, MATTHEWS P, TAVNER P. Automated on-line fault prognosis for wind turbine pitch systems using supervisory control and data acquisition[J]. IET Renewable Power Generation, 2014, 9(5):503-513.
[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 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.
[5] BI R, ZHOU C, HEPBURN D M, et al. A NBM based on P-N relationship for DFIG wind turbine fault detection[C].2015 International Conference on Smart Grid and Clean Energy Technologies(ICSGCE). IEEE, 2016.
[6]董兴辉,闫慧丽,张晓亮.基于FDA贡献图的风电机组变桨系统故障定位[J].可再生能源, 2017, 35(1):93-100.DONG Xinghui, YAN Huili, ZHANG Xiaoliang. Fault location of pitch system based on FDA contribution diagram[J]. Renewable Energy Resources. 2017, 35(1):93-100.
[7]肖成,刘作军,张磊.基于SCADA系统的风电变桨故障预测方法研究[J].可再生能源, 2017, 35(2):278-284.XIAO Cheng, LIU Zuojun, ZHANG Lei. Variable pitch fault prediction of wind power system based on SCADA system[J]. Renewable Energy Resources, 2017, 35(2):278-284.
[8]巨林仓,史贝贝,杨清宇,等.基于LM算法建立风电机组神经网络故障预警诊断模型[J].热力发电, 2010,39(12):44-49.JU Lincang, SHI Beibei, YANG Qingyu, et al.Establishment of fault warning diagnosis model for wind power units based on lm algorithm of neural network[J].Thermal Power Generation, 2010, 39(12):44-49.
[9]徐创学,刘鲁清,谢云明,等.基于实时数据的风力发电机组性能在线评价[J].热力发电, 2015, 44(4):88-91.XU Chuangxue, LIU Luqing, XIE Yunming, et al.Real-time data based online evaluation of output performance for wind turbine units[J]. Thermal Power Generation, 2015, 44(4):88-91.
[10] WANG Y, INFIELD D, STEPHEN B, et al. Copulabased model for wind turbine power curve outlier rejection[J]. Wind Energy, 2014, 17(11):1677-1688.
[11] KUSIAK A, VERMA A. Monitoring wind farms with performance curves[J]. IEEE Transactions on Sustainable Energy, 2013, 4(1):192-199.
[12]邢作霞,张鹏飞,李媛.基于CFD技术的风电机组功率特性评估方法[J].太阳能学报, 2015, 36(12):2882-2887.XING Zuoxia, ZHANG Pengfei, LI Yuan. Evaluation method of power characteristics of wind turbine based on CFD technology[J]. Acta Energiae Solaris Sinica, 2015,36(12):2882-2887.
[13]陈警钰,陈玉航.基于INNER-DBSCAN和功率曲线模型的风机异常状态检测[J].电力科学与工程, 2017,33(8):27-34.CHEN Jingyu, CHEN Yuhang. Condition monitoring for wind turbines based on INNER-DBSCAN and power curve pattern[J]. Electric Power Science and Engineering, 2017,33(8):27-34.
[14]张家安,刘宁,吴林林,等.基于风力机功率特性的风资源评估?指标体系[J].太阳能学报, 2017, 38(2):498-502.ZHANG Jiaan, LIU Ning, WU Linlin, et al.?index system for wind resource assessment based on power characteristics of wind turbine[J]. Acta Energiae Solaris Sinica, 2017, 38(2):498-502.
[15]夏长亮.双馈风力发电系统设计与并网运行[M].北京:科学出版社, 2014:22-23.XIA Changliang. The design and grid-connected operations for double fed wind power generation system[M]. Beijing:Science Press, 2014:22-23.
[16]王明军.风电机组功率曲线问题及争议浅析[J].风能,2016(5):42-45.WANG Mingjun. Power curve problem and dispute analysis of wind turbines[J]. Wind Energy, 2016(5):42-45.
[17]王明军,高原生.风电机组实际运行功率曲线影响因素分析[J].风能, 2013(4):74-79.WANG Mingjun, GAO Yuansheng. An analysis of influence factors on wind turbine’s actual power curve[J]. Wind Energy, 2013(4):74-79.
[18]吴双群.风力发电原理[M].北京:北京大学出版社,2011:77.WU Shuangqun. Principle of the wind driven generator[M].Beijing:Peking University Press, 2011:77.
[19]赵振宙.风力机原理[M].北京:中国水利水电出版社,2016:45.ZHAO Zhenzhou. Principle of wind turbine[M]. Beijing:China Water&Power Press, 2016:45.