More and more large capacity wind power will be integrated into power system in the future,and certain technical challenges will emerge due to the fluctuation characteristics of wind power and the complex control of p...More and more large capacity wind power will be integrated into power system in the future,and certain technical challenges will emerge due to the fluctuation characteristics of wind power and the complex control of power electronic devices inside the wind turbines(e.g.,low voltage ride through(LVRT)).By comparing a wind power integration grid with a hydropower integration grid,the special transient phenomena caused by the wind power integration is studied and simulation results are presented.Furthermore,the potential impacts on the traditional protection are discussed.Results show that the special transient phenomena can decrease the sensitivity,reliability and operation speed of conventional protections.展开更多
The characteristics of induction generator based fixed-speed wind turbines(FSWT)are investigated.The impacts of different execution time in protective operations are studied under different fault duration and various ...The characteristics of induction generator based fixed-speed wind turbines(FSWT)are investigated.The impacts of different execution time in protective operations are studied under different fault duration and various wind velocity situations,e.g.,FSWT stabilities of load shedding in distribution systems.Based on this research,a dynamic protective control strategy for a distributed generation system(DGS)with FSWT is proposed.Finally,simulation results demonstrate the effectiveness of the strategy.展开更多
With the rapid increase of wind farms,the grid code needs to be improved to meet the requirement of wind farms and enhance grid stability.Doubly-fed induction generators are largely used in wind turbines,but they are ...With the rapid increase of wind farms,the grid code needs to be improved to meet the requirement of wind farms and enhance grid stability.Doubly-fed induction generators are largely used in wind turbines,but they are very sensitive to grid disturbances.The voltage swell can be caused by switching on capacitor banks or switching off large loads,which may result in the reversal of the power flow in the grid convertor;the current may flow from the grid into the DC link,which may step up DC voltage,and result in large faults of rotor currents and instantaneous power oscillation.The grid reactive compensation devices can not have the automatic swithing function after the low voltage fault,which will result in local reactive power surplus,so some wind power generators will retreat from the grid under high voltage protection.展开更多
为了提高利用监控和数据采集(supervisory control and data acquisition,SCADA)多变量长时间序列预测齿轮箱油温的精度,解决不同风电机组因处不同运行环境导致的数据分布不一致的问题,提出了一种基于多分支时间序列预测与迁移学习相结...为了提高利用监控和数据采集(supervisory control and data acquisition,SCADA)多变量长时间序列预测齿轮箱油温的精度,解决不同风电机组因处不同运行环境导致的数据分布不一致的问题,提出了一种基于多分支时间序列预测与迁移学习相结合的齿轮箱状态监测方法。首先,利用极致梯度提升(extreme gradient boosting,XGBoost)算法筛选输入参数组成原始序列,对其进行分解得到季节与趋势序列。其次,提出季节、趋势序列特征提取模块获取季节及趋势特征的序列,将其与经过Informer模型处理后的特征序列进行融合后输入进多层感知机映射成最终的预测值,以构建提出的多分支时间序列预测网络(multi-branch time series prediction network,MBFN)。最后,利用迁移学习并结合一分类向量支持机(one-class support vector machine,OCSVM)模型及滑动窗口构建齿轮箱的健康指数,完成齿轮箱状态监测。实验结果表明,所提出模型的MBFN显著提高了油温预测精度,优于常规时间序列预测模型,所使用的迁移策略能以较少数据适应不同数据的分布,进而实现对齿轮箱的状态监测,并且所提出的模型可以提前18.9 d发出齿轮箱故障预警。展开更多
文摘More and more large capacity wind power will be integrated into power system in the future,and certain technical challenges will emerge due to the fluctuation characteristics of wind power and the complex control of power electronic devices inside the wind turbines(e.g.,low voltage ride through(LVRT)).By comparing a wind power integration grid with a hydropower integration grid,the special transient phenomena caused by the wind power integration is studied and simulation results are presented.Furthermore,the potential impacts on the traditional protection are discussed.Results show that the special transient phenomena can decrease the sensitivity,reliability and operation speed of conventional protections.
基金supported by the Danish Academy of Wind Energy(DAWE)
文摘The characteristics of induction generator based fixed-speed wind turbines(FSWT)are investigated.The impacts of different execution time in protective operations are studied under different fault duration and various wind velocity situations,e.g.,FSWT stabilities of load shedding in distribution systems.Based on this research,a dynamic protective control strategy for a distributed generation system(DGS)with FSWT is proposed.Finally,simulation results demonstrate the effectiveness of the strategy.
文摘With the rapid increase of wind farms,the grid code needs to be improved to meet the requirement of wind farms and enhance grid stability.Doubly-fed induction generators are largely used in wind turbines,but they are very sensitive to grid disturbances.The voltage swell can be caused by switching on capacitor banks or switching off large loads,which may result in the reversal of the power flow in the grid convertor;the current may flow from the grid into the DC link,which may step up DC voltage,and result in large faults of rotor currents and instantaneous power oscillation.The grid reactive compensation devices can not have the automatic swithing function after the low voltage fault,which will result in local reactive power surplus,so some wind power generators will retreat from the grid under high voltage protection.
文摘为了提高利用监控和数据采集(supervisory control and data acquisition,SCADA)多变量长时间序列预测齿轮箱油温的精度,解决不同风电机组因处不同运行环境导致的数据分布不一致的问题,提出了一种基于多分支时间序列预测与迁移学习相结合的齿轮箱状态监测方法。首先,利用极致梯度提升(extreme gradient boosting,XGBoost)算法筛选输入参数组成原始序列,对其进行分解得到季节与趋势序列。其次,提出季节、趋势序列特征提取模块获取季节及趋势特征的序列,将其与经过Informer模型处理后的特征序列进行融合后输入进多层感知机映射成最终的预测值,以构建提出的多分支时间序列预测网络(multi-branch time series prediction network,MBFN)。最后,利用迁移学习并结合一分类向量支持机(one-class support vector machine,OCSVM)模型及滑动窗口构建齿轮箱的健康指数,完成齿轮箱状态监测。实验结果表明,所提出模型的MBFN显著提高了油温预测精度,优于常规时间序列预测模型,所使用的迁移策略能以较少数据适应不同数据的分布,进而实现对齿轮箱的状态监测,并且所提出的模型可以提前18.9 d发出齿轮箱故障预警。
