提出一种基于最小二乘支持向量机(LS-SVM,least squares support vectormachine)理论的故障预测算法,利用该理论方法的回归预测算法进行分析,选用径向基核函数(RBF)作为预测模型核函数,通过MATLAB建模仿真,验证了对风力发电机组故障的...提出一种基于最小二乘支持向量机(LS-SVM,least squares support vectormachine)理论的故障预测算法,利用该理论方法的回归预测算法进行分析,选用径向基核函数(RBF)作为预测模型核函数,通过MATLAB建模仿真,验证了对风力发电机组故障的较准确的实时预测。针对某风电场某台风机高速端轴承的振动数据进行特征参数预测研究,有效降低了模型的复杂度,且运算简单、精度高、收敛速度快。仿真结果表明,文中所提模型在预测精度和运算速度上都在很大程度上优于其他模型。展开更多
针对风力发电机组数据采集与监视控制系统(supervisory control and data acquisition,SCADA)监测参量间的耦合关联性,提出基于多参数耦合关联互信息编码的风电机组故障检测方法.该方法构建了SCADA数据的耦合关联矩阵,采用互信息变分自...针对风力发电机组数据采集与监视控制系统(supervisory control and data acquisition,SCADA)监测参量间的耦合关联性,提出基于多参数耦合关联互信息编码的风电机组故障检测方法.该方法构建了SCADA数据的耦合关联矩阵,采用互信息变分自编码器对关联矩阵进行编码重构;将SCADA参量关联矩阵的重构误差作为机组健康评估指标,结合指数加权移动平均模型的迭代更新,对机组实时故障阈值进行自适应设置.两个风场的风电机组SCADA数据分析结果表明,所提方法充分利用了SCADA数据的耦合关联结构信息,能有效提高风电机组故障检测的准确性及对环境工况的鲁棒性.展开更多
In order to ensure power system stability, modern wind turbines are required to be able to endure deep voltage dips. The specifications that determine the voltage dip versus time are called fault r/de-through （FRT） ...In order to ensure power system stability, modern wind turbines are required to be able to endure deep voltage dips. The specifications that determine the voltage dip versus time are called fault r/de-through （FRT） requirements. The purpose of this paper is not only to examine the FRT behavior of a full-power converter wind turbine but also to combine the power system viewpoint to the studies. It is not enough for the turbine to be FRT capable; the loss of mains （LOM） protection of the turbine must also be set to allow the FRT. Enabling FRT, however, means that the LOM protection settings must be loosen, which may sometimes pose a safety hazard. This article introduces unique real-time simulation environment and proposes an FRT method for a wind turbine that also takes the operation of LOM protection relay into account. Simulations are carried out using the simulation environment and results show that wind turbine is able to ride-through a symmetrical power system fault.展开更多
For the discrete-time system which is subjected to uncoupled actuator faults and sensor faults simultaneously,a robust fault diagnosis method based on a proportional integral observer (PIO) is presented.The proposed P...For the discrete-time system which is subjected to uncoupled actuator faults and sensor faults simultaneously,a robust fault diagnosis method based on a proportional integral observer (PIO) is presented.The proposed PIO uses an additionally introduced integral term of the output errors to obtain the estimationof actuator faults. Besides, the sensor faults are regarded as the augment states so that the PIO cantrace them. Moreover, the convergence of the PIO is proved. A variable speed wind turbine(VWT) exampleis given to demonstrate the fast convergence and diagnosis precision of the proposed PIO.展开更多
文摘提出一种基于最小二乘支持向量机(LS-SVM,least squares support vectormachine)理论的故障预测算法,利用该理论方法的回归预测算法进行分析,选用径向基核函数(RBF)作为预测模型核函数,通过MATLAB建模仿真,验证了对风力发电机组故障的较准确的实时预测。针对某风电场某台风机高速端轴承的振动数据进行特征参数预测研究,有效降低了模型的复杂度,且运算简单、精度高、收敛速度快。仿真结果表明,文中所提模型在预测精度和运算速度上都在很大程度上优于其他模型。
文摘针对风力发电机组数据采集与监视控制系统(supervisory control and data acquisition,SCADA)监测参量间的耦合关联性,提出基于多参数耦合关联互信息编码的风电机组故障检测方法.该方法构建了SCADA数据的耦合关联矩阵,采用互信息变分自编码器对关联矩阵进行编码重构;将SCADA参量关联矩阵的重构误差作为机组健康评估指标,结合指数加权移动平均模型的迭代更新,对机组实时故障阈值进行自适应设置.两个风场的风电机组SCADA数据分析结果表明,所提方法充分利用了SCADA数据的耦合关联结构信息,能有效提高风电机组故障检测的准确性及对环境工况的鲁棒性.
文摘In order to ensure power system stability, modern wind turbines are required to be able to endure deep voltage dips. The specifications that determine the voltage dip versus time are called fault r/de-through （FRT） requirements. The purpose of this paper is not only to examine the FRT behavior of a full-power converter wind turbine but also to combine the power system viewpoint to the studies. It is not enough for the turbine to be FRT capable; the loss of mains （LOM） protection of the turbine must also be set to allow the FRT. Enabling FRT, however, means that the LOM protection settings must be loosen, which may sometimes pose a safety hazard. This article introduces unique real-time simulation environment and proposes an FRT method for a wind turbine that also takes the operation of LOM protection relay into account. Simulations are carried out using the simulation environment and results show that wind turbine is able to ride-through a symmetrical power system fault.
基金Supported by the National Science & Technology Pillar Program in the Eleventh Five-year Plan Period (No. 2007BAF10B00).
文摘For the discrete-time system which is subjected to uncoupled actuator faults and sensor faults simultaneously,a robust fault diagnosis method based on a proportional integral observer (PIO) is presented.The proposed PIO uses an additionally introduced integral term of the output errors to obtain the estimationof actuator faults. Besides, the sensor faults are regarded as the augment states so that the PIO cantrace them. Moreover, the convergence of the PIO is proved. A variable speed wind turbine(VWT) exampleis given to demonstrate the fast convergence and diagnosis precision of the proposed PIO.
