一种新型谐波电流检测策略

A New Harmonic Current Detection Method

针对传统ip-iq算法结构复杂、延时长、抗干扰能力差的问题,利用人工神经网络具有强大的自适应性以及对任意非线性逼近能力的特点,提出一种基于BP神经网络的谐波电流检测方法,在神经网络的输入端增加一附加量,将检测到的三相负载电流和虚拟磁链空间位置角作为神经网络系统输入,以改善神经网络的检测性能,提高检测的准确性。最后根据这种检测方法建立仿真模型,仿真结果验证了其优越性。

Harmonic detection is an important index to evaluate the harmonic control performance of active power filter.Considering the problems of complex structure , time delay , and poor anti - interference in tra - ditional ip - iq algorithm , and making use of the strong adaptability and the ability to approximate arbitrary nonlinear characteristics of artificial neural network , a harmonic current detection method based on BP neural network is proposed.An additional amount is added to the neural network input , and the detected three - phase load current and virtual flux linkage space position angle are taken as input neural network system , in order to improve the detection performance of the neural network and the accuracy of detection.Finally , a simulation model is established based on this method , whose results prove its superiority.