A time–frequency resolution technique based recognition of power system faults is proposed in the present work. Superlet transformation, a modified and super-resolution form of the wavelet transform, has been used to recognize the type of power system faults occurring in an interconnected power system. The Superlets were tested for sample power system disturbances and found advantageous. An IEEE-9 Bus system has been used to implement the proposed technique wherein it was observed that unique signatures were obtained for each type of fault. Further, to automatically recognize the type of power system faults, a Support Vector Machine (SVM) classifier has been introduced. The SVM is provided with the inputs from the extracted parameters of the proposed Superlets technique. It was found that the proposed methodology of Superlets with SVM has excelled in comparison with other techniques and provided 100% accuracy in the classification of all the events considered.

本文提出了一种基于时频分辨技术的电力系统故障识别方法。Superlet变换是小波变换的一种修改后的超分辨率形式，已被用于识别互连电力系统中发生的电力系统故障的类型。对Superlets进行了示例电力系统干扰测试，发现其优越性。IEEE-9总线系统已用于实施所提出的技术，其中观察到针对每种类型的故障均获得了唯一的签名。此外，为了自动识别电力系统故障的类型，引入了支持向量机（SVM）分类器。为SVM提供了从建议的Superlets技术的提取参数中获得的输入。