With an elevating demand and use of power electronics equipment, green energy and the development of smart grids, power quality disturbance detection and classification holds great importance. It is important not only from the technical point of view but from an economic perspective also. This paper presents a comprehensive review of the work done until now in the field of power quality disturbance detection and classification. In this paper, signal processing techniques such as Fourier transform (FT) and its variants (STFT, DFT, FFT), S transform (ST), Hilbert Huang transform (HHT), Wavelet transform (WT) along with machine learning techniques for classification such as Neural Networks (NN), Support Vector Machine (SVM), Fuzzy Logic (FL), Neuro Fuzzy (NF) techniques, Deep Learning methods etc. have been extensively reviewed. Different combinations of signal processing techniques with machine learning techniques have also been reviewed. Comparison and proper analysis of different techniques are given in tabular form along with the bona-fide review of the major work done hitherto in this domain. This paper may prove to be a good help for researchers working in the field of power quality disturbance detection and classification.

随着电力电子设备，绿色能源和智能电网的需求和使用的增加，电能质量扰动的检测和分类变得非常重要。不仅从技术角度来看很重要，而且从经济角度来看也很重要。本文对迄今为止在电能质量扰动检测和分类领域所做的工作进行了全面回顾。在本文中，信号处理技术（例如傅立叶变换（FT）及其变体（STFT，DFT，FFT），S变换（ST），希尔伯特·黄变换（HHT），小波变换（WT）以及用于分类的机器学习技术诸如神经网络（NN），支持向量机（SVM），模糊逻辑（FL），神经模糊（NF）技术，深度学习方法等已被广泛审查。信号处理技术与机器学习技术的不同组合也已被审查。以表格的形式对不同技术进行了比较和适当的分析，并对迄今为止在这一领域所做的主要工作进行了真诚的回顾。对于从事电能质量扰动检测和分类领域的研究人员，本文可能会提供很好的帮助。