Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

Abstract

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%.

Power quality disturbances classification using rotation forest and multi‐resolution fast S‐transform with data compression in time domain

“…RF can achieve a higher classification accuracy under 100 base classifiers, the increase of the number of base classifiers does not contribute much to the classification effect, but the classification efficiency will be affected. The detailed theoretical introduction and implementation process of RF algorithm are from literature [24]. DT is constructed by CART algorithm, which includes embedded feature selection method and can automatically select features in the process of building DT.…”

“…The discrete form of OMFST is expressed as where represents the reserved frequency point that is obtained after Otsu's [16, 24] threshold filtering, is the width factor of OMFST window. The corresponding relationship between and can be estimated as where represents the fitting function of the window width factor for harmonic analysis.…”

“…Rotation forest (ROF) [23] used in the proposed method is an excellent ensemble classification algorithm, which takes into account both the diversity between base classifiers and the classification accuracy. ROF has been applied to many fields of pattern recognition and achieved good classification results [24, 25]. Before building the subsample sets for base classifiers, the feature transformation strategy is applied to increase the diversity between base classifiers of ROF.…”

An Integrated Approach Based on Swarm Decomposition, Morphology Envelope Dispersion Entropy, and Random Forest for Multi-Fault Recognition of Rolling Bearing

“…Presented by Leo, random forest (RF) algorithm [39] is a non-parametric classification algorithm driven by data, which does not need prior knowledge. RF has been effectively applied in engineering cases [40][41][42]. Compared with other classification methods, RF has the characteristic of high accuracy, fast learning speed, good anti-noise and anti-singular value.…”

Analysis of Power Quality Signals Using an Adaptive Time-Frequency Distribution

“…In order to improve the PQ, utilities must first record the information about the statistical behavior of the voltage and current in a power system and subsequently analyze that information for the occurrence of disturbances in order to avoid any damage to the equipment. These requirements have sparked a lot of interest in the development of signal processing algorithms for the analysis of electrical PQ [1][2][3][4][5][6][7][8][9].…”