A Novel Mechanical Fault Feature Selection and Diagnosis Approach for High-Voltage Circuit Breakers Using Features Extracted without Signal Processing.

Bin Wang,Jiajin Qi,Lingling Chen,Lin Lin,Nantian Huang

doi:10.3390/s19020288

Abstract

The reliability and performance of high-voltage circuit breakers (HVCBs) will directly affect the safety and stability of the power system itself, and mechanical failures of HVCBs are one of the important factors affecting the reliability of circuit breakers. Moreover, the existing fault diagnosis methods for circuit breakers are complex and inefficient in feature extraction. To improve the efficiency of feature extraction, a novel mechanical fault feature selection and diagnosis approach for high-voltage circuit breakers, using features extracted without signal processing is proposed. Firstly, the vibration signal of the HVCBs’ operating system, which collects the amplitudes of signals from normal vibration signals, is segmented by a time scale, and obviously changed. Adopting the ensemble learning method, features were extracted from each part of the divided signal, and used for constructing a vector. The Gini importance of features is obtained by random forest (RF), and the feature is ranked by the features’ importance index. After that, sequential forward selection (SFS) is applied to determine the optimal subset, while the regularized Fisher’s criterion (RFC) is used to analyze the classification ability. Then, the optimal subset is input to the hierarchical hybrid classifier, and based on a one-class support vector machine (OCSVM) and RF for fault diagnosis, the state is accurately recognized by OCSVM. The known fault types are identified using RF, and the identification results are calibrated with OCSVM of a particular fault type. The experimental proves that the new method has high feature extraction efficiency and recognition accuracy by the measured HVCBs vibration signal, while the unknown fault type data of the untrained samples is effectively identified.

Highlights

High-voltage circuit breakers (HVCBs) are the most important control and primary protection equipment in electric power systems [1,2]
Using one-class support vector machine (OCSVM) to avoid mistaken identifications of fault status, we further identified the unknown fault types accurately without training samples, through random forest (RF) and OCSVM
This paper proposes a novel mechanical fault feature selection and diagnosis approach for

Summary

Introduction

High-voltage circuit breakers (HVCBs) are the most important control and primary protection equipment in electric power systems [1,2]. Because of the differences in the degree of attenuation and starting time of the different types of fault vibration signals, HVCBs failure states can be analyzed by the time domain features when directly extracted from the original vibration signal. Selecting the optimal feature subset from higher-dimensional features extracted from original signals is the key to improve the efficiency and accuracy of HVCBs fault diagnosis. To improve the efficiency of feature extraction of vibration signals, and to avoid untrained samples of unknown type faults from being identified as normal or error known types, a new method of mechanical fault diagnosis for HVCBs based on feature extraction and selection without signal processing is proposed. The effectiveness of the new method is verified by the measured signal

Gini Importance

Random Forest

Construction of the Hierarchical Classifier

Signal Acquisition System

Feature on Time

Measured

Comparison of Classification Effects of Different Feature Extraction Methods

EMD-C1 0 10 0 0 10 0 153

Feature Selection

Sequential Forward Selection Based on RFC

Analysis of the Recognition

Findings