On‐line identification model for single phase‐earth fault in distribution network driven by wavelet transform and multi‐learner combination

Abstract

The detection of single phase‐earth faults has been a difficult task for a long time due to its very low current in high impedance grounded fault especially in a neutral un‐effectively grounded system. To address this issue, this paper firstly proposes multi‐learner based single phase‐earth fault identification models. First, to erase disturb noise in fault recording profiles, a denoising model is put forward based on the wavelet transform optimized via the proposed threshold improvement approach. Second, feature engineering reflecting local and/or global evolutionary process of fault evolving features is modelled, and in turn two key feature transforming techniques of principal component analysis (PCA) and random forest (RF) are individually employed to recognize the best effective combination of fault feature set. Subsequently, six learners of logistical regression (LR), support vector machine (SVM), K‐neighbor (KN), RF, XGBoost and LightGBM based fault identification models are individually custom‐designed which the feature subset in high priority are fed into. Furthermore, to guide the model optimization, several advanced manners of hyper‐parametric sampling via normal and Chi‐2 distribution, learning curve, validation curve, receiver operation characteristic curve (ROC) are applied. Numerical studies indicates the the high value of the proposed model when applied in engineering practice.

Kernel‐PCA‐based single‐phase earth fault detection model using multilayer perceptron in deep learning

“…In real‐world scenarios, single‐phase earth faults present complicated and extremely changeable, where most of the current mainstream algorithms in this field merely fit the parts of these scenarios, due to their imperfect performance in representing fault characteristic. To fill this gap, our previous research [27] has conducted many studies and then put forward the method that constructs a set of fault features, about 16‐dimension, for example, three‐phase voltages, three‐phase currents, zero‐sequence voltage, zero‐sequence current, and zero‐sequence angle difference feature, which can enrich fault features and finally form an entire and valid feature engineering system taking into account stable/transient features of faulty network.…”

Three‐phase isolated power transformer based novel structure for power distribution system and new theoretical/practical judgement criteria in detecting high‐impedance earth faults

“…Specifically, these detecting approaches can be mainly categorized into three branches: injection method, steady‐state method, and transient method [5–9]. Considering that the advantages and drawbacks among them have in deep discussed and in detailed analyzed in our previous work [10], here only their basic concepts and the principals used in detecting single phase‐earth faults are provided and summarized in this section.…”