Hermite Transform Based Algorithm for Detection and Classification of High Impedance Faults

Abstract

This work proposes a new algorithm to classify high impedance faults (HIFs) in distribution systems. HIFs can be represented by small current magnitudes with non-linear variations, which complicate their detection in distribution grids. The proposed method uses the Hermite transform (HT) as a signal processing technique that offers several advantages, one of the more important being the ability to analyze the signal at multiple resolution levels and at different frequency bands thanks to their filter functions based on Gaussian derivatives. The Hermite coefficients are used to extract signal features that allow efficient identification of the transient behaviour related to HIFs and other typical faults. In this sense, a multichannel approach based on the Hermite transform is proposed to classify different types of faults and HIFs. This analysis is carried out in a distribution network considering photovoltaic (PV) systems considering three different classifiers, which are also used to compare our results with the discrete wavelet transform (DWT) as signal decomposition model; the comparison suggests that our proposal presents better performance discriminating HIFs from typical faults.

High Impedance Fault Detection in Distribution Feeder Based on Spectrum Analysis and ANN with Non-Linear Load

“…Continuous monitoring of this feature is carried out with a moving standard deviation as an indicator to identify HIF. In reference [17], Hermite Transform (HT) was utilized to extract relevant features and then used K-Nearest Neighbor (KNN) to classify and differentiate HIF from other healthy events. A modified Gabor Wigner Transform (WT) was used in [8] to extract features in the form of 2-D scalograms, and CNN was utilized for HIF identification and classification.…”

“…ANNs are a potent programming tool for defect detection and classification that can address non-linear issues [26]. It has been demonstrated that ANN is an effective supervised learning method widely employed in machine learning [17]. A notable benefit of ANN is its capacity for parallel computation.…”

Equipment Detection and Maintenance in Mechanical Workshop Based on Anomaly Detection Algorithm

“…Users can search for the information they want anytime and anywhere through the network. The platform also provides technical services related to equipment detection and fault diagnosis for the machinery workshop with the help of internet technology and computer technology.So that business owners can master the operation and use of equipment in real time, monitor and maintain equipment in a timely manner, and avoid unnecessary losses [17][18].…”

Working State of Diesel Engine Cylinder Based on Continuous Wavelet Transform Algorithm

“…The vibration signal of diesel engine is unsteady and nonlinear. Because there are many vibration excitation sources of diesel engine, many noises are often mixed in the signal [17][18]. There are three main steps for the state detection of the cylinder.…”