Classification of Many Abnormal Events in Radial Distribution Feeders Using the Complex Morlet Wavelet and Decision Trees

Almalki, Mishari Metab; Hatziadoniu, Constantine J.

doi:10.3390/en11030546

Cited by 9 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By considering an orthogonal wavelet decomposition (W) in the wavelet packet node level (WP), the division of approximation coefficients creates a tree structure of two vectors: the first one is the approximation coefficient vector, and the second one can be defined as a detailed vector [35]. The information lost during the approximation procedure is captured in the previously mentioned coefficients and a new vector is created.…”

Section: Features Extractionmentioning

confidence: 99%

Electrical Insulator Fault Forecasting Based on a Wavelet Neuro-Fuzzy System

et al. 2020

View full text Add to dashboard Cite

The surface contamination of electrical insulators can increase the electrical conductivity of these components, which may lead to faults in the electrical power system. During inspections, ultrasound equipment is employed to detect defective insulators or those that may cause failures within a certain period. Assuming that the signal collected by the ultrasound device can be processed and used for both the detection of defective insulators and prediction of failures, this study starts by presenting an experimental procedure considering a contaminated insulator removed from the distribution line for data acquisition. Based on the obtained data set, an offline time series forecasting approach with an Adaptive Neuro-Fuzzy Inference System (ANFIS) was conducted. To improve the time series forecasting performance and to reduce the noise, Wavelet Packets Transform (WPT) was associated to the ANFIS model. Once the ANFIS model associated with WPT has distinct parameters to be adjusted, a complete evaluation concerning different model configurations was conducted. In this case, three inference system structures were evaluated: grid partition, fuzzy c-means clustering, and subtractive clustering. A performance analysis focusing on computational effort and the coefficient of determination provided additional parameter configurations for the model. Taking into account both parametrical and statistical analysis, the Wavelet Neuro-Fuzzy System with fuzzy c-means showed that it is possible to achieve impressive accuracy, even when compared to classical approaches, in the prediction of electrical insulators conditions.

show abstract

Section: Features Extractionmentioning

confidence: 99%

Electrical Insulator Fault Forecasting Based on a Wavelet Neuro-Fuzzy System

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Morlet wavelet [40] provides an outstanding balance between the time-frequency domain in terms of localization, so this paper selects it as the mother wavelet function, which is expressed as:…”

Section: Xwt-based Dynamic Feature Extractormentioning

confidence: 99%

Real-Time Identification of False Data Injection Attacks: A Novel Dynamic-Static Parallel State Estimation Based Mechanism

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

Although cyber-physical system (CPS) enhances the monitoring ability of power systems, it also raises the threats of cyber-attacks. False data injection attacks (FDIAs) can evade the bad data detection (BDD) module to inject pre-designed false data into a subset of measurements without being observed. To mitigate the threats, this paper develops a real-time FDIAs identification mechanism for AC state estimation (SE) based on dynamic-static parallel SE. When the system is compromised by FDIAs, the decrease of temporal correlation of the parallel SE time series can effectively reveal the potential FDIAs. To further capture these sequential uncorrelation features presented in the system states and enhance the detection accuracy, we also employ the cross wavelet transform (XWT) to execute the time-frequency domain decomposition and cross-examination with the parallel SE time series. Case studies on several IEEE standard test systems verify the validity of the proposed mechanism. In addition, we conduct sensitivity tests of two influence factors of the proposed mechanism and analyze in depth. INDEX TERMSFalse data injection attacks (FDIAs), parallel state estimation (SE), cross wavelet transform (XWT), anomaly identification mechanism. NOMENCLATURE z, z a Natural/compromised measurement vector x, x a Natural/compromised state vector n, m Number of state variables/measurements e, R Measurement noise vector and its covariance r, r a Measurement residuals before/after the attack γ Detection threshold of LNR-based BDD a Attack vector c Change vector of x caused by attacks h(•) Measurement function k Subscript: time instant k P k Covariance matrix of state vector at instant k x UKF k

show abstract

“…In recent years, artificial intelligence has been involved in HIF detection. For example, reference introduces a method to detect and classify the HIFs by discrete wavelet transform and adaptive neuro‐fuzzy inference system. Reference describes the use of multiple algorithms to detect various types of faults and the use of an expert decision maker to decipher incoming data, to determine the status and health of a distribution feeder.…”

Section: Introductionmentioning

confidence: 99%

Detection of high‐impedance fault in distribution network based on time–frequency entropy of wavelet transform

Shu

Xiao

2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Due to the characteristics of small, nonlinear, random, and unstable current, the high impedance faults (HIF) are not always effectively cleared by conventional over current relays. A new simple and effective algorithm of HIF detection in distribution network based on the wavelet time-frequency entropy is presented in this article. On the basis of analysis, the time-frequency distribution characteristics in the concerned frequency band of HIFs by wavelet transform. The feature sequence developed by the wavelet time-frequency entropy at the time sequence is employed to detect HIF at substation. This criterion is calculated from the sum of wavelet time-frequency entropy at the time sequence every half cycle. If the value of the criterion is more than the threshold during four cycles, the HIF event can be identified. The developed detection method has been tested with real-world recorded signals from different HIF medium and PSCAD/EMTDC-generated signals. The result shows that the proposed method is robust to transients generated during normal events such as capacitor bank switching, load switching, and harmonic load. It has good performance for antinoise ability by noise reduction coefficient improved appropriately. And the proposed method has better reliability than the traditional third-harmonic-based method.

show abstract

Classification of Many Abnormal Events in Radial Distribution Feeders Using the Complex Morlet Wavelet and Decision Trees

Cited by 9 publications

References 25 publications

Electrical Insulator Fault Forecasting Based on a Wavelet Neuro-Fuzzy System

Electrical Insulator Fault Forecasting Based on a Wavelet Neuro-Fuzzy System

Real-Time Identification of False Data Injection Attacks: A Novel Dynamic-Static Parallel State Estimation Based Mechanism

Detection of high‐impedance fault in distribution network based on time–frequency entropy of wavelet transform

Contact Info

Product

Resources

About