Fault location in transmission lines based on stationary wavelet transform, determinant function feature and support vector regression

Yusuff, Adedayo A.; Jimoh, A.A.; Munda, Josiah L.

doi:10.1016/j.epsr.2014.01.002

Cited by 59 publications

(27 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Malathi et al [6] Wavelet and SVM 1% 99.11% S. Eikici et al [7] Wavelet and ANN 2.05% -S. Eikici [8] Wavelet and SVM 1% 99% M. Jamil et al [9] Wavelet and GNN 2% -A.A. Yusuff et al [10] Wavelet and SVR 1% 100% S.R. Samantary [12] Wavelet, S and Fuzzy -98% of faults when dealing with noisy voltage signal database.…”

Section: Proposed By Reference Numbermentioning

confidence: 99%

“…In order to obtain improved results, wavelet entropy has been adopted to reduce the vector size regarding the detail coefficient as a preparation stage for the fault classification [8]. Generalized neural network (GNN), WT and support vector regression (SVR) have also been considered in this case providing errors lower than 2% [9,10]. It is worth to mention that errors rated at about 1% are acceptable since the practical effects are measured when dealing with distances measured in kilometers.…”

mentioning

confidence: 99%

See 1 more Smart Citation

ICA feature extraction for the location and classification of faults in high-voltage transmission lines

Almeida

Júnior

et al. 2017

Electric Power Systems Research

View full text Add to dashboard Cite

Section: Proposed By Reference Numbermentioning

confidence: 99%

mentioning

confidence: 99%

ICA feature extraction for the location and classification of faults in high-voltage transmission lines

Almeida

Júnior

et al. 2017

Electric Power Systems Research

View full text Add to dashboard Cite

“…The resistance and inductance of the transmission line are modelled as 5 Ω and 0.06 mH. The parameters described above are the initial setting and they can be extended for large size bus systems based on the real‐time applications.…”

Section: The Aco‐ and Pso‐based Fault Identification And Recovery Formentioning

confidence: 99%

“…The use of wavelet transform techniques aims to analyze the faults in short time intervals. The estimation of coefficients is the initial phase in detection, rectification, and classification of fault by using an adaptive neural network (ANN), fuzzy systems, classification and regression trees, and support vector machine (SVM) models . The research works in FACTS address the various processes injection of reactive power, regulation of power level, and optimization of fault rectification time in the fault analysis.…”

Section: Introductionmentioning

confidence: 99%

An enhanced ACO and PSO based fault identification and rectification approaches for FACTS devices

Vijayakumar¹,

Veeraraghavan

2017

Int. Trans. Electr. Energ. Syst.

View full text Add to dashboard Cite

Summary Major attributes of an electrical power network are the service continuity and high reliability. The occurrence of fault in the transmission line causes the disruption of attributes. If any fault occurs in the transmission line, the reactive power is generated to compensate the failure. The reactive power compensation is based on the utilization of flexible AC transmission system devices like static synchronous compensator (STATCOM) for power regulation. Many research works investigated the use of flexible AC transmission system in power systems for effective fault identification, classification, and localization. In traditional methods, the influence of fault on network parameters such as consumer gateway communication overhead, memory usage, consumer computational overhead, and critical time was more. This paper introduces a novel framework to identify, classify, and rectify the faults in the power transmission line and reduces the influence level of network parameters. Initially, the proposed algorithm detects the fault and ant colony optimization (ACO) and particle swarm optimization (PSO) are used to optimize the time and rectify the fault by the reactive power injection from static synchronous compensator. Finally, the identified faults are classified using relevance vector machine. The best fitness value by ACO‐PSO assures an effective reactive power generation and fault rectification. The proposed method outperforms the existing models regarding the detection, rectification of fault, and critical time required. The comparative analysis of proposed (ACO‐PSO) method with the existing methods confirms the effectiveness in assurance of high reliability and service continuity.

show abstract

“…Furthermore, fault detection has been a goal of power system engineers since the creation of distribution and transmission systems. Yusuff et al [7] developed a fault location methods use the combination of stationary wavelet transform, determinant function feature, and support vector machine at one or both ends of a transmission line to determine where a fault has occurred. Hasabe et al [8] presents a discrete wavelet transform and neural network approach to fault detection and classification in transmission lines.…”

Section: Introductionmentioning

confidence: 99%

Detecting Abrupt Changes in a Noisy van der Pol Type Oscillator

Nema

Kowalczyk

2015

Differ Equ Dyn Syst

View full text Add to dashboard Cite

Many signals produced by dynamical systems may undergo abrupt changes such as a jump or a sharp change. Detecting such change points is of primary importance in many applications ranging from exploratory data analysis to diagnosis. This paper addresses the detection of abrupt changes in a noisy van der Pol oscillator as a model of an electrical circuit with nonlinear resistance. The proposed approach combines wavelet analysis with information entropy in order to extract signal frequencies corresponding to any abrupt changes that occur. We also investigate the influence of noise intensity on detecting change points in the model system. Performance is evaluated on simulated data generated by using different model parameters.

show abstract

Fault location in transmission lines based on stationary wavelet transform, determinant function feature and support vector regression

Cited by 59 publications

References 28 publications

ICA feature extraction for the location and classification of faults in high-voltage transmission lines

ICA feature extraction for the location and classification of faults in high-voltage transmission lines

An enhanced ACO and PSO based fault identification and rectification approaches for FACTS devices

Detecting Abrupt Changes in a Noisy van der Pol Type Oscillator

Contact Info

Product

Resources

About