Accurate Fault Location in the Power Transmission Line Using Support Vector Machine Approach

Sałat, Robert; Osowski, S.

doi:10.1109/tpwrs.2004.825883

Cited by 160 publications

(73 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results reached for the location of faults prove the very good performance of this research. SVM fault location (Robert Salat and Stanislaw Osowski (2004), [10] ) with + 4% error. The maximum errors of fault location for the proposed method is limited to 1.852km (double circuit) in the worst case and 7.874e -003 km (double circuit) in the best case with a short duration of time in each 50km line, the type of system which can locate the fault in EHV double circuit transmission line for double line to ground fault.…”

Section: Resultsmentioning

confidence: 99%

“…Table 3 gives the result numerical values of the FL error of hybrid approach for double circuit of double line to ground fault (100-150 km) with target value (t), actual value (a), and error value (c). SVM fault location (Robert Salat and Stanislaw Osowski (2004), [10] ) with + 4% error. The minimum error value of fault location for the proposed method is 7.874e -003 km and maximum error value is 1.852 km representing quite satisfactory results in double circuit fault location using hybrid approach as shown in Fig.…”

Section: Co-published By Atlantis Press and Taylor And Francismentioning

confidence: 99%

“…The design and implementation of an artificial neural networks based fault locator for EHV transmission lines are presented in [9]. The location of fault has been presented in the high-voltage power transmission line, support vector machine and frequency characteristics of the measured one-terminal voltage and current transient signals of the systems are reported in [10]. The fault location algorithm for the parallel lines with measurements at one end is delivered in [11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Double Circuit EHV Transmission Lines Fault Location with RBF Based Support Vector Machine and Reconstructed Input Scaled Conjugate Gradient Based Neural Network

Gayathri¹,

Kumarappan²

2015

IJCIS

View full text Add to dashboard Cite

A new algorithm is developed to enhance the solution for the problems associated with double circuit transmission lines for the mutual coupling between the two circuits under fault conditions and which is highly variable in nature. The algorithm depends on the three-line voltages and the six line currents of double circuit lines at one end. It relies on the application of Support Vector Machine (SVM) and frequency characteristics of the measured single end positive sequence voltage and current measurement of transient signals of the system. Fault resistance, mutual coupling between two circuits and initial prefault conditions are considered. The accuracy of this method has been assessed using a fault simulation software program. In the first state, the accuracy of the method was determined on the basis of SVM reconstructed method. In the second state, this method utilizes voltage and current data acquired at one common end of the two lines. This paper proposes a new hybrid approach for fault location on Extra High Voltage (EHV) lines using RBF based SVM with reconstructed input and Scaled Conjugate Gradient (SCALCG) based neural network method. Sample inputs are determined by MATLAB. The average error fault location in 400kV and 150km line is tested and the results prove that the proposed method is effective and reduces the error within a short duration of time using both RBF based reconstructed input of SVM and SCALCG based neural network.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Co-published By Atlantis Press and Taylor And Francismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Double Circuit EHV Transmission Lines Fault Location with RBF Based Support Vector Machine and Reconstructed Input Scaled Conjugate Gradient Based Neural Network

Gayathri¹,

Kumarappan²

2015

IJCIS

View full text Add to dashboard Cite

show abstract

“…Nevertheless, such a solution ensures that the sum of squared residuals is minimal, where a residual is defined as the difference between the measurement in and its corrected value obtained from . The sum of squared residuals corresponding to the faulted line -is obtained from (17) It should be pointed out that the current sources substituted for the actual faulted line are the unknowns for which (15) holds true. It means that is expected to take a negligible value for the faulted line, and large values for the other ones.…”

Section: B Extension To Meshed Transmission Networkmentioning

confidence: 99%

Locating Faults on Untransposed, Meshed Transmission Networks Using a Limited Number of Synchrophasor Measurements

Azizi

Sanaye‐Pasand

Paolone

2016

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

Abstract-The method of symmetrical components is not effective for fault location in the case of untransposed lines, due to potential couplings between the sequence circuits. This paper proposes a non-iterative algorithm in the phase-coordinates for wide-area fault location on untransposed transmission networks. In doing so, first, an improved two-terminal method is suggested to accurately locate faults on untransposed lines. Next, an algorithm is proposed to infer voltage and current phasors at the faulted line ends without direct measurements, by taking advantage of the data provided by phasor measurement units (PMUs). Accordingly, the adverse effect of close instrument transformers transients on the estimation accuracy is minimized. Being highly nonlinear in terms of fault distance and impedance, the fault equations are derived and made linear in this paper by defining six suitable auxiliary variables. The resulting system of equations is solved using the least-squares method to obtain three-phase voltages and currents at the faulted line ends. A main feature of the proposed algorithm is that it only requires a limited number of current and voltage synchrophasors. An additional advantage of the proposed algorithm is that the faulted line is not required to be known a-priori. The proposed algorithm is validated using extensive simulation studies on the New England 39-bus test system, accounting for different fault locations, types and resistances.

show abstract

“…In this case, the SVM maps the input vectors x into a high dimensional space through some nonlinear mapping (F function), where an optimal hyperplane is constructed [7], [8]. Schematic structure of the SVM network is shown in Fig.…”

Section: Support Vector Machinementioning

confidence: 99%

Automated Classification of Power-Quality Disturbances Using SVM and RBF Networks

Janík

Łobos

2006

IEEE Trans. Power Delivery

215

View full text Add to dashboard Cite

Accurate Fault Location in the Power Transmission Line Using Support Vector Machine Approach

Cited by 160 publications

References 14 publications

Double Circuit EHV Transmission Lines Fault Location with RBF Based Support Vector Machine and Reconstructed Input Scaled Conjugate Gradient Based Neural Network

Double Circuit EHV Transmission Lines Fault Location with RBF Based Support Vector Machine and Reconstructed Input Scaled Conjugate Gradient Based Neural Network

Locating Faults on Untransposed, Meshed Transmission Networks Using a Limited Number of Synchrophasor Measurements

Automated Classification of Power-Quality Disturbances Using SVM and RBF Networks

Contact Info

Product

Resources

About