Fault section estimation in electrical power systems using artificial neural network approach

Aygen, Z.E.; Şeker, Serhat; Bagnyanik, M.; Bagnyanik, F.G.; Ayaz, Emine

doi:10.1109/tdc.1999.756098

Cited by 35 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A.2.4.3.6 Fault section estimation in electrical power systems using Artificial Neural Network (ANN) approach [43] Summary: This paper presents an ANN-based approach to estimate the faulty section in a power system by using the information from the protective relays and circuit breakers. The proposed approach is applied to a sample system where bus, transformer, and line protection schemes are considered.…”

Section: Issuesmentioning

confidence: 99%

Fault Locating, Prediction and Protection (FLPPS)

Yinger¹,

Venkata²,

Centeno³

2010

View full text Add to dashboard Cite

Section: Issuesmentioning

confidence: 99%

Fault Locating, Prediction and Protection (FLPPS)

Yinger¹,

Venkata²,

Centeno³

2010

View full text Add to dashboard Cite

“…deriving a unit state process that can best explain fault information, the appearance is maximum in which the joint probability of the unit state and fault information. At present, the electric product diagnosis approaches mainly include expert system [5], artificial neural nets [6,7], optimization method [8], and etc. When the fault information is precise and complete, these approaches can have satisfactory results.…”

Section: Bnc Implement Processmentioning

confidence: 99%

“…Calculate the after probability of some samples by present evidence, and the maximum after probability belongs to the class which sample belongs to. low temperature X 9 canker-elec X 3 wet-electrolyse X 10 rain X 4 low-dry X 11 eradiate X 5 high-compress X 12 ozone X 6 low-expand X 13 insulation X 7 wind X 14 Table 2 Fault classes NUM omen types NUM omen types C 1 insulated-destroy C 8 abrasion-add C 2 material-turn C 9 transmit-add C 3 spoilage C 10 ele-fault C 4 structure-destroy C 11 heat-ion C 5 pressurize-leak C 12 insulation-bad C 6 eletricity-arc C 13 struc-destroy C 7 low intensity C 14 struc-destroy BNC has the feature of condition independence, so as to reduce the complexity of knowledge gaining and deduction, and effectively process immaturity set. Because what BNC reflects is probability relationship among objects in the whole area.…”

Section: Fault Diagnosis Analysismentioning

confidence: 99%

An Initial Analysis of Fault Diagnosis to Electrical Apparatus Product on Bayesian

Liu

Wang

et al. 2006

2006 International Conference on Machine Learning and Cybernetics

View full text Add to dashboard Cite

This paper is based on the fault diagnosis analysis about electrical product of Bayesian network. Representing fault diagnosis as decision problem under ambiguity and immaturity of information. Bayesian network classifiers (BNC) is thus established which is based on the fault diagnosis of, and representing the ambiguity of information as probability description. Pre-process analysis is made to fault information and the attribute technology in term of maximum information entropy approach is brought forth. Realize electrical productfault diagnosis under the ambiguity and immaturity of information; further research and put forward probability study new arithmetic of BNC. Apply Bayesian network classifiers technology to electrical system fault diagnosis, and make it play a better role.

show abstract

“…This is because the protective relays of B8 in zone 2 are reduced 5 (L6-7s, L7-5s, L10-9s, L12-10s, L13-11s) to three (L7-5s, L12-10s, L13-11s) by the previous faults. Therefore, it is difficult to identify the fault in B8 [9]. However, it is possible to estimate that the fault sections are L6(0.9154), L10(0.9950), and B8(0.8500) from the fault-candidate matrix.…”

Section: Case Studymentioning

confidence: 99%

Adaptive Fault Section Estimation Using Matrix Representation With Fuzzy Relations

Min

Sohn

Park

et al. 2004

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

In this paper, a method for the fault section estimation that considers the network topology under the influence of a circuit breaker tripped by the previous fault is proposed. The proposed method uses a three-dimensional (3-D) matrix to represent the network topology and the protection systems. The proposed network matrix describes the sections that are protected by particular protective devices that can be changed according to the network topology. To deal with the uncertainties imposed on the protection systems, the fuzzy set theory was applied to the network matrix in order to examine the relationships between the operated protective devices and the fault section candidates. A systematic method for the fuzzy membership function for each relation is proposed. In the proposed method, the operated time sequences of the protective devices were employed because either the network matrix or the network topology varied whenever the operations of the circuit breakers occur. The efficiency and adaptivity of the proposed method were demonstrated in experimental studies on real power systems in the Korean electric power system, particularly in case of complicated multiple faults.Index Terms-Fault diagnosis, fuzzy set, power system.

show abstract

Fault section estimation in electrical power systems using artificial neural network approach

Cited by 35 publications

References 8 publications

Fault Locating, Prediction and Protection (FLPPS)

Fault Locating, Prediction and Protection (FLPPS)

An Initial Analysis of Fault Diagnosis to Electrical Apparatus Product on Bayesian

Adaptive Fault Section Estimation Using Matrix Representation With Fuzzy Relations

Contact Info

Product

Resources

About