Fault analysis with modular neural networks

Rodríguez, Carlos Larrinaga; Rernentería, S.; Martín, Jesús Izquierdo; Lafuente, Alberto; Muguerza, Javier; Pérez, Juan Carlos

doi:10.1016/0142-0615(95)00007-0

Cited by 10 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the convergence and accuracy problem incurred from a monolithic ANN for the whole power system, the hierarchical and modular neural networks were suggested [17], [18]. The ANN is divided into levels, which the lowest one models and diagnoses each section, and upper ones perform integration tasks.…”

Section: Case Studiesmentioning

confidence: 99%

“…Recently, artificial neural network (ANN) approaches have been extensively applied to power system fault diagnosis [13]- [18]. Fundamental capabilities of ANN in on-line fault diagnosis have been verified, but certain practical problems remain unsolved, e.g., slow convergence in training, and manual determination of the network structure and parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Abductive reasoning network based diagnosis system for fault section estimation in power systems

Huang

2002

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

This paper presents an abductive reasoning network (ARN) for real-time fault section estimation in power systems. The proposed ARN handles complicated and knowledge-embedded relationships between the circuit breaker status (input) and the corresponding candidate fault section (output) using a hierarchical network with several layers of function nodes of simple low-order polynomials. The relay status is then further used to validate the final fault section. Test results confirm that the proposed diagnosis system can obtain rapid and accurate diagnosis results with flexibility and portability for diverse power system fault diagnosis. In addition, the proposed method performs better than the artificial neural networks (ANN) classification method both in developing the diagnosis system and in estimating the practical fault section. Moreover, this study demonstrates the feasibility of applying the proposed method to real power system fault diagnosis.Index Terms-Abductive reasoning network (ARN), fault section estimation, power systems.

show abstract

Section: Case Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Abductive reasoning network based diagnosis system for fault section estimation in power systems

Huang

2002

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

show abstract

“…Most of the times the elements pointed out after this stage will coincide with the most probable ones proposed in the generation phase. There are fault situations in which, according to domain experts, some improvement of the initial diagnosis is possible, however, in the sense of rejecting the most probable hypothesis in favor of a less probable one [30]. Such inconsistencies can only be detected when all the candidate fault hypotheses are globally accounted for.…”

Section: G Operation: Hypothesis Justilficationmentioning

confidence: 99%

A modular neural network approach to fault diagnosis

Rodríguez

Rementeria

Martín

et al. 1996

IEEE Trans. Neural Netw.

Self Cite

View full text Add to dashboard Cite

Certain real-world applications present serious challenges to conventional neural-network design procedures. Blindly trying to train huge networks may lead to unsatisfactory results and wrong conclusions about the type of problems that can be tackled using that technology. In this paper a modular solution to power systems alarm handling and fault diagnosis is described that overcomes the limitations of "toy" alternatives constrained to small and fixed-topology electrical networks. In contrast to monolithic diagnosis systems, the neural-network-based approach presented here accomplishes the scalability and dynamic adaptability requirements of the application. Mapping the power grid onto a set of interconnected modules that model the functional behavior of electrical equipment provides the flexibility and speed demanded by the problem. After a preliminary generation of candidate fault locations, competition among hypotheses results in a fully justified diagnosis that may include simultaneous faults. The way in which the neural system is conceived allows for a natural parallel implementation.

show abstract

Abductive Reasoning Network-Based Diagnosis System for Fault Section Estimation in Power Systems

Huang

2002

IEEE Power Eng. Rev.

View full text Add to dashboard Cite

Fault analysis with modular neural networks

Cited by 10 publications

References 18 publications

Abductive reasoning network based diagnosis system for fault section estimation in power systems

Abductive reasoning network based diagnosis system for fault section estimation in power systems

A modular neural network approach to fault diagnosis

Abductive Reasoning Network-Based Diagnosis System for Fault Section Estimation in Power Systems

Contact Info

Product

Resources

About