Using Bayesian Network for Fault Location on Distribution Feeder

Chien,; Chen, Guihai; Lin, Kun-You

doi:10.1109/mper.2002.4311700

Cited by 28 publications

(29 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This particular issue is discussed in some theoretical detail in [35], and there are also experimental results that illustrate this point. 3 That said, it is clear that our approach produces, for ADAPT, a BN that all three systems (ACE, JTP, and VE) perform well on. This illustrates that the ADAPT BN was carefully constructed, using our novel modeling approach and autogeneration algorithm, in a manner that supports efficient inference using three quite different exact inference algorithms.…”

Section: ) Designmentioning

confidence: 84%

See 1 more Smart Citation

Probabilistic Model-Based Diagnosis: An Electrical Power System Case Study

Mengshoel

Chavira

Cascio

et al. 2010

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

Abstract-We present in this paper a case study of the probabilistic approach to model-based diagnosis. Here, the diagnosed system is a real-world electrical power system (EPS), i.e., the Advanced Diagnostic and Prognostic Testbed (ADAPT) located at the NASA Ames Research Center. Our probabilistic approach is formally well founded and based on Bayesian networks (BNs) and arithmetic circuits (ACs). We pay special attention to meeting two of the main challenges often associated with real-world application of model-based diagnosis technologies: model development and real-time reasoning. To address the challenge of model development, we develop a systematic approach to representing EPSs as BNs, supported by an easy-to-use specification language. To address the real-time reasoning challenge, we compile BNs into ACs. AC evaluation (ACE) supports real-time diagnosis by being predictable, fast, and exact. In experiments with the ADAPT BN, which contains 503 discrete nodes and 579 edges and produces accurate results, the time taken to compute the most probable explanation using ACs has a mean of 0.2625 ms and a standard deviation of 0.2028 ms. In comparative experiments, we found that, while the variable elimination and join tree propagation algorithms also perform very well in the ADAPT setting, ACE was an order of magnitude or more faster.

show abstract

Section: ) Designmentioning

confidence: 84%

“…In several ways, this work is different from previous diagnosis efforts that utilize BNs, including EPS diagnosis [3], [4]. A first contribution is our expression of EPS components and structure, using a novel high-level language, coupled with autogeneration of BNs from models expressed in this language.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Model-Based Diagnosis: An Electrical Power System Case Study

Mengshoel

Chavira

Cascio

et al. 2010

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

show abstract

“…An identification of faulted sections and malfunctions of protection relays and CBs requires an extensive knowledge of the behavior of protection systems during various conditions [23][24][25][26][27]. Due to the fact that this problem is non-linear, largescale and often has a combinatorial nature, various artificial intelligence techniques have been explored and successfully used.…”

Section: A Fault Identification Problemmentioning

confidence: 99%

Computational intelligence applications to crisis management in power systems

Negnevitsky¹

2008

IJAAC

View full text Add to dashboard Cite

Abstract-In emergency and abnormal conditions, a power system operator has to deal with a large amount of data and apply most appropriate remedial actions. However, due to emotional and psychological stress, an operator may not be able to adequately respond to critical conditions and make correct decisions. Mistakes can damage very expensive power system equipment or worse lead to major emergencies and catastrophic situations. Intelligent systems can play an advisory role suggesting the necessary actions, which should be taken to deal with a given emergency or abnormal condition as well as identifying failures of protection systems and circuit breakers. This paper outlines some experience obtained at the School of Engineering of the University of Tasmania in developing intelligent systems for power systems security. An expert system for clearing overloads applies the network sensitivity factors to determine appropriate actions, which include generation rescheduling, network reconfiguration and load shedding. An expert system for voltage control is developed and used for detecting voltage violations and providing a set of effective control actions to solve voltage problems in real-time. An artificial neural network is used to identify multiple failures of protection relays and circuit breakers.This system uses information received from protection systems in the form of alarms and is able to deal with incomplete and distorted data.

show abstract

“…Mora-Flórez et al [13] developed a statistical classification algorithm based on fuzzy probability functions to locate single-phase faults. Chien et al [14] adopted a Bayesian network on the basis of expert knowledge and historical data for fault diagnosis. The Bayesian network imitates the causal relations between the fault equipment and the evidences of observations, and gives the possibilities that the failure is on each equipment.…”

Section: Introductionmentioning

confidence: 99%