A distribution network fault data analysis method based on association rule mining

Gao, Zhanjun; Peng, Zhengliang; Nuo, Gao; Chen, Bin

doi:10.1109/appeec.2014.7066121

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Fig. 3, A,B,C,D refer to the power source or end load of the distribution network [14], where, A,C is the main trunk line; a,b represents the cross node of the branch line and the trunk line, and the detection device is installed at the nodes [15].Then, fault interval points are calculated. The above three points constitute the maximum fault interval, and the thick dotted line is the potential fault interval [16,17].…”

Section: Fig 2 Equivalent Model Diagram Of Front Line Of Fault Intervalmentioning

confidence: 99%

Research on the Positioning Method of Single-Phase to Earth Fault in Distributed Distribution Network

Zhao

Cen

Shi

2021

Materials, Computer Engineering and Education Technology

View full text Add to dashboard Cite

The existing high-density distributed distribution network single-phase earth fault interval location method has the disadvantage of long positioning time. Hence, a single-phase earth fault interval positioning method for high-density distributed distribution network is proposed to solve this problem. In order to accurately locate the single-phase earth fault interval of distribution network, zero-order equivalent model of distribution network is built at first. Next the clustering algorithm is used to extract the single-phase earth fault characteristics, while the single-phase earth fault phase current increment is calculated by using the analysis method to obtain the single-phase earth fault phase current increment law. Then a fault-maximum interval T-shaped structure is built to divide the potential fault interval. Finally, the S-transformation is applied to accurately locate the single-phase earth fault interval, and the localization of the single-phase earth fault interval of the high-density distributed distribution network is achieved. The experimental results show that comparing with the existing high-density distributed distribution network single-phase earth fault interval positioning method, the proposed high-density distributed distribution network single-phase earth fault interval positioning method dramatically reduces the positioning time. It is fully explained that the proposed method in this article has a better positioning effect.

show abstract

Section: Fig 2 Equivalent Model Diagram Of Front Line Of Fault Intervalmentioning

confidence: 99%

Research on the Positioning Method of Single-Phase to Earth Fault in Distributed Distribution Network

Zhao

Cen

Shi

2021

Materials, Computer Engineering and Education Technology

View full text Add to dashboard Cite

show abstract

“…V. RELATED WORK Zhanjun et al [16] presents a new method of the distribution network fault diagnose based on data mining. The method synthetical analysises the spatial and temporal characteristics of fault information produced in the distribution network It uses APRIORI algorithm to mine the association rules of fault information and establish strong association rules database of fault attributes.…”

Section: Industrial Benefits Of the Studymentioning

confidence: 99%

Understanding Causes of Low Voltage (LV) Faults in Electricity Distribution Network Using Association Rule Mining and Text Clustering

Silva

Saraee

2019

2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Syst

View full text Add to dashboard Cite

In-depth understanding of a fault cause in electricity distribution network has always been of paramount importance to Distributed Network Operators (DNO) for a reliable power supply. Faults in the network have direct effect on its stability, availability and maintenance; and so, their quick elimination, prevention and avoidance of fault causes that generated them, is of special interest. Possible opportunity to understanding the causes and correlation of the factors where future faults may arise can significantly help electricity distribution operators who happen to be accountable to detect and repair such problems. Every asset in the distribution network has a different level of reliability and which may vary. Faults identifying in distribution network have rich literature but a very few studies had been done on understanding the factors that contribute to LV Faults using data mining and machine learning techniques. As there are lack of studies on Faults identifying in distribution network with data mining, this study will formulate a starting point. This paper aims to use the association rule mining and clustering techniques to understand the various hidden patterns from the faults database. The uncovered relationships can be represented in the form of Association rules and clusters. The outcomes of this research will hugely beneficial to the engineering departments in DNOs. New knowledge gain from this study will help to priorities investments in new or replacement infrastructure which will ensure that financial and manpower resources are used more efficiently.

show abstract

“…In the literature this analysis is known as discovering patterns in event sequences. One approach is based on finding association rules, and has been addressed by several researchers [1], [3], [5], [14]. Association rules are based on the frequency of the co-occurrence of features and conditional dependency between them.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Network representation of meaningful patterns in electricity distribution grids

Nemati

Sant'Anna

Nowaczyk

2016

2016 IEEE International Energy Conference (ENERGYCON)

View full text Add to dashboard Cite

Abstract-The diversity of components in electricity distribution grids makes it impossible, or at least very expensive, to deploy monitoring and fault diagnostics to every individual element. Therefore, power distribution companies are looking for cheap and reliable approaches that can help them to estimate the condition of their assets and to predict the when and where the faults may occur.In this paper we propose a simplified representation of failure patterns within historical faults database, which facilitates visualization of association rules using Bayesian Networks. Our approach is based on exploring the failure history and detecting correlations between different features available in those records. We show that a small subset of the most interesting rules is enough to obtain a good and sufficiently accurate approximation of the original dataset. A Bayesian Network created from those rules can serve as an easy to understand visualization of the most relevant failure patterns. In addition, by varying the threshold values of support and confidence that we consider interesting, we are able to control the tradeoff between accuracy of the model and its complexity in an intuitive way.

show abstract

A distribution network fault data analysis method based on association rule mining

Cited by 4 publications

References 3 publications

Research on the Positioning Method of Single-Phase to Earth Fault in Distributed Distribution Network

Research on the Positioning Method of Single-Phase to Earth Fault in Distributed Distribution Network

Understanding Causes of Low Voltage (LV) Faults in Electricity Distribution Network Using Association Rule Mining and Text Clustering

Bayesian Network representation of meaningful patterns in electricity distribution grids

Contact Info

Product

Resources

About