Recognizing animal-caused faults in power distribution systems using artificial neural networks

Abstract

Faults are likely to occur in most power distribution systems. If the causes of the faults are known, specific action can be taken to eliminate the fault sources as soon as possible to avoid unnecessary costs, such as power system down-time cost, that are caused by failing to identify the fault sources. However, experts that can accurately recognize the causes of distribution faults are scarce and the knowledge about the nature of these faults is not easily transferable from person to person. Therefore, artificial neural networks are used in this paper to recognize the causes of faults in power distribution systems, based on fault currents information collected for each outage. Actual field data collected by Duke Power Company are used in this paper. The methodology and implementation of artificial neural networks and fuzzy logic for the identification of animal-caused distribution faults will be presented. Satisfactory results have been obtained, and the developed methodology can be easily generalized and used to identify other causes of faults in power distribution systems.

Time of outage restoration analysis in distribution systems

“…In [3], the authors have presented their work on estimating the outage causes based on the other factors considered in this paper, acheving satisfactory results. This implies that the factors under consideration may be correlated with each other as well.…”

Bayesian Network Model With Monte Carlo Simulations for Analysis of Animal-Related Outages in Overhead Distribution Systems

“…In the previous work, median values were used [3], but we have chosen the average values as they better represent the historical outage data. The median values are based on range of outages in each outage level, but the average values take account of the distribution of outages within the outage levels and thus can provide better characterization of the outage levels.…”

“…A lthough animals cause significant number of outages in overhead distribution systems [1][2][3][4][5][6][7], the exact causal relationship between them has not been addressed adequately in literature. Practical techniques for mitigating animal-caused outages have been presented [1,2].…”

“…Practical techniques for mitigating animal-caused outages have been presented [1,2]. Chow et al have focused on identifying and classifying animal-caused outages [3,4]. Models for estimating outages caused by animals with time of the year and weather conditions as inputs have been proposed previously by the authors of this paper [5][6].…”

Data classification using the Dempster–Shafer method

“…Section 3 describes the basic general principles for classifier system design using the theory. Sections 4, 5, and 6 provide information about the three standard benchmark problems, the Wisconsin Breast Cancer Dataset (WBCD) [1], the Iris Plant Dataset (IPD) [1], and the Duke Outage Dataset (DOD) [18][19][20][21][22][23][24][25][26] respectively. These sections also detail the individual D-S system architectures used for classifying each dataset, and present their results.…”