Analysis of Significant Factors on Cable Failure Using the Cox Proportional Hazard Model

Tang, Zeyang; Zhou, Chengke; Jiang, Wei; Zhou, Wenjun; Jing, Xiaoping; Yu, Jing; Alkali, Babakalli; Sheng, Bojie

doi:10.1109/tpwrd.2013.2287025

Cited by 67 publications

(34 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… demonstrated a nonparametric regression‐based failure rate model for transformers using life‐cycle data. The study compared their model with the existing time‐based and condition‐based models . Data mining is useful in this type of study where the aim is to train mathematical models and later use them for extended studies like reliability and maintenance optimization.…”

Section: Domains Of Asset Management and Advent Of Data Managementmentioning

confidence: 99%

A literature survey on asset management in electrical power [transmission and distribution] system

Khuntia

Rueda

Bouwman

et al. 2016

Int. Trans. Electr. Energ. Syst.

View full text Add to dashboard Cite

SUMMARYAsset management is one of the key components in a transforming electric power industry. Electric power industry is undergoing significant changes because of technical, socio-economical and environmental developments. Also, because of restructuring and deregulation, the focus has been on transmission and distribution assets that include transmission lines, power transformers, protection devices, substation equipment and support structures. This study aims to provide a detailed exposure to asset management classification, various interesting maintenance methods and theories developed. The work encompasses the issue of data management in recent years. Because of the use of various smart metering devices, large amounts of information are being collected. The advent of data-mining techniques has changed the asset management scenario, and it has been covered in this survey paper. In the end, it also discusses various risk assessment techniques in asset management developed and used for academic research and industries. It is accompanied with survey results from pan-European Transmission System Operator (TSOs) on various aspects in asset management.

show abstract

Section: Domains Of Asset Management and Advent Of Data Managementmentioning

confidence: 99%

A literature survey on asset management in electrical power [transmission and distribution] system

Khuntia

Rueda

Bouwman

et al. 2016

Int. Trans. Electr. Energ. Syst.

View full text Add to dashboard Cite

show abstract

“…In [10] the Cox proportional hazard model is used for analyzing burn-in failures of medium and high voltage cables and cable joints from a regional electricity company in China. The explanation variables used in the study where: the installing company, the manufacturer, the method of Fig.…”

Section: Review Of Papers Using Failure Rate Factorsmentioning

confidence: 99%

Categorization and review of failure rate factors used in power systems

Ekstedt

Hilber

2014

2014 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)

View full text Add to dashboard Cite

Abstract-To evaluate the reliability of power systems, good estimates of the failure rates of the included components are needed. Better predictions can be performed if relevant factors that affect the failure rates are used, and an increasing number of models that include different types of factors have been presented recently. This paper proposes a categorization of failure rate factors into seven categories, based on the type of information for the factors. The categorization can be used to map future studies in the context of similar work. Furthermore, the paper presents a review of a number of publications that uses different factors to model the failure rate of different power system components. The failure rate factors used in the reviewed publications are categorized into the proposed seven categories and a comprehensive summary table is included. The used models and methods to estimate the failure rate in the reviewed publications are also noted in the summary table.

show abstract

“…The development process of cable failure is usually divided into three stages: the partial discharge period, incipient failure period and permanent failure period [1]. Due to defect formation, corrosion or aging of the insulating layer, a series of partial discharge pulses first appear in the cable, forming electrical or water branches.…”

Section: Introductionmentioning

confidence: 99%

Recognition and Classification of Incipient Cable Failures Based on Variational Mode Decomposition and a Convolutional Neural Network

2019

View full text Add to dashboard Cite

To avoid power supply hazards caused by cable failures, this paper presents an approach of incipient cable failure recognition and classification based on variational mode decomposition (VMD) and a convolutional neural network (CNN). By using VMD, the original current signal is decomposed into seven modes with different center frequencies. Then, 42 features are extracted for the seven modes and used to construct a feature vector as input of the CNN to classify incipient cable failure through deep learning. Compared with using the original signals directly as the CNN input, the proposed approach is more efficient and robust. Experiments on different classifiers, namely, the decision tree (DT), K-nearest neighbor (KNN), BP neural network (BP) and support vector machine (SVM), and show that the CNN outperforms the other classifiers in terms of accuracy.

show abstract

Analysis of Significant Factors on Cable Failure Using the Cox Proportional Hazard Model

Cited by 67 publications

References 15 publications

A literature survey on asset management in electrical power [transmission and distribution] system

A literature survey on asset management in electrical power [transmission and distribution] system

Categorization and review of failure rate factors used in power systems

Recognition and Classification of Incipient Cable Failures Based on Variational Mode Decomposition and a Convolutional Neural Network

Contact Info

Product

Resources

About