Please use this identifier to cite or link to this item:
|Title:||Analysis of significant factors on transformer failure by the Cox proportional hazards model||Authors:||Xu, Qianxin||Keywords:||Engineering::Electrical and electronic engineering::Electric power||Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Xu, Q. (2022). Analysis of significant factors on transformer failure by the Cox proportional hazards model. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/160985||Abstract:||As a hub for transforming voltage and exchanging power in the power system, transformers play an increasingly important role as the voltage level of the power system continues to increase and the power grid becomes more and more complex. Their safe and reliable operation will directly affect the safety level of the power system and is of great significance in improving the reliability level of the entire power system. Survival analysis has been applied in various fields, and the deep mining of transformer fault information can improve the analysis of transformer fault influencing factors. The Cox proportional hazards model can quantitatively analyze the influence of different risk factors on transformer life. The aim of this paper is to investigate the factors affecting transformer reliability and survival life. In order to demonstrate the usability of the model, the actual operation of transformers produced by an energy company is studied in order to quantitatively analyze the factors affecting transformer failure and to guide transformer operation and maintenance. This paper firstly investigates the typical life distribution of transformers and statistical modelling of failure data based on literature research etc.; secondly, it describes the basic concepts of survival analysis, the basic principles of the Cox proportional hazards model; the raw data is processed, the Cox model is implemented using transformer survival data containing multiple covariates, the regression results of the Cox model are interpreted according to different statistical indicators, and the visualization of the Cox model results to clearly illustrate the impact of covariates on transformers.||URI:||https://hdl.handle.net/10356/160985||Schools:||School of Electrical and Electronic Engineering||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Theses|
Updated on Sep 29, 2023
Updated on Sep 29, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.