Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151531
Doc. No	:	ET23323
Main Entry	:	Zhenyuan Wang
Title Proper	:	Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	This dissertation is a systematic study of artificial intelligence (AI) applications for the diagnosisof power transformer incipient fault. The AI techniques include artificial neural networks (ANN,or briefly neural networks - NN), expert systems, fuzzy systems and multivariate regression.The fault diagnosis is based on dissolved gas-in-oil analysis (DGA). A literature review showedthat the conventional fault diagnosis methods, i.e. the ratio methods (Rogers, Dornenburg andIEC) and the key gas method, have limitations such as the ب‍no decisionپ problem. Various AItechniques may help solve the problems and present a better solution.Based on the IEC 599 standard and industrial experiences, a knowledge-based inference enginefor fault detection was developed. Using historical transformer failure data from an industrialpartner, a multi-layer perceptron (MLP) modular neural network was identified as the best choiceamong several neural network architectures. Subsequently, the concept of a hybrid diagnosis wasproposed and implemented, resulting in a combined neural network and expert system tool (theANNEPS system) for power transformer incipient diagnosis. The abnormal condition screeningprocess, as well as the principle and algorithms of combining the outputs of knowledge basedand neural network based diagnosis, were proposed and implemented in the ANNEPS. Methodsof fuzzy logic based transformer oil/paper insulation condition assessment, and....-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL46562.pdf
Title and statement of responsibility and	:	Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults [Thesis]