DEVELOPMENT OF FUZZY NEURAL NETWORK FOR THE INTERPRETATION OF THE RESULTS OF DISSOLVED IN OIL GASES ANALYSIS

Abstract

Purpose. The purpose of this paper is a diagnosis of power transformers on the basis of the results of the analysis of gases dissolved in oil. Methodology. To solve this problem a fuzzy neural network has been developed, tested and trained. Results. The analysis of neural network to recognize the possibility of developing defects at an early stage of their development, or growth of gas concentrations in the healthy transformers, made after the emergency actions on the part of electric networks is made. It has been established greatest difficulty in making a diagnosis on the criterion of the boundary gas concentrations, are the results of DGA obtained for the healthy transformers in which the concentration of gases dissolved in oil exceed their limit values, as well as defective transformers at an early stage development defects. The analysis showed that the accuracy of recognition of fuzzy neural networks has its limitations, which are determined by the peculiarities of the DGA method, used diagnostic features and the selected decision rule. Originality. Unlike similar studies in the training of the neural network, the membership functions of linguistic terms were chosen taking into account the functions gas concentrations density distribution transformers with various diagnoses, allowing to consider a particular gas content of oils that are typical of a leaky transformer, and the operating conditions of the equipment. Practical value. Developed fuzzy neural network allows to perform diagnostics of power transformers on the basis of the result of the analysis of gases dissolved in oil, with a high level of reliability.

Authors and Affiliations

V. Е. Bondarenko, O. V. Shutenko

Keywords

Related Articles

CONTROL SYSTEM FOR MULTILEVEL INVERTOR OF SOLAR POWER STATION

Purpose. The development of control law for network multilevel invertor of solar power station and design device for control law realization. Methodology. At synthesis of control law theory of automatic control, power ne...

COMPUTING EXPERIMENTS FOR CALCULATION OF ELECTROSTATIC AXISYMMETRIC FIELD IN PIECEWISE-HOMOGENEOUS INSULATION WITH SPHERICAL INCLUSIONS

Calculations of electrostatic axisymmetric field are made with application of solution to Fredholm integral equation of the first and the second kinds in a piecewise homogeneous isotropic linear polymeric insulation. On...

METHODICS, SOFTWARE AND LABORATORY EQUIPMENT FOR AN INNOVATIVE ELECTRICAL ENGINEERING DISCIPLINE

Purpose. Development of innovative electrical engineering discipline «Electric Machines in Mechatronic Systems» in order to improve the training of specialists of electrical engineering specialty. Methodology. The propos...

NUMERICAL COMPUTATION OF ELECTRIC FIELDS IN PRESENCE OF CURVILINEAR INTERFACE BETWEEN CONDUCTIVE AND NON-CONDUCTIVE MEDIA

Purpose. To elaborate a method of electric field numerical calculation in systems with curved boundaries between conductive and non-conductive media at final volume method usage and application of the rectangular grids....

A CALCULATION METHOD OF TRANSIENT MODES OF ELECTRIC SHIPS’ PROPELLING ELECTRIC PLANTS

The purpose of the work is to develop the method for calculating the transient modes of electric ships’ propelling electric plants during maneuver. This will allow us to evaluate and improve the maneuverability of vessel...

Download PDF file
  • EP ID EP292123
  • DOI 10.20998/2074-272X.2017.2.08
  • Views 123
  • Downloads 0

How To Cite

V. Е. Bondarenko, O. V. Shutenko (2017). DEVELOPMENT OF FUZZY NEURAL NETWORK FOR THE INTERPRETATION OF THE RESULTS OF DISSOLVED IN OIL GASES ANALYSIS. Електротехніка і Електромеханіка, 0(2), 49-56. https://europub.co.uk/articles/-A-292123