DEVELOPMENT OF FUZZY NEURAL NETWORK FOR THE INTERPRETATION OF THE RESULTS OF DISSOLVED IN OIL GASES ANALYSIS
Journal Title: Електротехніка і Електромеханіка - Year 2017, Vol 0, Issue 2
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
- EP ID EP292123
- DOI 10.20998/2074-272X.2017.2.08
- Views 115
- Downloads 0
RESEARCH INTO METHODS OF PIPE END DEMAGNETIZATION UNDER MAIN PIPELINE REPAIR
Efficiency of pipe end demagnetization methods is experimentally investigated to avoid arc magnetism at repair welding jobs on main pipelines. It is found that multi-polar biased static and dynamic demagnetization provid...
THE PHASE REACTOR INDUCTANCE SELECTION TECHNIQUE FOR POWER ACTIVE FILTER
Purpose. The goal is to develop technique of the phase inductance power reactors selection for parallel active filter based on the account both low-frequency and high-frequency components of the electromagnetic processes...
STATISTICAL PROCEDURES FOR TWO-SIDED LIMIT OF A CONTROLLED PARAMETER IN THE PROCESS OF PRODUCTION OF CABLE AND WIRE PRODUCTS
Purpose. To consider issues of statistical control in the process of mass production of cable and wire products on the example of enameled wire. To analyze the results of direct control of the diameter of the wire in two...
THE STRUCTURAL AND PARAMETRICAL ORGANIZATION OF ELEMENTS OF A POWER SUPPLY SYSTEM IN THE CONDITIONS OF NETWORK CENTRISM
Purpose. Development of indicators of the structural and parametrical organization of effective active and adaptive system of service of power supply systems in the conditions of ideology of Smart Grid. Methodology. In t...
INVESTIGATION AND CALCULATION OF VALLEYS OF OUTGOING FROM SUBSTATION GROUNDING CONDUCTORS FOR SHORT-CIRCUIT IN SINGLE-PHASE SHORT OF ELECTRICAL GRID
Introduction. Earthing device electrical substation in modern conditions must meet both the requirements of electrical safety of people and animals, as well as electromagnetic compatibility requirements established her e...