• KIEE International Transactions on Electrophysics and Applications
• /
• v.3C no.4
• /
• pp.130-135
• /
• 2003

This study describes neural network based dissolved gas analysis using composition patterns of gas concentrations for transformer fault diagnosis. DGA samples were gathered from related literatures and classified into six types of faults and then a neural network was trained using the DGA samples. Diagnosis tests were performed by the trained neural network with DGA samples of serviced transformers, fault causes of which were identified by actual inspection. Diagnosis results by the neural network were in good agreement with actual faults.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.1
• /
• pp.45-53
• /
• 1997

This paper presents hybrid expert system for diagnosis of electric power transformer faults. The expert system diagnose and detect faults in oil-filled power transformers based on dissolved gas analysis. As the preprocessing stage, fuzzy information theory is used to manage the uncertainty in transformer fault diagnosis using dissolved gas analysis. The Kohonen neural network takes the interim results by applying fuzzy informations theory as inputs, and performs the transformer fault diagnosis. The Proposed system tested gas records of power transformers from Korea Electric Power Corporation to verify the diagnosis performance of transformer faults.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.60 no.3
• /
• pp.114-119
• /
• 2011

Large Power transformer is a complex and critical component of power plant and consists of cellulosic paper, insulation oil, core, coil etc. Insulation materials of transformer and related equipment break down to liberate dissolved gas due to corona, partial discharge, pyrolysis or thermal decomposition. The dissolved gas kinds can be related to the type of electrical faults, and the rate of gas generation can indicate the severity of the fault. The identities of gases being generated are using very useful to decide the condition of transformation status. Therefore dissolved gas analysis is one of the best condition monitoring methods for power transformer. Also, on-line multi-gas analyzer has been developed and installed to monitor the condition of critical transformers. Rogers method, IEC method, key gas method and Duval Triangle method are used to failure diagnosis typically, and those methods are using the ratio or kinds of dissolved gas to evaluate the condition of transformer. This paper analyzes the reliability of transformer diagnostic methods considering actual dissolved gas concentration. Fault diagnosis is performed based on the dissolved gas of five transformers which experienced various fault respectively in the field, and the diagnosis result is compared with the actual off-line fault analysis. In this comparison result, Diagnostic methods using dissolved gas ratio like Rogers method, IEC method are sometimes fall outside the ratio code and no diagnosis but Duval triangle method and Key gas method is correct comparatively.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.54 no.5
• /
• pp.206-212
• /
• 2005

In this paper, criterion and algorithm for on-line dissolved gas of a Power transformer are studied. For the initial diagnosis of a power transformer, the on-line dissolved gas analysis is one of the most important and acceptable item to preventively diagnose a power transformer. But the criterion and algorithm of this item are not established yet in korea. In this paper, criterion and alarm level of the on-line dissolved gas analysis are based on the analysis of on-line data of operating transformers, Korea industrial standard and operation manual for a power transformer as well as accumulated data of the preventive diagnosis systems which have been operated at nine substations of Korea Electric Power Co.(KEPCO) since 1997, Therefore, the criterion and alarm level proposed in this paper are to be well suitable and are adaptable for the domestic operational environments and conditions of the power transformer. Considering that the conventional diagnosis system is capable only of accumulating and monitoring data of the power transformer operation, the criteria and the algorithms make it possible to accomplish an ultimate goal of the preventive diagnosis system. It is expected, therefore, that they will have a beneficial effect on broad applications of the preventive diagnosis system and the achievement of manless substation system in the future.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.2058-2064
• /
• 2014

In transformer fault diagnosis, dissolved gas analysis (DGA) is been widely employed for a long period and numerous methods have been innovated to interpret its results. Still in some cases it fails to identify the corresponding faults. Due to the limitation of training data and non-linearity, the estimation of key-gas ratio in the transformer oil becomes more complicated. This paper presents Intuitionistic Fuzzy expert System (IFS) to diagnose several faults in a transformer. This revised approach is well suitable to diagnosis the transformer faults and the corresponding action to be taken. The proposed method is applied to an independent data of different power transformers and various case studies of historic trends of transformer units. It has been proved to be a very advantageous tool for transformer diagnosis and upkeep planning. This method has been successfully used to identify the type of fault developing within a transformer even if there is conflict in the results of AI technique applied to DGA data.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.2
• /
• pp.119-126
• /
• 2022

A growing number of gas-insulated transformers in underground power substations in urban areas are approaching 20 years of operation, the time when failures begin to occur. It is thus essential to prevent failure through accurate condition diagnosis of the given facility. Various solid insulation materials exist inside of the transformers, and the generated decomposition gas may differ for each gas-insulated equipment. In this study, a simulation system was designed to analyze the deterioration characteristics of SF₆ decomposition gas and insulation materials under the conditions of partial discharge and thermal fault for diagnosis of gas-insulated transformers. Degradation characteristics of the insulation materials was determined using an automatic viscometer and FT-IR. The analysis results showed that the pattern of decomposition gas generation under partial discharge and thermal fault was different. In particular, acetaldehyde was detected under a thermal fault in all types of insulation, but not under partial discharge or an arc condition. In addition, in the case of insulation materials, deterioration of the insulation itself rapidly progressed as the experimental temperature increased. It was confirmed that it was possible to diagnose the internal discharge or thermal fault occurrence of the transformer through the ratio and type of decomposition gas generated in the gas-insulated transformer.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1727-1731
• /
• 2004

We propose an ART2 neural network-based fault diagnosis method to diagnose of sensor in the gas monitoring system. In the proposed method, using thermal modulation of operating temperature of sensor, the signal patterns are extracted from the voltage of load resistance. Also, fault classifier by ART2 NN (adaptive resonance theory 2 neural network) with uneven vigilance parameters is used for fault isolation. The performances of the proposed fault diagnosis method are shown by simulation results using real data obtained from the gas monitoring system.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.143-145
• /
• 1996

This paper presents the hybrid type based expert system for fault diagnosis in transformers. The proposed system uses the novel fault diagnostic technique based on dissolved gas analysis(DGA) in oil-immersed transformers. The uncertainty of key gas analysis, norm threshold, and gas ratio boundaries are managed by using a fuzzy set. Also, the uncertainty of the fault diagnostic rules are handled by using fuzzy measures. Finally, kohnen's feature map performs fault classification in transformers. To verify the effectiveness of the proposed diagnosis technique, the hybrid type based expert system for fault diagnosis has been tested by using KEPCO's transformer gas records.

• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.4
• /
• pp.447-454
• /
• 2020

Since SF₆ gas was discovered in the early 1900s, it has been widely used as an insulation material for electrical equipment. While various indicators have been developed to diagnose oil-immersed transformers, there are still insufficient indicators for the diagnosis of gas-insulated transformers. When necessary, chemical diagnostic methods can be used for gas-insulated transformers. However, the field suitability and accuracy of those methods for transformer diagnosis have not been verified. In addition, since various types of decomposition gases are generated therein, it is also necessary to establish appropriate analysis methods to cover the variety of gases. In this study, a gas-insulated transformer was diagnosed through the analysis of decomposition gases. Reliability assessments of both simple analysis methods suitable for on-site tests and precise analysis methods for laboratory level tests were performed. Using these methods, a gas analysis was performed for the internal decomposition gases of a 154 kV transformer in operation. In addition, simulated discharge and thermal fault experiments were demonstrated. Each major decomposition gas generation characteristics was identified. The results showed that an approximate diagnosis of the inside of a gas-insulated transformer is possible by analyzing SO₂, SOF₂, and CO using simple analysis methods on-site. In addition, since there are differences in the types of decomposition gas generation patterns with various solid materials of the internal transformer, a detailed examination should be performed by using precise analysis methods in the laboratory.

• Ceramist
• /
• v.22 no.1
• /
• pp.70-81
• /
• 2019

Breath analysis is rapidly evolving as a non-invasive disease recognition and diagnosis method. Metal oxide gas sensors are one of the most ideal platforms for realizing portable, hand-held breath analysis devices in the near future. This paper reviewed the recent developments in metal oxide gas sensors detecting exhaled biomarker gases such as nitric oxides, acetone, ammonia, hydrogen sulfide, and hydrocarbons. Emphasis was placed on strategies to tailor sensing materials/films capable of highly selective and sensitive detection of biomarker gases with negligible cross-response to ethanol, the major interfering breath gas. Specific examples were given to highlight the validity of the strategies, which include optimization of sensing temperature, doping additives, utilizing acid-base interaction, loading catalysts, and controlling gas reforming reaction. In addition, we briefly discussed the design and optimization method of gas sensor arrays for implementing the simultaneous assessment of multiple diseases. Breath analysis using high-performance metal oxide gas sensors/arrays will open new roads for point-of-care diagnosis of diseases such as asthma, diabetes, kidney dysfunction, halitosis, and lung cancer.