Dissolved gas Analysis (DGA) is a widely used technique to estimate the condition of oil-immersed transformers. The measurement of the level and the change of combustible gases in the insulating oil is a trustworthy diagnostic tool which can be used as indicator of undesirable events occurring inside the transformer, such as hot spots, electrical arcing or partial discharge. The objective of this paper is mainly to analyze available data from DGA, and investigate data that may be useful in quantitative modeling of the transformer's reliability. There are standards available for this purpose the DGA interpretation should also be based on other information about the reliable particular transformer. This paper describes a realistic method for power transformers using readily available data. The method considers practical limitations on obtaining data and possible constraints on the parameters utilize IEC, IEEE, and OGRE criteria. The calculation considers not only typical test results but also other parameters such as physical observations, tap changer and bushing condition, load history, maintenance work orders, age, trends of the transformer failures etc. The calculation includes condition ratings, weighting factors, and assigned scores for specific condition parameters by using fuzzy logic. A neural network using the DGA results is applied to achieve the initial conclusion firstly. Then, several fuzzy equations are established to realize the detailed diagnosis. As many sorts of data and relevant DGA information are selected in different fuzzy equations, which result in the accuracy of the detailed diagnosis being higher.

Power transformers being the major apparatus in a power system, thus the assessment of transformer operating condition and lifespan have obtained crucial significance in latest years. Dissolved gas analysis (DGA) is a sensitive and reliable technique for the detection of incipient fault condition within oil-immersed transformers, which provides the basis of diagnostic evaluation of equipment health. The first part of this paper deals with an expert system that utilizes fuzzy logic implementation into dissolved gas in oil analysis technique. To improve the diagnosis accuracy of the conventional dissolved gas analysis (DGA) approaches, this part proposes a fuzzy system development technique based combined with neural networks (fuzzy-neural technique) to identify the incipient faults of transformers. Using the IEEE/IEC and National Standard DGA criteria as references, a preliminary framework of the fuzzy diagnosis system. In the second part, artificial neural network (ANN) based fault diagnosis is presented, which overcomes the drawbacks of the previously applied fuzzy diagnostic system that is it cannot learn directly from the data samples. These expert system also consider other information of transformer such as type, voltage level, maintenance history, with or without tap changer etc. These proposed approaches provide the user a more accurate result and better condition awareness of the transformer.