Abstract
Fault type diagnosis is a very important tool to maintain the continuity of power transformer operation. Dissolved gas analysis (DGA) is one of the most effective and widely used techniques for predicting the power transformer fault types. In this paper, a convolutional neural network (CNN) model is proposed based on the DGA approach to accurately predict transformer fault types under different noise levels in measurements. The proposed model is applied with three categories of input ratios: conventional ratios (Rogers’4 ratios, IEC 60599 ratios, Duval triangle ratios), new ratios (five gas percentage ratios and new form six ratios), and hybrid ratios (conventional and new ratios together). The proposed model is trained and tested based on 589 dataset samples collected from electrical utilities and literature with varying noise levels up to ±20%. The results indicate that the CNN model with hybrid input ratios has superior prediction accuracy. The high accuracy of the proposed model is validated in comparison with conventional and recently published AI approaches. The proposed model is implemented based on MATLAB/toolbox 2020b.
Highlights
Power transformers are considered one of the vital equipment in the electric power system
A convolutional neural network (CNN) depends on random initialization, which means that different results are obtained each time the CNN is trained using the same dataset
The noise in Dissolved gas analysis (DGA) data was introduced to all samples with various levels ranging up to 20%
Summary
Power transformers are considered one of the vital equipment in the electric power system. These faults include the following types: 1) partial discharge (PD) represents by small carbonized captures in the paper; 2) low energy discharge (D1) causes large captures in paper and carbon particles in oil; 3) high energy discharge (D2) characterized by extensive carbonizations and metal fusion; 4) low and medium thermal faults (T1/T2) with oil temperature less than 300 °C for T1 and oil temperature greater than 300 °C and less than 700 °C for T2; 5) high thermal fault (T3) with oil temperature greater than 700 °C These abovementioned conventional methods failed in several cases to interpret the transformer faults due to some issues such as an outage of gas ratio combinations from predefined codes or dependence on only three combustible gases in Duval triangle. These new graphical representations could increase the diagnostic accuracy rather than the Duval triangle method [8]. Our main contributions are the augmentation of CNN training dataset with noisy points to improve the DGA diagnosis accuracy, and solving the DGA problem using different combinations of gas ratios and identifying the ratios that achieve the best detection accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
