Abstract
Support vector machine (SVM), which serves as one kind of artificial intelligence technique, has been widely employed in transformer fault diagnosis when involving dissolved gas analysis (DGA). However, when using SVM, it is easy to misclassify samples which are located near the decision boundary, resulting in a decrease in the accuracy of fault diagnosis. Given this issue, this paper proposed a genetic algorithm (GA) optimized probabilistic SVM (GAPSVM) integrated with the fuzzy three-ratio (FTR) method, in which the GAPSVM can judge whether a sample is near the decision boundary according to its output probabilities and diagnose the samples which are not near the decision boundary. Then, FTR is used to diagnose the samples which are near the decision boundary. Combining GAPSVM and FTR, the integrated model can accurately diagnose samples near the decision boundary of SVM. In addition, to avoid redundant and erroneous features, this paper also used GA to select the optimal DGA features. The diagnostic accuracy of the proposed GAPSVM integrated with the FTR fault diagnosis method reached 86.80% after 10 repeated calculations using 118 groups of IEC technical committee (TC) 10 samples. Moreover, the robustness is also proven through 30 groups of DGA samples from the State Grid Co. of China and 15 practical cases with missing values.
Highlights
Oil-immersed power transformers are important pieces of power transmission equipment in the power system
Back propagation neural network (BPNN), K-Nearest Neighbor, and GASVM are usually used in traditional power transformer fault diagnosis, when optimal DGA features (ODF) is adopted as the input feature of used in traditional power transformer fault diagnosis, when ODF is adopted as the input feature of these methods
The fault diagnosis accuracy reached 86.67%, which is higher than K-Nearest Neighbor (kNN) (66.67%), BPNN (73.33%), GASVM (73.33%), the method in [18] (80%), and the method in [19] (80%)
Summary
Oil-immersed power transformers are important pieces of power transmission equipment in the power system. The authors of [23] proposed an association rule mining method, which can select the most appropriate fault diagnosis method from two empirical rules and three AI-based classifiers These integrated methods have significantly improved the diagnostic accuracy. These methods only combine several classifiers and select the most effective classifier for diagnosing transformer fault types according to certain rules or optimization algorithms, resulting in a large time complexity in the calculation process. These studies have not pointed out the defects of each classifier. Taking into account the redundant or wrong features, this paper uses GA to screen the optimal DGA features (ODF) from 36 groups of generated features
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
