Identification of faults within power transformers is the means of ensuring unit transformer protection. Existing relay maloperates during abnormalities such as magnetising inrush, CT saturation and high resistance internal fault condition. Therefore, it is essential to categorise the internal fault and external abnormality/fault in case of transformer protection. This study presents a new scheme, based on relevance vector machine (RVM) as a fault classifier. The developed algorithm is assessed by simulating various disorders on 345 MVA, 400/220 kV transformer in PSCAD/EMTDC software and also on prototype model with 2 kVA, 230/110 V multi-tapping transformer. One cycle post fault current signals are captured from primary and secondary to form feature vectors. These feature vectors are used as an input to RVM for classification of various test cases. Wide variation in system parameters and fault conditions are considered for test data generation and validation. The proposed scheme is compared with the support vector machine (SVM) and probabilistic neural network (PNN)-based techniques. The proposed scheme successfully discriminates various types of internal faults and external abnormalities in power transformer within a short time. The fault classification accuracy obtained by proposed RVM technique is more than 99% in comparison to SVM and PNN-based schemes.
To increase the classification accuracy of a protection scheme for power transformer, an effective convolution neural network (CNN) extreme gradient boosting (XGBoost) combination is proposed in this work. Data generated from various test cases are fed to one‐dimensional CNN for high‐level feature extraction. After that, an efficient classifier tool XGBoost is used to properly discriminate different transformer internal faults against outside abnormalities. A portion of an Indian power system is considered and simulated in PSCAD software using the multi‐run feature to collect a large number of data for various fault/abnormal situations. The generated data are used in MATLAB software where the proposed algorithm is programmed. A high‐performance CPU is used for training and testing purpose of the projected artificial intelligent technique. The obtained results for classification accuracy as well as discrimination time shows that the proposed scheme is competent enough to properly discriminate transformer operational conditions. Further, the combined CNN‐XGBoost technique is compared with existing relevance vector machine and hierarchical ensemble of extreme learning machine classifier techniques. Moreover, a hardware experiment is performed in a laboratory prototype of 50 kVA, 440/220 V transformer to verify the authenticity of the developed protective scheme. After analyzing a variety of experiments, the authors note that the presented method provides promising classification accuracy within a short time period.
Despite having several modern transformer protection schemes, the protection engineer prefers the universally adopted unit-type differential protection scheme for the current transformer (CT) because of its functional flexibility. Inrush condition, external fault with current transformer saturation, over-fluxing, or the combination of these may maloperate the unit-protection schemes. In this article, all the above-mentioned situations have been addressed that mislead differential protection. A multifunctional algorithm is presented that filters the disturbance for correct relay operation. The inrush condition is carefully examined with the help of the average angle of the differential current. Moreover, an adaptive algorithm takes care of the false operation of the transformer protection scheme during an external fault with CT saturation condition. Also, the momentary over-fluxing condition is dealt with, with the help of fifth-and seventh-harmonic-based analysis of the differential current. Hence, the disturbance will be thoroughly examined and a decision signal issued accordingly to avoid unnecessary isolation of the transformer to improve system stability. The power system is simulated in PSCAD software and the algorithm is developed in MATLAB. Moreover, the proposed scheme is validated on a hardware prototype for authentication. It is found that the proposed scheme provides acceptable results and can be implemented in the real field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.