Background: Winding deformation is one of the most common faults that an operating power transformer experiences over its operational life. Thus it is essential to detect and rectify such faults at early stages to avoid potential catastrophic consequences to the transformer. At present, methods published in the literature for transformer winding fault diagnosis are mainly focused on identifying fault type and quantifying its extent without giving much attention to the identification of fault location. Methods: This paper presents a method based on a genetic algorithm and support vector machine (GA-SVM) to improve the faults’ classification of power transformers in terms of type and location. In this regard, a sinusoidal sweep signal in the frequency range of 600 kHz to 1MHz is applied to one terminal of the transformer winding. A mathematical index of the induced current at the head and end of the transformer winding under various fault conditions is used to extract unique features that are fed to a support vector machine (SVM) model for training. Parameters of the SVM model are optimized using a genetic algorithm (GA). Results : The effectiveness of mathematical indicators to extract fault type characteristics and the proposed fault classification model for fault diagnosis is demonstrated through extensive simulation analysis for various transformer winding faults at different locations. Conclusion : The proposed model can effectively identify different fault types and determine their location within the transformer winding, and the diagnostic rate of the fault type and fault location are 100% and 90%, respectively.
With the growing concerns over the energy crisis and environmental pollution, fuel cells have attracted increasing attention. Proton exchange membrane fuel cells (PEMFCs) have promising prospects due to their economic efficiency, low noise, and minimal environmental pollution. However, the existing commercial testing systems for PEMFCs suffer from limited functionalities and lack of scalability. In this study, we propose the design of a testing platform specifically tailored for water-cooled PEMFCs with a power greater than 1 kW. The functionality of the testing platform is verified through static and dynamic testing, demonstrating its compliance with the required standards. Furthermore, a fault diagnosis model for fuel cell stacks is developed based on the back-propagation (BP) neural network, achieving an overall accuracy rate of over 95% for fault classification.
Winding fault is one of the most common types of transformer faults. The frequency response method is a common diagnosis method for winding fault detection. In order to improve the feature extraction ability of the frequency response curve before and after the winding fault, this paper proposes a winding fault feature extraction method based on the moving window algorithm to improve the Euclidean distance and correlation coefficient and uses a support vector machine to diagnose winding fault. “Moving window meter algorithm” refers to the fixed moving window width and window moving interval, scanning the entire frequency response curve from the initial point to the end point of the frequency response curve, using the correlation coefficient (CC) and Euclidean distance (ED) to calculate the mathematical index of each window. The mathematical index of each window is used as the characteristic quantity of fault type classification. Finally, the grid search algorithm is used to optimize the support vector machine to classify and identify the type of winding fault. At the same time, the standard support vector machine s(SVM) and back propagation neural network algorithm (BPNN) are compared with the support vector machine optimized by the grid search method to diagnose the fault type. The research shows that the improved correlation coefficient and Euclidean distance using the moving window algorithm are more sensitive to winding faults than the traditional calculation methods. The combination of the two calculation methods makes up for the shortcomings of their respective methods. The fault features obtained meet the requirements of the support vector machine for fault diagnosis, and the grid search method-optimized support vector machine classification algorithm has a good classification and recognition effect on the identification of fault types. The effectiveness and superiority of this method are further illustrated.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.