Arc faults are one of the important causes of electric fires. In order to solve the problem of randomness, diversity, the concealment of series arc faults and to improve the detection accuracy, a novel arc fault detection method integrated random forest (RF), improved multi-scale permutation entropy (IMPE) and wavelet packet transform (WPT) are designed. Firstly, singular value decomposition (SVD) was applied to filter the current signal and then the high-dimensional fault features were constructed by extracting IMPE, the wavelet packet energy and the wavelet packet energy-entropy. Afterward, the high-dimensional fault features were employed to train the RF to realize the arc fault detection of different load types and the experimental results verify the effectiveness of the arc fault detection method designed in this paper. Finally, the comparative experiments demonstrates that the RF shows better performance in arc fault detection compared to the back-propagation neural network (BPNN) and least squares support vector machines (LSSVM), and that the experiments of transient events indicate that RF is able to effectively avoid incorrectly detecting different load types during the start operations and stop operations.
Series arc fault (SAF) has severe impacts on the safety of DC power supply systems. Timely and accurate SAF detection under different operating conditions is an open and challenging problem. To address this problem, this paper proposes an integrated SAF detection method for different operating conditions. In the proposed method, dual-tree complex wavelet transform (DT-CWT) is employed to obtain an accurate current signal decomposition. The singular values of each wavelet component are then extracted by using an improved matrix construction method, which can effectively reduce the computational cost of constructing the high-dimension features. Finally, the kernel extreme learning machine (KELM) is applied to fuse the feature information for SAF detection. A series of experiments are presented to demonstrate the effectiveness of the proposed method. The results of off-line experiment show that the accuracy of the proposed method has higher detection accuracy than that of six state-of-the-art methods under different operating conditions. The proposed method is then embedded into the hardware of the experimental platform for online in-service implementation. The online experimental results show that the proposed method achieves fast and accurate SAF detection and, at the same time, offers outstanding reliability and stability in system dynamic transients.
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.