Series-arc-fault diagnosis using feature fusion-based deep learning model

This paper describes the detection of series arc faults, which constitute the major cause of electrical fires, in a power distribution system. Because the characteristics of series arc faults change considerably depending on the load type, their accurate detection and analysis are difficult. We propose a series-arc-fault detector that uses a transfer learning (TL)-based feature fusion model. The model is trained stagewise for various features in the time and frequency domains using a one-dimensional convolutional neural network combined with a long short-term memory model that uses an attention mechanism to accurately detect arc-fault features. To enhance the reliability of the proposed model, we implement an arc-fault generator compliant with the UL1699 standard and acquire high-quality data that suitably reflect the real environment. Experimental results show that the proposed model achieves an accuracy of 99.99% in classifying series arc faults for five different loads. Hence, a performance improvement of approximately 1.7% in classification accuracy is reached compared with a feature fusion model that does not incorporate TL-based model transfer and the attention mechanism.