DA-DCGAN: An Effective Methodology for DC Series Arc Fault Diagnosis in Photovoltaic Systems

Abstract

DC arc faults, especially series arcing, can occur in photovoltaic (PV) systems and pose a challenging detection and protection problem. Machine learning-based methods are increasingly being used for fault diagnosis applications. However, the performance of such detection algorithms will degrade because of variations between the source domain data used during the development and the target domain data encountered in operation of the field. Furthermore, the fault’s data in the target domain for model training are usually not available. In this paper, domain adaptation combined with deep convolutional generative adversarial network (DA-DCGAN)-based methodology is proposed, where DA-DCGAN first learns an intelligent normal-to-arcing transformation from the source-domain data. Then by generating dummy arcing data with the learned transformation using the normal data from the target domain and employing domain adaptation, a robust and reliable fault diagnosis scheme can be achieved for the target domain. The PV loop current is framed and arranged into a 2D matrix as input for cross-domain DC series arc fault diagnosis. The system is validated offline using pre-recorded PV loop current data from a real 1.5-kW grid-connected rooftop PV system. Also, the proposed method is implemented in an embedded system and tested in real-time according to UL-1699B standard. The experimental results clearly demonstrate benefits of DA-DCGAN and confirm the effectiveness of the proposed methodology for practical PV applications.