This paper examines the recent advances made in the field of Deep Learning (DL) methods for the automated identification of Partial Discharges (PD). PD activity is an indication of the state and operational conditions of electrical equipment systems. There are several techniques for on-line PD measurements, but the typical classification and recognition method is made off-line and involves an expert manually extracting appropriate features from raw data and then using these to diagnose PD type and severity. Many methods have been developed over the years, so that the appropriate features expertly extracted are used as input for Machine Learning (ML) algorithms. More recently, with the developments in computation and data storage, DL methods have been used for automated features extraction and classification. Several contributions have demonstrated that Deep Neural Networks (DNN) have better accuracy than the typical ML methods providing more efficient automated identification techniques. However, improvements could be made regarding the general applicability of the method, the data acquisition, and the optimal DNN structure.

No abstract

On-line measurement and monitoring of partial discharges in an MV cable system, including terminations and joints, is a challenging subject because it interacts with other components of the distribution network such as ring main units. The stochastic nature of partial discharges, the different configurations of the network, the external noise and the lack of standard recommendations have consequentially made the quantification of this phenomena more difficult. This paper is an attempt to investigate the behaviour of a theoretical pulse propagation and a real partial discharge in different circuits with almost the same configuration, that can be easily configured in a real Smart Grid laboratory. Several experiments and measurements were performed in order to compare these circuits and to find a factor that represents the influence of different circuit components to use as a reference or calibration to ensure the validity of further measurements.