Condition monitoring of high voltage apparatus is of much importance for the maintenance of electric power systems. Whether it is detecting faults or partial discharges that take place in high voltage equipment, or detecting contamination and degradation of outdoor insulators, deep learning which is a branch of machine learning has been extensively investigated. Instead of using hand-crafted manual features as an input for the traditional machine learning algorithms, deep learning algorithms use raw data as the input where the feature extraction stage is integrated in the learning stage, resulting in a more automated process. This is the main advantage of using deep learning instead of traditional machine learning techniques. This paper presents a review of the recent literature on the application of deep learning techniques in monitoring high voltage apparatus such as GIS, transformers, cables, rotating machines, and outdoor insulators.

This study presents a comprehensive review of the automated classification in partial discharge (PD) source identification and probabilistic interpretation of the classification results based on the relationship between the variation of the phase‐resolved PD (PRPD) patterns and the source of the PD. The proposed automated classification system consists of modern, high‐performance statistical feature extraction methods and classifier algorithms. Their application in online monitoring and recognition of the PD patterns is investigated based on their low‐processing time and high‐performance evaluation. The application of modern statistical algorithms and pre‐processing methods configured in this automated classification system improves the pattern recognition accuracy of the different PD sources that are suitable to be employed in different high‐voltage (HV) insulation media. To evaluate the performance of the different combinations of the feature extraction/classier pairs, laboratory setups are designed and built that simulate various types of PDs. The test cells include three sources of PD in , two sources of PD in transformer oil, and corona in the air. Data samples for different classes of PD sources are captured under two levels of voltage and two different levels of noise. The results of this study evaluate the suitability of the proposed classification systems for probabilistic source identification in various insulation media. Furthermore, of importance to the problem of the PD source identification is to assign a ‘degree of membership’ to each PRPD pattern, besides assigning a class label to it. Some of the classifier algorithms studied in this study, such as fuzzy classifiers, are not only able to show high classification accuracy rate, but they also calculate the ‘degree of membership’ of a sample to a class of data. This enables probabilistic interpretation of a new PRPD pattern that is being classified. The determination of the degree of membership for future PRPD samples allows safer decision making based on the risk associated with the different sources of PD in HV apparatus.

This research provides conclusions that can partially cover the lack of knowledge related to the effects of ambient atmospheric conditions on DC electric power transportation. Two polymer insulating materials are used for completing this research study. Inside a climate chamber, the relative humidity is controlled and adjusted from 20% to 80% RH. Then, the samples are charged with positive or negative charges by applying to the corona‐generating ring of needles. The surface potential is measured using an electrostatic voltmeter and is converted into surface charge density later by applying the probe response matrix method. The pre‐charged samples are then stressed with high‐voltage negative or positive DC values inside the climate chamber over a range of controlled values of the surrounding air humidity until flashover takes place. The space charges, which can drift in the air gap to reach the solid surface, are highly affected by the level of the relative humidity of the surrounding air. Also, increasing humidity results in a reduction of the DC flashover inception voltage and a shorter time to flashover regardless of the voltage polarity. Moreover, the positive or negative flashover inception voltage of both materials increases with pre‐deposited negative charges while it decreases with pre‐deposited positive charges.

A transformer white box model based on multiconductor transmission line (MTL) theory in cylindrical coordinates has been developed. This model allows variable lengths in conductors to be incorporated into the MTL formulation. A 2D axisymmetric model for the windings is implemented using finite element method (FEM) to determine the per unit length capacitance and inductance matrices. The model is capable of producing voltage and current results in both the frequency and time domains for each turn in the winding. The results obtained using the proposed model has been compared with those from Numerical Electromagnetic Code (NEC) and measurements done by others. Applications of the proposed model in analyzing interturn voltages and the induced voltages on secondary windings have been investigated.

Grounding electrodes have an important role in electric power transmission and distribution systems. They are used to prevent excessive hazardous voltages due to ground potential rise in the case of system faults or lightning surges. The electrical properties of soil, which vary substantially with geographical location and time of year, affect the process considerably along with the properties of the grounding electrode itself, such as its dimensions. To have an accurate estimation of the induced overvoltages due to lightning strike, one has to take into account the effect of the value of the soil electrical parameters, such as the electrical conductivity and dielectric constant. This study investigates the high frequency behaviour of the grounding electrodes by solving a full‐wave electromagnetic problem using the finite element method. The focus of this paper is on the effect of the variation of soil relative permittivity on the induced transient voltage in grounding electrodes. This allows an evaluation of the response of grounding systems due to seasonal changes, which would cause its electrical properties to vary significantly. This study demonstrates the importance of considering the variation of relative permittivity of the soil especially in the modelling of electrodes buried in highly resistive soil.