Power electronic devices are widely used in renewable power systems, and the characteristics of partial discharge (PD) signals under repetitive impulse excitation are vastly different from those observed under power frequency excitation, causing many pattern recognition methods to fail. This paper proposes a improved identification method based on representation learning that can directly process PD sequences received by ultra-high frequency (UHF) sensors. First, a representation learning architecture based on the Transformer Encoder module is proposed and the model is pretrained in an unsupervised manner to extract features from the raw input discharge sequences. Then, the extracted features are processed using the ridge regression classifier to achieve end-to-end PD source identification. Finally, the effectiveness of the proposed model is validated through an experimental study, achieving an improved accuracy of 98.6%, which is better than classical PD identification deep learning models under repetitive impulse voltage. Furthermore, the model exhibits strong robustness against noise interference and sampling rates. The effectiveness of the model was also tested on an inverter-fed motor stator device. To further validate its practical applicability, it is essential to collect diverse PD data from various electrical equipment.

Partial discharge (PD) localization is critical to ensure the safe operation of power equipment. In this paper, an optimization scheme is developed for PD positioning of external insulation equipment. The optimization scheme is based on an eight‐element cross sensor array to receive the ultrasonic signal generated by the PD, and uses the highly accurate 2‐D multiple signal classification (2‐D MUSIC) algorithm to locate the signal. Simulated discharge signal is adopted to test the optimization scheme, and the results show that the positioning error is less than 0.61° when the signal‐to‐noise ratio (SNR) is above −5 dB. In addition, three discharge models are tested at various locations. The average azimuth errors are 0.9°, 1.9°, and 1.55° for the needle‐plate, cone‐plate, and ball‐plate discharge models, respectively, and the average pitch angle errors are 0.75°, 2.1°, and 1.4°, respectively. These show that the needle‐plate model has the best positioning effect. Simulations and experiments are also carried out on the double discharge source scenario, and the error is within 2.2°. A PD location visualization equipment based on the proposed optimization scheme is developed and applied on‐site. The equipment is capable of satisfying the requirements of operation and maintenance.

The directional multiple signal classification (Dir-MUSIC) algorithm based on the antenna gain array manifold has been proposed to find the direction of the partial discharge (PD) source in substations. However, PD signals are wideband signals and the antenna gain pattern functions are always different at different frequencies; therefore, the accuracy can be improved using a wideband Dir-MUSIC algorithm. In this paper, wideband Dir-MUSIC algorithms are discussed and a novel wideband Dir-MUSIC algorithm using the strength proportion (DirSP) is proposed. This algorithm estimates a focusing PD signal at a certain frequency using the strength proportion among different directions, and then the Dir-MUSIC algorithm can process the focusing PD signal at this frequency. In simulations, when the antenna gain functions among different frequency bins are quite different, the Dir-MUSIC algorithm loses accuracy; meanwhile, DirDP performs very well. In the experiments, we deal with six sets of samples, and the mean error and standard deviation are both smaller than $4°$ better than other methods.

The directional multiple signal classification (Dir‐MUSIC) algorithm based on antenna gain array manifold has been proposed to find the direction of the partial discharge source successfully in substations, however, a non‐linear optimisation problem in this algorithm is usually time‐consuming. To achieve real‐time feature, a data‐driven Dir‐MUSIC method based on the multilayer perception model is proposed to speed up the computing process and simultaneously guarantee the accuracy. Pre‐trained the multilayer perception model, the non‐linear optimisation problem can be treated as a function can be calculated directly. Input of the model is the noise matrix which can be uniquely calculated with a certain matrix measurement, and output is the estimated direction of the partial discharge source. Simulation results demonstrate that the proposed method has an excellent efficiency and relatively high accuracy, and the computing time can match the real‐time demand. Additionally, two effective improvements are proposed to raise the direction accuracy and stability. Specifically, mean error is reduced from 2.58° to 2.22° with the first improvement, and from 2.58° to 1.00° with the second improvement.

Inspection robots are widely used in the field of smart grid monitoring in substations, and partial discharge (PD) is an important sign of the insulation state of equipment. PD direction of arrival (DOA) algorithms using conventional beam forming and time difference of arrival (TDOA) require large-scale antenna arrays and high computational complexity, making them difficult to implement on inspection robots. To address this problem, a novel directional multiple signal classification (Dir-MUSIC) algorithm for PD direction finding based on signal strength is proposed, and a miniaturized directional spiral antenna circular array is designed in this paper. First, the Dir-MUSIC algorithm is derived based on the array manifold characteristics. This method uses strength intensity information rather than the TDOA information, which could reduce the computational difficulty and the requirement of array size. Second, the effects of signal-to-noise ratio (SNR) and array manifold error on the performance of the algorithm are discussed through simulations in detail. Then, according to the positioning requirements, the antenna array and its arrangement are developed and optimized. Simulation results suggested that the algorithm has reliable direction-finding performance in the form of six elements. Finally, the effectiveness of the algorithm is tested by using the designed spiral circular array in real scenarios. The experimental results show that the PD direction-finding error is $3.{39}^{°}$, which meets the need for partial discharge DOA estimation using inspection robots in substations.

AC arc faults detection aims to detect the early arc faults to prevent potential accidents. To develop a small and low-cost testing device for arc fault detection devises (AFDDs), an AC arc faults simulation method is vital. Generally, physical arc models arc used to generate arc fault signals. However, signals can hardly address the high frequency component, such as the transient spikes. From a data-driven perspective, we propose an electric AC arc faults simulation method using measured data based on Principal Component Analysis (PCA) to simulate more accurate and more realistic arc current signals. Without extra physical models, this method can adaptively simulate actual AC arc fault current signals in different application scenarios using a few measured data. Based on a set of standard orthogonal basis derived from PCA, the simulated AC arc current signals can maintain the time and frequency features more effectively than classical models. Compared with other simulated arc current signals, real-world experimental results indicate that the proposed method can simulate more accurate and more actual AC arc current signals.