In this study, a novel method based on deep learning was developed for partial discharge (PD) pattern recognition. Traditional PD recognition methods are crucial for extracting features from PD patterns. The method of extracting crucial features is the key to PD pattern identification. The fractal theory is commonly used to determine the features of discharge patterns. The feature distribution of different defect types can be determined according to the fractal dimensions and lacunarity. However, finding fractal features is a complicated process. In this study, a PD image was entered as an input into a deep learning system to reduce the complexity of finding features. First, four defect type of gas-insulated switchgear (GIS) experimental models are established. Then, an LDP-5 inductive sensor (L-sensor) was used to measure the ground line signals caused by PD phenomenon. Second, these electrical signals were transformed into the most representative 3D (n-q-φ) PD patterns. Finally, a convolutional neural network was employed for PD image pattern recognition. A total of 160 sets of PD patterns were measured using a 15-kV GIS. The results obtained with the proposed method were compared with those obtained with the fractal method. The results revealed that the proposed method is easy to use and can easily distinguish various defect types. The proposed approach can determine the GIS insulation status and provide information to construction units for maintenance.

This study primarily discusses the measurement of partial discharge (PD) phenomena and clustering in the defect pattern of a cross-linked polyethylene power cable joint. First, high-speed data acquisition and pretreatment were performed for partial discharge electrical signals at a sampling rate of 20 MS/s. Crucial characteristic signals were reversed to reduce the calculated amount of noise. A characteristic matrix was created according to the resulting dynamic error of chaos synchronization. The characteristic parameters were extracted using fractal theory. Finally, extension theory was used to develop a diagnostic system and anti-interference test. A comparison with the existing Hilbert–Huang transform (HHT) method revealed that the two characteristics extracted from the chaos synchronization results using fractal theory were recognized at a higher pattern recognition rate by employing extension theory. The proposed method can extract crucial information concerning partial discharge as a defect in power cable joints.

Due to the negative impact of a highly stochastic wind power fluctuation on the power quality and stability during high penetration of wind power in power systems, there is growing interest in power smoothing and energy redistribution in wind power systems by using large‐scale energy storage technologies. The aim of this work is to use a vanadium redox flow battery as an energy storage system (ESS) to smooth wind power fluctuation with two system configurations and corresponding control strategies. As the first step, a vanadium redox flow battery (VRFB) mathematical model, underlain by electrochemical theories, is built to describe the battery behaviours in charge/discharge cycles. Accordingly, the aforementioned system configuration and power fluctuation smoothing schemes are proposed. At the end of this work, simulations are conducted on a 3.6 MW doubly‐fed induction generator (DFIG) at a diversity of wind speeds for an assessment of feasibility that this work can be applied to a high penetration of wind power in practice. Simulation results reveal that power fluctuations can be improved by power smoothing. The root mean square deviation (RMSD) percentage can be reduced to less than 1%.

As a key concern in a power system, a deteriorated insulation is likely to bring about a partial discharge phenomenon and hence degrades the power supply quality. Thus, a partial discharge test has been turned into an approach of significance to protect a power system from an unexpected malfunction. An improved Hilbert–Huang Transformation (HHT) is proposed in this work as an effective way to address the issues of an optimal shifting number and illusive components, both suffered in a conventional HHT approach, and is then applied to a defect mode recognition for a partial discharge signal analysis in the case of a cross-linked polyethylene insulated power cable. As the first step, the partial discharge signal detected is converted through the proposed improved HHT to a time-frequency-energy 3D spectrum. Then as the second step, the fractal features contained therein are extracted by way of a fractal theory, and in the end the defect modes are recognized as intended by use of an extension method.

This study Development a high-speed data acquisition (DAQ) device by using AD9226 analog-to-digital converters, a field programmable gate array, and an ARM Cortex-A8 microprocessor for a self-designed synchronous 6-channel high-speed DAQ card that was able to transmit data to a computer through its network interface. Its cost was approximately 10% that of a commercial model, the National Instruments PXI-5105, and thus overcame the prohibitively high cost of commercial DAQ cards. A high-frequency current transformer (HFCT) was used to measure three types of typical partial discharge (PD) in self-made models to compare the performance of the self-designed DAQ card and that of the National Instruments PXI-5105. The HFCT signals were converted into three-dimensional PD patterns, and mean discharge was chosen as the feature to be extracted for the application of extension theory in the recognition of discharge models. The results revealed that the self-designed DAQ card was comparable to the commercial model in the recognition of high-frequency PD signals. Given the high price of commercial high-speed DAQ devices, the self-designed DAQ card was deemed to have considerable advantages in cost and expandability.