Insulation systems are one of the most exposed parts of electrical machines and equipment. Special diagnostic methods have been developed not only to detect defects and anomalies in high voltage (HV) insulation systems, but also to evaluate the state of the systems with regard to further service reliability. Following the results of diagnostic methods, it is possible not only to determine the reliability of the equipment in subsequent service but also to prolong the inspection periods, or to reduce the number of inspections. Expert system with the elements of artificial intelligence is a very effective tool for the evaluation of measured data from the diagnostic measurements and for the estimation of behavior of the insulation system in future operation. Several rule-based expert systems for the diagnostics of HV insulation systems have been developed at the Czech Technical University in Prague in the collaboration with other top diagnostic workplaces of the Czech Republic.A complex system for the Partial Discharge (PD) evaluation, based on digital data processing, has been developed. Detected analog PD impulses are digitized in the measuring unit by a special analog-digital converter and the connection between the measuring unit and the computer enables to transfer detected PD impulses immediately into a computer for their further processing. Two parallel expert systems work in this complex evaluating system: a rule-based expert system performs an amplitude analysis of PD impulses for determining the damage of the insulation system, and a neural network is used for a phase analysis of PD impulses (the recognition of PD patterns) to determine the kind of PD activity and location of the resource of PD activity.

Partial Discharge (PD) measurement is one of the best solutions for condition assessment of Gas Insulated Switchgears (GISs). For having Condition-based maintenance of GIS, online PD monitoring is of great importance. For this aim, Ultra High Frequency (UHF) PD sensors should be installed inside the GIS during the installation. However, in most installed GISs in industries, the internal UHF PD sensors are not installed. In this paper, a new method for online defect type recognition according to external UHF PD sensors and based on the time-frequency representation of PD signal is proposed. In this case, four artificial defect types named protrusion on the main conductor, protrusion on the enclosure, free moving metal particle, and metal particle on spacer are implanted inside the 132 kV L-Shaped structure of one phase in enclosure GIS. The signal energy at each level of the decomposed signal by Discrete Wavelet Transform (DWT) is applied for features of each defect type. The trends of signal energy variations at each frequency range of signal are applied for discriminating between each defect type. The Deep Feed Forward Network (DFFN) classifier is applied for PD pattern recognition. The results show the benefits and simplicity of the proposed method for PD signal classification, independent from the position of the PD sensor, especially in the case of online PD monitoring of GIS.

Partial Discharge (PD) is a significant concern in the operation of rotating machines such as generators and motors, as it can lead to insulation degradation over time, reducing the reliability and lifespan of the machines. To monitor PD activity, coupling capacitors (CC) are widely used as sensors for online PD detection, as they can effectively capture PD pulses in high-voltage (HV) rotating machines. The primary objective of this research is to measure and analyze PD signals using a CC sensor for HV rotating machines under varying input voltages and frequencies, following the guidelines of the IEC 60270 standard and utilizing the MPD 600 device. The experimental setup includes performing insulation resistance (IR) testing, PD calibration, and PD measurement. Additionally, this paper provides a detailed study of PD signal characteristics, specifically focusing on phase-resolved Partial Discharge (PRPD) patterns, to understand the behavior of PD in HV rotating machines, enhancing fault diagnosis and preventive maintenance strategies.

The ultra-high frequency (UHF) technique offers significant advantages over the conventional Partial Discharge (PD) measurement method, particularly for online monitoring, 3D localization, and immunity against noise. However, its primary limitation lies in the challenge of calibration due to the impact of various factors such as PD source locations, antenna characteristics, and transformer structures including, active part and tank wall, on the received UHF signals. Currently established parameters such as signals peak-to-peak and energy of signals do not provide a meaningful correlation between received UHF signals strength and factors such as distance and antenna radiation pattern. Addressing these gaps, this paper introduces a novel parameter: the first arrived signal (FAS), derived from the short-time Fourier transform (STFT) of UHF signals. Experimental results demonstrated the capability of the FAS to correlate meaningfully between signal strength and distance from the source, as well as antenna radiation pattern and polarization. The proposed parameter is then utilized to estimate conventional transferred charge using the received UHF signals. Results indicate promising estimation accuracy, particularly when electromagnetic waves directly reach the antenna. This approach offers the potential for a more precise estimation of conventional PD transferred charge, enhancing the capabilities of the UHF method in assessing insulation system health conditions.

Partial Discharge (PD) is a critical phenomenon in electrical systems, particularly in high-voltage (HV) equipment like transformers, cables, switchgear, and rotating machines. In rotating machines such as generators and motors, PD is a significant concern as it leads to insulation degradation, potentially resulting in catastrophic failure. Effective and reliable diagnostic techniques are essential for detecting and analyzing PD to ensure the operational safety and longevity of such equipment. Various PD detection methods have been developed, including coupling capacitor (CC), high-frequency current transformer (HFCT), and ultra-high frequency (UHF) techniques, each offering unique advantages in assessing the condition of HV electrical systems. Among these, coupling capacitors have gained significant attention due to their ability to improve the accuracy, sensitivity, and efficiency of PD detection in rotating machines. This study focuses on the advancements in coupling capacitor-based techniques and their critical role in enhancing PD diagnostics for monitoring and maintaining high-voltage rotating machinery.