The article presents a novel on-line partial discharge (PD) monitoring system for power transformers, whose functioning is based on the simultaneous use of three unconventional methods of PD detection: high-frequency (HF), ultra-high frequency (UHF), and acoustic emission (AE). It is the first monitoring system equipped in an active dielectric window (ADW), which is a combined ultrasonic and electromagnetic PD sensor. The article discusses in detail the process of designing and building individual modules of hardware and software layers of the system, wherein the most attention was paid to the PD sensors, i.e., meandered planar inverted-F antenna (MPIFA), high-frequency current transformer (HFCT), and active dielectric window with ultrasonic transducer, which were optimized for detection of PDs occurring in oil-paper insulation. The prototype of the hybrid monitoring system was first checked on a 330 MVA large power transformer during the induced voltage test with partial discharge measurement (IVPD). Next, it was installed on a 31.5 MVA substation power transformer and integrated according to the standard IEC 61850 with SCADA (Supervisory Control and Data Acquisition) system registering voltage, active power, and oil temperature of the monitored unit. The obtained results showed high sensitivity of the manufactured PD sensors as well as the advantages of the simultaneous use of three techniques of PD detection and the possibility of discharge parameter correlation with other power transformer parameters.

Science and Technology article citation info: IntroductionLarge power transformers are the most critical component in electric power systems, as they are essential in maintaining a reliable supply of electric energy. There are many factors which cause a transformer malfunction, but those, which can potentially lead to catastrophic failure are winding damages (due to short-circuit, lightning, and other over-voltages) and insulation system failure (moisture, thermal aging, partial discharges). The damage from a catastrophic transformer failure may run into tens of millions of dollars [16]. To avoid such a scenario, power utilities are moving towards continuous transformer condition monitoring, based on dissolved gas analysis and acoustic emission (AE) or electromagnetic (HF/VHF/UHF) partial discharge detection.According to the newest research results and analyses presented by the experts of the CIGRE Working Group A2.37, in the technical brochure 642: Transformer Reliability Survey, the main reason of breakdowns of high voltage power transformers is damage to the windings and the main insulation system [3]. Mechanical defects in the form of winding deformations (axial displacements and radial deformations) and deterioration of insulation properties associated with thermal aging processes [6], can lead to the initiation of the partial discharge (PD) phenomena occurrence.In recent years, in the electric power industry and research centres, a trend consisting in developing and implementing advanced

Streszczenie. W artykule przedstawiono prototypową konstrukcję anteny typu "odwrócone F" (PIFA) przeznaczoną do monitoringu wyładowań niezupełnych (wnz) w transformatorach energetycznych przy użyciu metody UHF. Konstrukcję anteny przystosowano mechanicznie do montażu w oknie dielektrycznym kadzi transformatora, a jej pasmo przenoszenia zostało zoptymalizowane do detekcji wyładowań niezupełnych występujących w izolacji papierowo-olejowej. Przeprowadzone testy laboratoryjne wykazały, że opracowana antena charakteryzuje się około dwukrotnie wyższą skutecznością detekcji wnz w porównaniu do standardowej anteny dyskowej.

The article presents research on the influence of the type of UHF antenna and the type of machine learning algorithm on the effectiveness of classification of partial discharges (PD) occurring in the insulation system of a power transformer. For this purpose, four antennas specially adapted to be installed in the transformer tank (UHF disk sensor, UHF drain valve sensor, planar inverted F-type antenna, Hilbert curve fractal antenna) and a reference log-periodic antenna were used in laboratory tests. During the research, the main types of PD, typical for oil-paper insulation, were generated, i.e., PD in oil, PD in oil wedge, PD in gas bubbles, surface discharges, and creeping sparks. For the registered UHF PD pulses, nine features in the frequency domain and four features in the wavelet domain were extracted. Then, the PD classification process was carried out with the use of selected methods of supervised machine learning. The study investigated the influence of the number and type of feature on the obtained classification results gained with the following machine-learning methods: decision tree, support vector machine, Bayes method, k-nearest neighbor, linear discriminant, and ensemble machine. As a result of the works carried out, it was found that the highest accuracies are gathered for the feature representing peak frequency using a decision tree, reaching values, depending on the type of antenna, from 89.7% to 100%, with an average of 96.8%. In addition, it was found that the MRMR method reduces the number of features from 13 to 1 while maintaining very high effectiveness. The broadband log-periodic antenna ensured the highest average efficiency (100%) in the PD classification. In the case of the tested antennas adapted to work in an energy transformer tank, the highest defect-recognition efficiency is provided by the UHF disk sensor (99.3%), and the lowest (89.7%) is by the UHF drain valve sensor.

The article presents the process of designing and manufacturing a prototype antenna based on the PIFA (Planar Inverted F Antenna) technology for the detection of UHF signals from partial discharges occurring in the power transformer insulation system. The main objective of the simulation studies was to obtain a frequency band covering the range of radio frequencies emitted by partial discharges in oil-paper insulation (surface discharges) and to adjust the dimensions of the antenna for its installation in the inspection window of the power transformer. The proposed structure consists of a radiating element in the shape of a rectangular meandering line and an additional parasitic element in the form of a specially selected resistor connecting the reflector with the radiator. The design of the prototype antenna was tested during laboratory tests in a high-voltage laboratory using a model of a transformer tank in which partial discharges were generated. The results of the measurements showed that the developed antenna has a higher sensitivity of partial discharge detection than other popular antennas used in transformer diagnostics, i.e. the disk antenna and the Hilbert fractal antenna. Due to high sensitivity, compact and simple structure and low production costs, the proposed PIFA antenna may be an interesting alternative to the currently used commercial antennas (mainly disk antennas) in on-line monitoring systems for partial discharges of power transformers. Keywords: diagnostics and reliability of power transformers, partial discharge detection, UHF method, PIFA antenna.