Collecting labeled Dissolved Gas Analysis (DGA) data is difficult because the determination of the transformer fault is time-consuming and expensive in the transformer substation, but DGA data without labels is easier to obtain. In order to make full use of DGA data with few labels and a large number of unlabeled data to improve the transformer fault diagnosis rate, it is an important to study the DGA fault diagnosis method based on semi-supervised learning for solving practical problems in the field. Therefore, the paper proposed a novel filter-based semi-supervised feature selection method for building fault diagnosis model and selecting optimal DGA features. The method is test by using IEC T10 dataset and compared with traditional supervised diagnostic models. The results show that the proposed method works in optimizing DGA features and has strong robustness in solving small sample DGA classification problems.
Silicone rubber (SiR) is a fundamental electrical insulating material. For its use in nuclear power plants, the degradation induced by heat, gamma-ray irradiation, and steam exposure could be a concern. Therefore, their synergism on the degradation of SiR was examined experimentally. When SiR is first exposed to the steam at 200 °C, it melts and its tensile strength becomes impossible to measure. However, if the gamma-ray irradiation was given in advance, SiR is not destroyed so badly by the high-temperature steam. The reason for the above is that the formation of tight cross-linked structures via oxygens, induced by the irradiation of gamma rays, prevents the progress of hydrolysis.
Overhead transmission line has always been the major approach for large capacity power transmission over long distances, which takes a great deal of steel and land source. Therefore, composite cross arms are introduced to a full-scale AC 500 kV model tower, which could save the transmission corridor by 10%• The switching overvoltage flashover characteristics of the air gaps are investigated. Three flashover paths are observed and the flashover processes are recorded. Also, the influence of air humidity and air density is considered. And the test results are corrected to standard conditions. By comparison with other air gaps, the switching overvoltage withstand ability of composite cross arm is slightly higher than the typical V -string line insulators, which totally meets the requirement of AC 500 kV transmission tower.
To study the electrical tree growth and partial discharge (PD) characteristics of cross-linked polyethylene (XLPE) under the DC electric field, the XLPE insulation was made into needle-plate electrode samples to carry out experiments at 25°C and 50 °C. The results show that the electrical tree grows at 50°C accompanied by PD, and the PD amplitude positively correlates with the tree length. However, under the same voltage condition, the DC electrical tree does not grow at 25°C, and there is only a small amount of PD observed. The elevated temperature not only promotes the growth of the electrical tree but also enhances the amplitude and frequency of PD signals. In addition, when the power is turned off and the applied DC voltage begins to decay to zero, PD with the reversal polarity can be detected in the sample with an electrical tree defect at both 25°C and 50 °C. With the exponential decline of the applied voltage, the PD amplitude increases, as well as the discharge interval, until the applied voltage is close to zero. This may be due to the formation of a reverse electric field at the needle tip during the applied voltage drop, resulting in PD in the electrical tree.
There is no doubt that transformer plays a fundamental role in power system. At the same time, transformer winding fault diagnosis is an important topic. Many works put the most emphasis on the identification of fault type and degree, while ignoring the fault location. However, fault location is an urgent problem to be solved, which is worth studying and discussing. The contribution of this paper lies in the location of Disk space variation (DSV) fault The introduction of digital twin can solve the problem of insufficient fault cases, and pave the way for the intellectualization of fault diagnosis. In this paper, the digital twin of transformer winding is established based on double ladder network, in which the distributed parameters are calculated by finite element method. Frequency response analysis (FRA) is one of the most widely accepted methods for transformer winding mechanical deformation fault diagnosis. By extracting the mathematical index of FRA, multi-layer perceptron (MLP) is trained and DSV fault location is realized. In addition, the popular support vector machine is also compared with the MLP model in this paper, which further highlights the advantages of MLP. The proposed method is verified by an actual transformer, and the results are satisfactory.
