Search

In recent years, frequency domain spectroscopy (FDS) is often used to evaluate oil paper insulation state in power transformer bushing. But it is still very difficult to evaluate the moisture content accurately and quickly. In order to solve this problem, this paper proposes an intelligent algorithm based on random forest regression (RFR) to construct an efficient evaluation method through segmented FDS curves. Furthermore, the characteristics of FDS curves were studied and the intelligent method was compared with support vector regression (SVR) and deep neural networks (DNN). The results show that the dielectric loss, the real part and imaginary part of complex capacitance all move upward with the moisture increasing, so they can be used as the input feature of the evaluation model; The moisture content evaluation accuracy of the RFR model in the whole frequency band is higher than that of SVR and DNN models; With the increase of lower cut off frequency (FDS test stop frequency), the FDS test time is greatly shortened, and the accuracy of the RFR model can still meet the evaluation requirements. Therefore, the data in a compromise frequency band can be used to evaluate the moisture content of oil paper insulation accurately and quickly. [ABSTRACT FROM AUTHOR]

Epoxy‐impregnated paper transformer bushings are prone to water absorption due to the presence of water‐attracting moieties in the cellulose chemical structure and epoxy resin, leading to moisture‐induced insulation defects. To understand the mechanism of moisture's impact on epoxy‐impregnated paper, this study developed a testing platform that integrated moisture diffusion, adsorption, and dielectric properties of insulating materials. Insulation specimens made of epoxy resin and epoxy‐impregnated paper were prepared and their water diffusion characteristics were investigated using the Fick diffusion model and the Langmuir model, respectively. The Guggenheim–Anderson–de Boer equation was used to examine the vacuum vapour adsorption characteristics of the materials, providing a theoretical foundation for examining the form of water present within them. The dielectric response of materials with varying moisture levels was then tested to study the effect of water on the dielectric spectrum curve. Using the Extended Derivative Method, the characteristic frequency reflecting the water content of the epoxy‐impregnated paper was extracted. The results demonstrate that 0.01‐Hz characteristic frequency provides superior accuracy for moisture assessment in epoxy resins compared to 50 Hz, and extracting and fitting the relaxation peak characteristic frequency in epoxy‐impregnated paper moisture evaluation yields higher accuracy than using tan δ at the power frequency. [ABSTRACT FROM AUTHOR]

Capacitive high‐voltage bushing is one of the typical oil‐immersed paper insulation equipment, which is an indispensable external connection component for power transformers. In order to evaluate the effectiveness of frequency domain spectroscopy (FDS) for diagnosing moisture content of oil‐immersed paper insulation bushing, this article studied the frequency‐domain dielectric characteristics of oil‐immersed paper insulation samples and field bushing. At the same time, the basic principle of interfacial polarisation is used to analyse the samples and field bushing with non‐uniform moisture content. The results show that the moisture content affects the whole frequency band of the FDS curve. When the distribution of moisture content is non‐uniform, the paper with high moisture content has a great influence on the whole FDS curve of oil‐immersed paper insulation. In addition, the FDS curves will show a significant loss peak. The frequency of the peak point gradually moves towards the high frequency as the non‐uniformity of the moisture content distribution increases. The experimental results show that the variation law of oil‐immersed paper insulation can be used to quantitatively evaluate the moisture content and moisture type of oil–paper insulation power equipment. [ABSTRACT FROM AUTHOR]