Detection of Water Content in Transformer Oil Using Multi Frequency Ultrasonic with PCA-GA-BPNN

Abstract

The water content in oil is closely related to the deterioration performance of an insulation system, and accurate prediction of water content in oil is important for the stability and security level of power systems. A novel method of measuring water content in transformer oil using multi frequency ultrasonic with a back propagation neural network that was optimized by principal component analysis and genetic algorithm (PCA-GA-BPNN), is reported in this paper. 160 oil samples of different water content were investigated using the multi frequency ultrasonic detection technology. Then the multi frequency ultrasonic data were preprocessed using principal component analysis (PCA), which was implemented to obtain main principal components containing 95% of original information. After that, a genetic algorithm (GA) was incorporated to optimize the parameters for a back propagation neural network (BPNN), including the weight and threshold. Finally, the BPNN model with the optimized parameters was trained with a random 150 sets of pretreatment data, and the generalization ability of the model was tested with the remaining 10 sets. The mean squared error of the test sets was 8.65 × 10−5, with a correlation coefficient of 0.98. Results show that the developed PCA-GA-BPNN model is robust and enables accurate prediction of a water content in transformer oil using multi frequency ultrasonic technology.

Special Issue “Selected Papers from the 2018 IEEE International Conference on High Voltage Engineering (ICHVE 2018)”

“…The topics of HV testing and monitoring/diagnostics are covered by papers [1,2]. In [1], the authors discuss the use of damped AC voltages (DAC) for after-laying testing and diagnosis of submarine power cables-both the export and inter-array cables-according to the recommendations of standards IEEE 400 and IEEE 400.4 for partial discharge monitored testing.…”

“…A novel diagnostic method of measuring water content in transformer oil using multi-frequency ultrasonic, with a back propagation neural network that was optimized by the principal component analysis and genetic algorithm (PCA-GA-BPNN), is reported in [2]. Accurate prediction of water content in oil is important for the stability and security level of power systems as moisture is considered enemy "number one" of insulation.…”

A Novel Measuring Method of Interfacial Tension of Transformer Oil Combined PSO Optimized SVM and Multi Frequency Ultrasonic Technology

“…SVM is a machine learning technique modelled that developed from the optimal classification plane in the case of linear separability [29], [30]. In order to ensure the robustness, SVM adopts the structural risk minimization principle, while minimizing the empirical risk and confidence range of training samples, and has better generalization performance for small sample cases [31], [32].…”

“…Kernel function, which play an important part in the study of SVMs, decides the nonlinear mapping ability of the model, and radial basis function (RBF) is used in this study [28], [29].…”

Hydrothermal Synthesis of Flake-Flower NiO and Its Gas Sensing Performance to CO

“…Dissolved Gas in Oil Analysis (DGA) is one of the most convenient and effective methods to judge the early latent faults of oil immersed high-voltage electrical equipment at present (Gui et al, 2019;Yang et al, 2019a;Zhou et al, 2019;Wang et al, 2020;Wei et al, 2020a). As one of the most important fault characteristic gases of oil immersed transformer, carbon monoxide (CO), has received considerable attention for its application to provide vital help for judging the operation state of transformer (Zhou et al, 2015(Zhou et al, , 2018aYang et al, 2019b).…”