Abstract:In order to explore a non-destructive method for measuring the polymerization degree (DP) of paper insulation in transformer, a new method that based on the optical properties of free fiber particles in transformer oil was studied. The chromatic dispersion images of fibers with different aging degree were obtained by polarizing microscope, and the eigenvalues (r, b, and Mahalanobis distance) of the images were extracted by the RGB (red, blue, and green) tricolor analysis method. Then, the correlation between the three eigenvalues and DP of paper insulation were simulated respectively. The results showed that the color of images changed from blue-purple to orange-yellow gradually with the increase of aging degree. For the three eigenvalues, the relationship between Mahalanobis distance and DP had the best goodness of fit (R 2 = 0.98), higher than that of r (0.94) and b (0.94). The mean square error of the relationship between Mahalanobis distance and DP (52.17) was also significantly lower than that of r and b (97.58, 98.05). Therefore, the DP of unknown paper insulation could be calculated by the simulated relationship of Mahalanobis distance and DP.

The noise pollution caused by urban substations is an increasingly serious problem, as is the issue of local residents being disturbed by substation noise. To accurately assess the degree of noise annoyance caused by substations to surrounding residents, we established a noise annoyance prediction model based on transfer learning and a convolution neural network. Using the model, we took the noise spectrum as the input, the subjective evaluation result as the target output, and the AlexNet network model with a modified output layer and corresponding parameters as the pre-training model. In a fixed learning rate and epoch setting, the influence of different mini-batch size values on the prediction accuracy of the model was compared and analyzed. The results showed that when the mini-batch size was set to 4, 8, 16, and 32, all the data sets had convergence after 90 iterations. The root mean square error (RMSE) of all validation sets was lower than 0.355, and the loss of all validation sets was lower than 0.067. As the mini-batch size increased, the RMSE, loss, and mean absolute error (MAE) of the verification set gradually increased, while the number of iterations and the training duration decreased gradually. In this test, a mini-batch size value of four was appropriate. The resultant convolutional neural network model showed high accuracy and robustness, and the error between the prediction result and the subjective evaluation result was between 2% and 7%. The model comprehensively reflects the objective metrics affecting subjective perception, and accurately describes the subjective perception of urban substation noise on human ears.

No abstract

No abstract

No abstract