Search

Epoxy resin impregnated paper (ERIP) composites are the main insulation material of capacitance core of the capacitance graded bushing. The insulating property of ERIP composites are relevant with the change of environmental temperature. Therefore, the influences of high-low temperature environment on the dielectric response properties of ERIP composites were studied in the paper. Firstly, the cycles test of ERIP samples is carried out by high-low temperature environment from 20°C to 120°C, and the frequency domain dielectric spectroscopy (FDS) test is performed on the ERIP sample at each cycle. Then, the dielectric loss factor (tanδ) and the real and imaginary parts of complex capacitance at different cycle numbers and frequencies are all analyzed in the paper. Finally, the features are extracted from the frequency domain of the tanδ, and the relationship with the features and the cycles is established. The test results and analysis indicated that as the number of cycles increases, the value of the tanδ and the imaginary part of the complex capacitance has an increase trend, while the value of the real part of the complex capacitance decreases with the increase of the number of cycles. As the number of cycles increases, the rate of change of the power tanδ, the imaginary and real parts of the power complex capacitance are 46.79%, 39.73% and 4.26% respectively. The tanδ at 1Hz, 0.46Hz and 0.22Hz are the selected features, all of which have linear relationship with the cycle times. The conclusion can provide a data basis for insulation state of the ERIP composites within the capacitance graded bushing.

Partial Discharge (PD) pattern recognition is one of the most important steps of PD based condition monitoring of high voltage cables, which is challenging as some types of the PD induced by cable defects are with high similarity. In recently years, deep learning based pattern recognition methods have achieved impressive pattern recognition accuracy on speech recognition and image recognition, which is one of the most potential techniques applicable for PD pattern recognition. The Stacked Denoising Autoencoder (SDAE) based deep learning method for PD pattern recognition of different insulation defects of high voltage cables is presented in the paper. Firstly, five types of artificial insulation defects of ethylene-propylene-rubber cables are manufactured in the laboratory, based on which PD testing in the high voltage lab is carried out to produce 5 types of PD signals, 500 samples for each defect types. PD feature extraction is carried out to generate 34 kinds of PD features, which are the input parameters of the PD pattern recognition methods. Secondly, the principle and network architecture of SDAE method and the flowchart of SDAE based PD pattern recognition are presented in details. Thirdly, the SDAE method is evaluated with the experimental data, 5 different types of PD signals, which achieves a recognition accuracy of 92.19%. Finally, the proposed method is compared with the traditional pattern recognition methods, Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN). The results show that the pattern recognition accuracy of the proposed method is improved by 5.33% and 6.09% compared with the SVM method and the BPNN method respectively, which is applicable for pattern recognition of PD signals with high similarity.

Partial Discharge (PD) pattern recognition is one of the most important steps of PD based condition monitoring and diagnosis of High Voltage (HV) cables. Although different types of pattern recognition methods, e.g. Support Vector Machine (SVM), Back-propagation Neural Network (BPNN) and Deep Learning, have been developed and applied to PD pattern recognition, limited training samples is one of the most important factors which restricts the PD pattern recognition accuracy. To overcome the challenge two PD data augmentation methods, based on the Variable Noise Superposition (VNS) and Generative Adversarial Network (GAN), are presented in the paper, which are evaluated with 1500 sets of experimental PD data and three pattern recognition methods, Support Vector Machine (SVM), Logical Regression (LR) and Random Forest (RF). The results show that PD pattern recognition accuracy, based on the VNS data augmentation method, is improved by 0.99%, evaluated with SVM, and is improved by 0.96%, evaluated with RF; PD pattern recognition accuracy, based on the GAN data augmentation method, is improved by 0.52%, evaluated with SVM, and is improved by 1.72%, evaluated with LR. Both two methods, VNS and GAN, are effective for PD data augmentation, which are applicable for PD pattern recognition of HV cables and other HV apparatuses, especially for pattern recognition methods which requires large volume of training samples.

As a typical “white box” pattern recognition method, the traditional Decision Tree (DT) method, which is easy to be interpreted and trained, has been widely applied in the Partial Discharge (PD) pattern recognition of high voltage cables. However, the disadvantages of the DT method are significant, including the limited recognition accuracy, poor anti-interference ability and poor generalization ability, etc. In order to overcome the challenges, Gradient Boosting Decision Tree (GBDT) and Random Forest (RF) based PD pattern recognition methods are presented in the paper. Firstly, 3500 PD samples are obtained based on the PD testing of five types of artificial defects of ethylene-propylene (EPR) cables in the high voltage lab. Secondly, PD data pre-processing is carried out and 34 types of PD features are extracted from the raw data. Thirdly, the principles of GBDT and RF based PD pattern recognition are presented in details. Finally, the 3500 PD samples are applied to evaluate the GBDT and RF based PD pattern recognition methods, which are compared with the traditional DT method. The results show that the PD pattern recognition accuracies of RF, GBDT and DT are 89.7%, 90.4% and 84.3% respectively. GBDT and RF based PD pattern recognition methods show remarkable advantages, compared with the DT method, which are both applicable for industrial application of PD based condition monitoring of high voltage cables.