It is a great challenge to differentiate Partial Discharge (PD) induced by different types of insulation defects in high voltage cables. Some types of PD signals have very similar characteristics and are specifically difficult to be differentiate, even for the most experienced specialists. To overcome the challenge, a Convolutional Neural Network (CNN) based deep learning methodology for PD pattern recognition is presented in this paper. Firstly, PD testing for five types of artificial defects in Ethylene-Propylene-Rubber (EPR) cables was carried out in the High Voltage (HV) laboratory to generate signals containing PD data. Secondly, 3500 sets of PD transient pulses were extracted and then 33 kinds of PD features were established. The third stage applies a CNN to the data: typical CNN architecture and the key factors which affect the CNN based pattern recognition accuracy, are described. Factors discussed include the number of the network layers, convolutional kernel size, activation function, and pooling method. The paper presents a flowchart of the CNN based PD pattern recognition method and an evaluation with 3500 sets of PD samples. Finally, the CNN based pattern recognition results are shown and the proposed method is compared with two more traditional analysis methods, i.e. Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN). The results show that the proposed CNN method has higher pattern recognition accuracy than SVM and BPNN, and that the novel method is especially effective for PD type recognition in cases of signals of high similarity, which is applicable for industrial applications.

Optimal selection of features of Partial Discharge (PD) signals recorded from defects in High Voltage (HV) cables will contribute not only to the improvement of PD pattern recognition accuracy and efficiency but also to PD parameter visualization in HV cable condition monitoring and diagnostics. This paper presents a novel Random Forest (RF)-based feature selection algorithm for PD pattern recognition of HV cables. Firstly, the experimental data acquisition and feature extraction processes are introduced. PD signals were captured from faults created in a cable to obtain the raw PD data, then a set of 3500 transient PD pulses and a set of 3500 typical interference pulses were extracted, based on which 34 PD features were extracted for further processing. Furthermore, 119 two-dimensional features and 1082 three-dimensional features were generated. The paper then discusses the basic principle of the RF algorithm. Finally, RF-based feature selection was implemented to determine the optimal features for PD pattern recognition. The results were obtained and evaluated with the Back Propagation Neural Network (BPNN) and Support Vector Machine (SVM). Results show that the proposed RF-based method is effective for PD feature selection of HV cables with the potential for application to additional HV power apparatus.

Partial discharge (PD) testing of high voltage (HV) cables and cable accessories has been implemented predominantly using high frequency current transformers (HFCTs) as PD sensors. PD currents initiating at PD sources are coupled onto cable conductors and travel away from the PD sources and will be detected by HFCTs installed at cable terminations. In this paper, based on combining finite-difference time-domain (FDTD) modeling and transfer function theory, a hybrid modeling approach is proposed to investigate the processes of PD coupling and detection involved in HFCT-based PD testing of HV cables. This approach allows exciting a PD event anywhere in FDTD models of the cables and predicting output from HFCTs some distance away. Implementation of the method is illustrated using an 11 kV XLPE cable. Moreover, a “direct measurement” method to obtain original PD pulses as the excitation source waveform is presented. The modeling approach introduced here will facilitate studies on the relationship between measured PD signals and those excited at PD sources, which can potentially give useful insight into the basic mechanisms behind PD detection in cables.

Electrical treeing (ET) can irreversibly deteriorate the insulation of polymeric power cables leading to a complete failure. This paper presents the results of an experimental investigation into the effects of unipolar and polarity reversing DC voltages on electrical tree (ET) and partial discharge (PD) behavior within high voltage direct current (HVDC) cross linked polyethylene (XLPE) cable insulation. A double needle configuration was adopted to produce non-uniform electric fields within the insulation samples, potentially leading to electrical trees. The development of trees was monitored through an optical method and the associated partial discharge signals were measured through an electrical detection technique, simultaneously. The analysis of the results shows reasonable relation between the formation of ETs and the type of the applied voltages. The polarity reversing attribute of the test voltages has a pronounced effect on formation and growth of electrical trees. This implicates an interaction between the space charges that accumulate within polymeric materials and the operational polarity reversing electric fields, which causes insulation degradation. Therefore, study of influencing HVDC operational parameters on insulation degradations can contribute to improvements in cable design and advancement in insulation diagnostic strategies applicable in HVDC systems leading to more effective asset management.

Insulation degradation is an irreversible phenomenon that can potentially lead to failure of power cable systems. This paper describes the results of an experimental investigation into the influence of direct current (DC) superimposed with harmonic voltages on both partial discharge (PD) activity and electrical tree (ET) phenomena within polymeric insulations. The test samples were prepared from a high voltage direct current (HVDC) cross linked polyethylene (XLPE) power cable. A double electrode arrangement was employed to produce divergent electric fields within the test samples that could possibly result in formation of electrical trees. The developed ETs were observed via an optical method and, at the same time, the emanating PD pulses were measured using conventional techniques. The results show a tenable relation between ETs, PD activities, and the level of harmonic voltages. An increase in harmonic levels has a marked effect on development of electrical trees as the firing angle increases, which also leads to higher activity of partial discharges. This study of the influencing operational parameters of HVDC converters on power cable insulation is predicted to contribute to enhancements in cable design and progressive advancement in condition monitoring and insulation diagnostic techniques that can lead to more effective asset management in HVDC systems.