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.
Condition monitoring is playing an increasingly important role within electrical power networks, where its use can help to reduce maintenance costs, improve supply reliability, and permit increased utilization of equipment capacity by providing a measure of actual operating conditions as an alternative to relying on more stringent “worst case scenario” assumptions. In this context, energy harvesting may have a role to play in that it offers the possibility of realizing autonomous, self-powering sensors that communicate their data wirelessly. In the vicinity of electrical transmission and distribution equipment, alternating magnetic fields at the power frequency offer a potential source of energy that does not require hard-wiring or batteries. There are many potentially useful locations for sensors where the level of magnetic flux density may be sufficient to provide enough power for a low-power wireless sensor node. This paper describes a free-standing inductive harvester for use in positions where there is an ambient magnetic field due to conductors that are remote and/or inaccessible. Using data from surveys of magnetic flux density levels at two substations, optimum core and coil designs for the harvester are obtained through theoretical analyses and experiments. A demonstrator is then constructed in which a wireless sensor becomes self-powering when immersed in a 50-Hz magnetic field. Laboratory results show that this system can deliver a useful average power of 300 $\mu{\rm W}$ when placed in a magnetic flux density of 18 $\mu T_{rms}$.
22 May 2019 in IEEE Transactions on Power Delivery
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.
11 April 2019 in IEEE Transactions on Power Delivery
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.
Objective: This study investigates possible advantages in pulsed over continuous 405-nm light-emitting diode (LED) light for bacterial inactivation and energy efficiency. Background: Alternative nonantibiotic methods of disinfection and infection control have become of significant interest. Recent studies have demonstrated the application of systems using 405-nm LEDs for continuous disinfection of the clinical environment, and also for potential treatment of contaminated wounds. Methods: Liquid suspensions of 10 3 colony-forming units/mL populations of Staphylococcus aureus were subject to pulsed 405-nm light of different frequencies, duty cycles, and intensities and for different lengths of time. Results: Pulsed exposures with the same average irradiance of 16 mW/cm 2 and varying duty cycle (25%, 50%, 75%) showed very similar performance compared with continuous exposures, with 95–98% reduction of S. aureus achieved for all duty cycles. The pulsing frequency was varied in intervals from 100 Hz to 10 kHz and appeared to have little effect on antimicrobial efficacy. However, when comparing pulsed with continuous exposure, an improvement in inactivation per unit optical energy was achieved, with results showing an increase of approximately 83% in optical efficiency. Conclusions: These results suggest that under pulsed conditions, a lower energy consumption and lower perceived brightness could be achieved, thus potentially providing improved operating conditions for medical/infection control applications without compromising antimicrobial efficacy.
7 March 2017 in IEEE Transactions on Dielectrics and Electrical Insulation
This paper presents an effective, Rough Set (RS) based, pattern recognition method for rejecting interference signals and recognising Partial Discharge (PD) signals from different sources. Firstly, RS theory is presented in terms of Information System, Lower and Upper Approximation, Signal Discretisation, Attribute Reduction and a flowchart of the RS based pattern recognition method. Secondly, PD testing of five types of artificial defect in ethylene-propylene rubber (EPR) cable is carried out and data pre-processing and feature extraction are employed to separate PD and interference signals. Thirdly, the RS based PD signal recognition method is applied to 4000 samples and is proven to have 99% accuracy. Fourthly, the RS based PD recognition method is applied to signals from five different sources and an accuracy of more than 93% is attained when a combination of signal discretisation and attribute reduction methods are applied. Finally, Back-propagation Neural Network (BPNN) and Support Vector Machine (SVM) methods are studied and compared with the developed method. The proposed RS method is proven to have higher accuracy than SVM and BPNN and can be applied for on-line PD monitoring of cable systems after training with valid sample data.