GIS partial discharge pattern recognition via lightweight convolutional neural network in the ubiquitous power internet of things context

The construction of the ubiquitous power internet of things (UPIoT) provides a new feasible solution for gas-insulated switchgear (GIS) online monitoring and fault diagnosis, but it also puts forward greater requirements for time and accuracy. How to find an effective real-time model that can be applied to the UPIoT mobile terminals has become an urgent problem needing to be solved. To this end, this study proposes a lightweight convolutional neural network (LCNN) for GIS partial discharge (PD) pattern recognition using three lightweight convolutional blocks, and introduces the lowest recognition accuracy of single-class faults as the primary indicator for selecting the optimal model under the UPIoT. First, three lightweight convolutional blocks are introduced for constructing an LCNN. Then, the optimal model constructed by the lightweight blocks is sought. Next, criteria for determining the best model are introduced, and the best model under the UPIoT is selected. This study provides a reference standard for the construction of GIS PD pattern recognition under the UPIoT. Meanwhile, through the balance of evaluation indicators, this study verifies that the minimum recognition accuracy of the MnasNet model is 98.8%, which is obviously better than other methods and lays a solid foundation for GIS PD pattern recognition.

[1]  Feng Li,et al.  Partial Discharge Feature Extraction Based on Ensemble Empirical Mode Decomposition and Sample Entropy , 2017, Entropy.

[2]  Masayuki Hikita,et al.  New aspects of UHF PD diagnostics on gas-insulated systems , 2014, IEEE Transactions on Dielectrics and Electrical Insulation.

[3]  Shigemitsu Okabe,et al.  Insulation characteristics of epoxy insulator with internal delamination-shaped micro-defects , 2013, IEEE Transactions on Dielectrics and Electrical Insulation.

[4]  Yong-Hwa Kim,et al.  Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear , 2018 .

[5]  A. A. Al-Arainy,et al.  Partial discharge pattern analysis using support vector machine to estimate size and position of metallic particle adhering to spacer in GIS , 2014 .

[6]  Haitham Abu-Rub,et al.  Partial discharge detection and diagnosis in gas insulated switchgear: State of the art , 2019, IEEE Electrical Insulation Magazine.

[7]  Wei Li,et al.  GIS partial discharge pattern recognition based on the chaos theory , 2014, IEEE Transactions on Dielectrics and Electrical Insulation.

[8]  Jieming Zhang,et al.  Feature extraction of GIS partial discharge signal based on S-transform and singular value decomposition , 2017 .

[9]  Junyi Li,et al.  A MobileNets Convolutional Neural Network for GIS Partial Discharge Pattern Recognition in the Ubiquitous Power Internet of Things Context: Optimization, Comparison, and Application , 2019, IEEE Access.

[10]  A. Beroual,et al.  Utilization of artificial neural network for the estimation of size and position of metallic particle adhering to spacer in GIS , 2013, IEEE Transactions on Dielectrics and Electrical Insulation.

[11]  Rui Huang,et al.  Assessment of PD severity in gas-insulated switchgear with an SSAE , 2017 .

[12]  Noureddine Harid,et al.  Simulation of Partial Discharge Induced EM Waves Using FDTD Method—A Parametric Study , 2019 .

[13]  Gehao Sheng,et al.  GIS partial discharge pattern recognition via deep convolutional neural network under complex data source , 2018, IEEE Transactions on Dielectrics and Electrical Insulation.

[14]  Chen Xin,et al.  Workload Allocation Mechanism for Minimum Service Delay in Edge Computing-Based Power Internet of Things , 2019, IEEE Access.

[15]  Min Chen,et al.  Improving the Error of Time Differences of Arrival on Partial Discharges Measurement in Gas-Insulated Switchgear , 2018, Sensors.

[16]  Steven Lanzisera,et al.  Communicating Power Supplies: Bringing the Internet to the Ubiquitous Energy Gateways of Electronic Devices , 2014, IEEE Internet of Things Journal.

[17]  Ian Gilbert,et al.  Partial Discharge Classification Using Deep Learning Methods—Survey of Recent Progress , 2019, Energies.

[18]  Yasin Khan,et al.  Partial discharge pattern analysis using PCA and back-propagation artificial neural network for the estimation of size and position of metallic particle adhering to spacer in GIS , 2016 .

[19]  Xiaohua Wang,et al.  Experimental Investigation on Propagation Characteristics of PD Radiated UHF Signal in Actual 252 kV GIS , 2017 .

[20]  Yoshihiro Baba,et al.  Finite-difference time-domain simulation of partial discharges in a gas insulated switchgear , 2016 .

[21]  Wei Hu,et al.  Selection of Cluster Heads for Wireless Sensor Network in Ubiquitous Power Internet of Things , 2019, Int. J. Comput. Commun. Control.

[22]  Ming Tang,et al.  Study on mathematical model for VHF partial discharge of typical insulated defects in GIS , 2007, IEEE Transactions on Dielectrics and Electrical Insulation.

[23]  Javier Ortego,et al.  Application of HFCT and UHF Sensors in On-Line Partial Discharge Measurements for Insulation Diagnosis of High Voltage Equipment , 2015, Sensors.

[24]  Mingyang Wu,et al.  Depthwise separable convolution architectures for plant disease classification , 2019, Comput. Electron. Agric..

[25]  Aijun Yang,et al.  Partial Discharge Recognition with a Multi-Resolution Convolutional Neural Network , 2018, Sensors.

[26]  Yanbin Zhang,et al.  Study on the Partial Discharge Characteristics and Development Process in Use of the Multiple Discharge Patterns for the Typical Defects in Gas-Insulated Switchgear , 2016, Canadian Journal of Electrical and Computer Engineering.