Partial Discharge Pattern-Recognition Method Based on Embedded Artificial Intelligence
Source abstract
Abstract
This paper proposes a method for detecting and recognizing partial discharges in high-voltage (HV) equipment. The aim is to address issues commonly found in traditional systems, including complex operations, high computational demands, significant power consumption, and elevated costs. Various types of discharges were investigated in an HV laboratory environment. Discharge data were collected using a high-frequency current sensor and a microcontroller. Subsequently, this data underwent processing and transformation into feature sets using the phase-resolved partial discharge analysis technique. These features were then converted into grayscale map samples in PNG format. To achieve partial discharge classification, a convolutional neural network (CNN) was trained on these samples. After successful training, the network model was adapted for deployment on a microcontroller, facilitated by the STM32Cube.AI ecosystem, enabling real-time partial discharge recognition. The study also examined storage requirements across different CNN layers and their impact on recognition efficacy. To assess the algorithm’s robustness, recognition accuracy was tested under varying discharge voltages, insulation media thicknesses, and noise levels. The test results demonstrated that the algorithm could be effectively implemented on a microcontroller, achieving a recognition accuracy exceeding 98%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: High voltage insulation and dielectric phenomena · Electrical Fault Detection and Protection · Power Transformer Diagnostics and Insulation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical Engineering, Xi’an University of Post and Telecommunications, Xi’an 710121, China
References (43)
Show source-provided references
1. Chen, Q. (2016). Non-Linear Ethylene Propylene Rubber and Its Application in DC Cable Accessories, Harbin Institute of Technology.
2. Florkowski, M. (2021). Anomaly Detection, Trend Evolution, and Feature Extraction in Partial Discharge Patterns. Energies, 14.10.3390/en14133886 ↗
3. Huang, T., Hao, Y., Xiao, J., Chen, Y., Chen, Y., Yang, L., Wang, C., and Li, L. (2021). Comparative study of industrial frequency partial discharge characteristics of typical installation defects in 10 kV XLPE cable terminations. Grid Technol.
4. Current Status of Research on Partial Discharge Models in Insulating Materials
5. Study on the propagation characteristics of partial discharge electrical signals in cables
6. Causes and prevention of cable fires in coal mines
7. Analysis of 10 kV cable insulation breakdown accidents at Longkou Hydropower Station and preventive measures
8. Typical fault case analysis of cable termination in 10kV ring network cabinet
9. A case of irregularly laid 10 kV power cable fault analysis
10. (2018). High Voltage Test Technology Partial Discharge Measurement (Standard No. GB/T7354—2018).
11. Local discharge pulse waveform feature extraction and classification techniques
12. Partial discharge diagnostics and electrical equipment insulation condition assessment10.1109/TDEI.2005.1522184 ↗
13. Review on the Status Quo of Partial Discharge Technical Standards for Power Equipment
14. Faizol, Z., Zubir, F., Saman, N.M., Ahmad, M.H., Rahim, M.K.A., Ayop, O., Jusoh, M., Majid, H.A., and Yusoff, Z. (2023). Detection Method of Partial Discharge on Transformer and Gas-Insulated Switchgear: A Review. Appl. Sci., 13.10.20944/preprints202307.0333.v1 ↗
15. Research on Insulation Test Method of Partial Discharge Based on Ultrasonic Measurement
16. Gan, D., Liu, F., and Xiao, W. (2013). Partial discharge monitoring system integrating ultra-high frequency and pulse current method. Electr. Power Autom. Equip., 33.
17. Yu, C., and Wu, W. Transformer partial discharge localization method based on ultra-high frequency sensor. Proceedings of the 10th Shenyang Science Annual Conference (Information Science and Engineering Technology Module).
18. Huang, C. (2014). Research on On-line Monitoring of Partial Discharge in High Voltage Switchgear Based on UHF Method. [Master’s Thesis, Chongqing University].
19. Partial discharge diagnosis of gas-insulated metal-enclosed transmission lines based on vibration signals
20. Application of data mining on partial discharge Part I: Predictive modelling classification10.1109/TDEI.2010.5492258 ↗
21. Schober, B., and Schichler, U. (2019, January 12–14). Application of Machine Learning for Partial Discharge Classification under DC Voltage. Proceedings of the Nordic Insulation Symposium, Vapriikki, Finland.10.5324/nordis.v0i26.3268 ↗
22. Partial discharge pattern recognition of high-voltage cables based on convolutional neural network
23. Partial discharge pattern recognition of multiple defects in gas-insulated switchgear based on PRPD mapping
24. Yang, J., Deng, M., Ma, Y., Ai, C., Li, Y., and Liu, C. (2020). Deep learning based feature extraction method for PRPD data. Electr. Meas. Instrum., 57.
25. Yin, K., Wang, Y., Liu, S., Li, P., Xue, Y., Li, B., and Dai, K. (2022). GIS Partial Discharge Pattern Recognition Based on Multi-Feature Information Fusion of PRPD Image. Symmetry, 14.10.3390/sym14112464 ↗
26. Li, G., Wang, X., Li, X., Yang, A., and Rong, M. (2018). Partial Discharge Recognition with a Multi-Resolution Convolutional Neural Network. Sensors, 18.10.3390/s18103512 ↗
27. Sikorski, W., and Wielewski, A. (2023). Low-Cost Online Partial Discharge Monitoring System for Power Transformers. Sensors, 23.10.3390/s23073405 ↗
28. Application of convolutional neural network in pattern recognition of partial discharge images
29. Deep learning10.1038/nature14539 ↗
30. Transformer partial discharge pattern recognition based on marginal spectral images and deep residual networks
31. Transformer PRPD mapping recognition based on multilayer feature fusion CNNs
32. Gianoglio, C., Ragusa, E., Bruzzone, A., Gastaldo, P., Zunino, R., and Guastavino, F. (2020). Unsupervised Monitoring System for Predictive Maintenance of High Voltage Apparatus. Energies, 13.10.3390/en13051109 ↗
33. Castro, B., Clerice, G., Ramos, C., Andreoli, A., Baptista, F., Campos, F., and Ulson, J. (2016). Partial Discharge Monitoring in Power Transformers Using Low-Cost Piezoelectric Sensors. Sensors, 16.10.3390/s16081266 ↗
34. Application of HFCT and UHF Sensors in Online Partial Discharge Measurements for Insulation Diagnosis of High Voltage Equipment10.3390/s150407360 ↗
35. Partial discharge type detection and identification based on its sources10.1088/1757-899X/1173/1/012022 ↗
36. Zhao, F., Liu, H., and Jia, H. (2021). Partial discharge process of insulating medium and construction of simulation model. Electr. Technol. Econ., 10–13.
37. Liu, B., and Zheng, J. (2017). Transformer partial discharge pattern recognition based on convolutional neural network. High Volt. Electr. Appl., 53.
38. Partial discharge classifications: Review of recent progress10.1016/j.measurement.2015.02.032 ↗
39. Chen, X., Qian, Y., Xu, Y., Shu, B., and Sheng, G. (2019). A novel pulse source-based method for measuring transfer impedance of high frequency current sensor. Electr. Power Autom. Equip., 39.
40. Din, E. (2000). Partial Discharge Measurement, European Standards Institute.
41. Zeiler, M., and Fergus, R. (2014). Visualizing and Understanding Convolutional Networks, Springer. European Conference on Computer vision.10.1007/978-3-319-10590-1_53 ↗
42. Elfwing, S., Uchibe, E., and Doya, K. (2018). Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. arXiv.10.1016/j.neunet.2017.12.012 ↗
43. (2021). STM32Cube.AI ecosystem strengthens support for efficient machine learning. Single Chip Microcomput. Embed. Syst. Appl., 21, 94.