Pattern Recognition Methods of Multi-source Partial Discharge Based on the Improved Deformable DETR Model and its Application

被引：1

作者：

Lei, Zhipeng ^{[1
]}

Peng, Chuan ^{[1
]}

Xu, Zihan ^{[1
]}

Jiang, Wanting ^{[1
]}

Li, Chuanyang ^{[2
]}

Lin, Lingyan ^{[1
]}

Peng, Bangfa ^{[1
]}

机构：

[1] Shanxi Key Laboratory of Mining Electrical Equipment and Intelligent Control, College of Electrical and Power Engineering, Taiyuan University of Technology, Shanxi Province, Taiyuan

[2] State Key Laboratory of Power System and Generation Equipment, Department of Electrical Engineering, Tsinghua University, Haidian District, Beijing

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2024年 / 44卷 / 15期

基金：

中国国家自然科学基金;

关键词：

Deformable DETR; multi-source partial discharge; object detection; partial discharge; pattern recognition;

D O I：

10.13334/j.0258-8013.pcsee.240009

中图分类号：

学科分类号：

摘要：

Pattern recognition methods of partial discharge (PD) utilizing images are efficient for the single PD source, yet they face challenges in recognizing the multi-source PD. An object detection model is proposed for the recognition of multi-source PD according to Deformable detection with transformers (Deformable DETR). Typical single-source PD and multi-source PD signals are collected by experiment. Two types of PD spectra, namely phase-resolved partial discharge spectrum and polar coordinate phase-resolved spectrum, are used to generate the data set. The denoising training task and Bayesian optimization algorithm are introduced to optimize the performance of the Deformable DETR model. Single-source and multi-source PD spectra are identified by the optimized PD Deformable DETR model. Results show that the proposed model can effectively recognize the source of single- and multi-PD patterns. In addition, compared with common types of object detection models, the performance of the PD Deformable DETR model can be evidently improved at the cost of losing a few efficiencies. Finally, the PD spectra of real motors with insulation defects are identified by the PD Deformable DETR model. The recognition accuracy reaches 91%, which shows the validity of this proposed method. Additionally, the acquisition and recognition program of PD spectrum is developed. The paper provides novel perspectives for identifying multi-source PD. ©2024 Chin.Soc.for Elec.Eng.

引用

页码：6248 / 6260

页数：12

共 29 条

[1]

KUCHLER A．, High voltage engineering：fundamentals -technology-applications[M], (2018)

[2]

Yuan XU, LIU Weidong, CHEN Weijiang, High-sensitivity measurement method and application of GIS spacer partial discharge[J], Proceedings of the CSEE, 40, 5, pp. 1703-1712, (2020)

[3]

LEI Zhipeng, SHI Zhijie, DU Yupeng, Effect of the properties of insulating materials on the surface electrostatic discharge under positive pulse volage[J], High Voltage Engineering, 49, 6, pp. 2662-2670, (2023)

[4]

WANG Hongxia, WANG Bo, ZHANG Jiaxin, Pattern recognition of partial discharge using imbalanced acoustic array data based on spatial correlation and temporal correlation feature fusion method[J], High Voltage Engineering, 50, 5, pp. 1913-1922, (2024)

[5]

Qing XIE, ZHANG Xuanyu, WANG Chunxin, Application status and prospect of the new generation artificial intelligence technology in the state evaluation of power transmission and transformation equipment[J], High Voltage Apparatus, 58, 11, pp. 1-16, (2022)

[6]

MAJIDI M, OSKUOEE M．, Improving pattern recognition accuracy of partial discharges by new data preprocessing methods[J], Electric Power Systems Research, 119, pp. 100-110, (2015)

[7]

YAO Rui, LI Jun, HUI Meng, Pattern recognition for partial discharge using adaptive boost classification model based on ensemble method[J], Power System Technology, 46, 6, pp. 2410-2419, (2022)

[8]

WANG Yanxin, Jing YAN, WANG Zhanbei, Multi-source partial discharge diagnosis in gas-insulated switchgear via zero-shot learning[J], Measurement, 217, (2023)

[9]

WU Min, JIANG Wei, LUO Yingting, Multi-source partial discharge pattern recognition in GIS based on improved SSD[J], High Voltage Engineering, 49, 2, pp. 812-821, (2023)

[10]

CARION N, MASSA F, SYNNAEVE G, End-to-end object detection with transformers[C], 16th European Conference on Computer Vision, pp. 213-229, (2020)

← 1 2 3 →