A fault diagnosis and location method for power grid simulators based on voltage threshold and MCNN

Jinyue Su; Yingwen Yang; YiLin Yu; Yueshuo Li; Shiwei Zhao; Zhidong Wang; Ling Yang; Fengqiang Deng

doi:10.4108/ew.10406

Authors

Jinyue Su South China University of Technology
Yingwen Yang South China University of Technology
YiLin Yu South China University of Technology
Yueshuo Li South China University of Technology
Shiwei Zhao South China University of Technology
Zhidong Wang South China University of Technology
Ling Yang South China University of Technology
Fengqiang Deng South China University of Technology

DOI:

https://doi.org/10.4108/ew.10406

Keywords:

Power Grid Simulator, MCNN, Frequency Domain Transformation, Sliding Window Method, Sample Expansion

Abstract

To accommodate the testing requirements of high-power wind turbines, this paper designs a power grid simulator topology and investigates fault diagnosis and localization methods by integrating mathematical models and neural networks. To address the drawback of lengthy computation times associated with intelligent diagnostic methods, this paper employs a threshold-based approach using voltage mathematical models to achieve rapid preliminary diagnostics. To address the positioning challenges brought about by symmetrical structures, a multi-layer convolutional neural network (MCNN) model is utilized to achieve accurate positioning. To tackle the issue of insufficient fault samples, a sliding window technique and frequency domain transformation methods are applied to expand the sample set, enabling the diagnosis and localization of 36 types of faults. This paper builds an inverter-side model of the power grid simulator using Simulink to verify the proposed method. And the diagnostic accuracy rate reaches 100%, and the overall localization accuracy exceeds 96%.

Downloads

Download data is not yet available.

References

[1] Deng W, Dai N Y, Lao K W, et al. A virtual-impedance droop control for accurate active power control and reactive power sharing using capacitive-coupling inverters[J]. IEEE Transactions on Industry Applications, 2020, 56(6): 6722-6733.

[2] Deng W, Xiao D, Chen M, et al. Multi-regional energy sharing approach for shared energy storage and local renewable energy resources considering efficiency optimization[J]. International Journal of Electrical Power & Energy Systems, 2025, 167: 110592.

[3] Xiong L, Li P, Wu F, et al. Stability enhancement of power systems with high DFlG-windturbine penetration via virtual inertia planning[J. lEEE Transactions on Power Systems, 201934(2): 1352-1361.

[4] Liu J, Xu Y, Dong Z Y, et al. Retirement-driven dynamic VAR planning for voltage stabilityenhancement of power systems with high-level wind power{J]. IEEE Transactions on PowerSystems,2018,33(2):2282-2291.

[5] Shuai Z, Liu D, Shen J, et al. Series and parallel resonance problem of widebandfrequency harmonic and its elimination strategy[J]. lEEE Transactions on Power Electronics. 2014, 29(4):1941-1952.

[6] Li Houxiang, Zhang Yongming, Zhai Hongyu. Research on Topology and Control System of High Power Grid Simulator[J]. Journal of Physics: Conference Series, 2021, 2083(3).

[7] Feke, Chen Guochu. Parameter Design of Grid Simulator Based on Improved Proportional Resonance Controller [J]. Science and Technology Economic Review, 2018, 26(23): 23-24 + 37.

[8] Sobanski Piotr, Miskiewicz Milosz, Bujak Grzegorz, et al. Real Time Simulation of Power Electronics Medium Voltage DC-Grid Simulator[J]. Energies, 2021, 14(21): 7368-7368

[9] Wang Qi. Research on control technology of inverter side of grid simulator based on hierarchical repetitive adaptive control[D]. Nanjing University of Science & Technology, 2023.DOI:10.27241/d.cnki.gnjgu.2023.000561.

[10] Liu Shuxi, Liu Ke, Wang Qianyun, Qu Yufei, Luo Qin. Open-circuit fault diagnosis of MMC sub modules based on modal time-frequency diagrams and the Resnet-BiGRU model[J]. Power System Protection and Control, 2025, 53 (02): 73-88.

[11] Yang Heya, Xing Wenshuo, et al. A Fault Detection and Location Strategy for Sub-module Open-circuit Fault in Modular Multilevel Converters Based on Random Forest Binary Classifier[J].Proceedings of the CSEE, 2023,43(10):3916-3928. DOI:10.13334/j.0258-8013. pcsee. 221115.

[12] PABLO L, RICARDO A, JOSE R. Fault detection on multi-cell converter based on output voltage frequency analysis[J]. IEEE ransactions on Industrial Electronics, 2009, 56(6): 2275-2283.

[13] DENG Fujin, JIN Ming, LIU Chengkai, et al. Switch open-circuit fault localization strategy for MMCs using sliding-time window based features extraction algorithm[J]. IEEE Transactions on Industrial Electronics, 2021

[14] S. Kiranyaz, A. Gastli, L. Ben-Brahim, N. Al-Emadi, and M. Gabbouj, “Real time fault detection and identification for MMC using 1-D con-volutional neural networks,” IEEE Trans. Ind. Electron., vol. 66, no. 11, pp. 8760– 8771, Nov. 2019.

[15] J. Liu and Y. Ren, "A General Transfer Framework Based on Industrial Process Fault Diagnosis Under Small Samples," in IEEE Transactions on Industrial Informatics, vol. 17, no. 9, pp. 6073-6083, Sept. 2021, doi: 10.1109/TII.2020.3036159.

[16] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein generative adversarial networks,” in Proc. 34th Int. Conf. Mach. Learn., vol. 70, Aug. 2017, pp. 214–223.

[17] Choudhary, Sarika, and Nishtha Kesswani. "Analysis of KDD-Cup’99, NSL-KDD and UNSW-NB15 datasets using deep learning in IoT." Procedia Computer Science 167 (2020): 1561-1573.

[18] Mahalakshmi, G., et al. "Intrusion detection system using convolutional neural network on UNSW NB15 dataset." Advances in Parallel Computing Technologies and Applications. IOS Press, 2021. 1-8.