Research on the generation of localized overheating samples and fault prediction models of transformers and based on brain-inspired spiking neural networks

被引：0

作者：

Zhang, Guoliang ^{[1
]}

Zhang, Peng ^{[1
]}

Zhou, Fei ^{[1
]}

Du, Zexu ^{[1
]}

Chen, Jiangqi ^{[1
]}

Zhang, Zhisong ^{[1
]}

Kong, Qingyu ^{[1
]}

机构：

[1] Electic Power Res Inst Co Ltd, Beijing 100182, Peoples R China

来源：

INTERNATIONAL JOURNAL OF LOW-CARBON TECHNOLOGIES | 2025年 / 20卷

关键词：

transformer; thermal fault; spiking neural networks; fuzzy rules; OIL;

D O I：

10.1093/ijlct/ctae294

中图分类号：

O414.1 [热力学];

学科分类号：

摘要：

The prediction of transformer failures holds significant importance for maintaining the stability of power systems. This paper investigates the application of a brain-inspired spiking neural network model for fault prediction of transformers. The research is grounded in dissolved gas analysis, employing fuzzy reasoning spiking neural P systems to process fuzzy diagnostic knowledge. It constructs a set of sample data associated with localized overheating and utilizes linguistic variables, membership functions, and an inference rule base to conduct fault analysis. The results indicate that this approach significantly enhances the fault identification and predictive capabilities of transformers.

引用

页码：436 / 442

页数：7

共 20 条

[1] Thiviyanathan VA, Ker PJ, Leong YS., Et al., Power transformer insulation system: a review on the reactions, fault detection, challenges and future prospects, Alex Eng J, 61, pp. 7697-7713, (2022)
[2] Shiravand V, Faiz J, Samimi MH., Et al., Prediction of transformer fault in cooling system using combining advanced thermal model and thermography, IET Gener Transm Distrib, 15, pp. 1972-1983, (2021)
[3] Christina AJ, Salam MA, Rahman QM., Et al., Causes of transformer failures and diagnostic methods–a review, Renew Sustain Energy Rev, 82, pp. 1442-1456, (2018)
[4] Gouda OE, El-Hoshy SH, EL-Tamaly H H., Proposed three ratios technique for the interpretation of mineral oil transformers based dissolved gas analysis, IET Gener Transm Distrib, 12, pp. 2650-2661, (2018)
[5] Aizpurua JI, Catterson VM, Stewart BG., Et al., Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing, IEEE Trans Dielectr Electr Insul, 25, pp. 494-506, (2018)
[6] Grobelna I, Szczesniak P., Interpreted petri nets applied to autonomous components within electric power systems, Appl Sci, 12, (2022)
[7] Zarkovic M, Stojkovic Z., Analysis of artificial intelligence expert systems for power transformer condition monitoring and diagnostics, Electr Pow Syst Res, 149, pp. 125-136, (2017)
[8] Hong L, Chen Z, Wang Y., Et al., A novel SVM-based decision framework considering feature distribution for power transformer fault diagnosis, Energy Rep, 8, pp. 9392-9401, (2022)
[9] Xie J, Zhang J, Sun J., Et al., A transformer-based approach combining deep learning network and spatial-temporal information for raw EEG classification, IEEE Trans Neural Syst Rehabil Eng, 30, pp. 2126-2136, (2022)
[10] Wenhua W, Rui C, Yu C., Et al., Research on standardization of power transformer monitoring and early warning based on multisource data, Front Energy Res, 12, (2024)

← 1 2 →