[1] Zhou Jianhua, Hu Minqiang, Tang Guoqing,. Hologamous integrating strategiesfor incipient fault diagnosis of transformer [J]. Journal of Southeast University (English Edition), 2004, 20 (4): 503-507. [doi:10.3969/j.issn.1003-7985.2004.04.022]
Copy
Hologamous integrating strategiesfor incipient fault diagnosis of transformer(
)
变压器内部故障诊断的融合集成策略研究
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 20
- Issue:
- 2004 4
- Page:
- 503-507
- Research Field:
- Electrical Engineering
- Publishing date:
- 2004-12-30
Info
- Title:
- Hologamous integrating strategiesfor incipient fault diagnosis of transformer
- 变压器内部故障诊断的融合集成策略研究
- Author(s):
- Zhou Jianhua; Hu Minqiang; Tang Guoqing
- Department of Electrical Engineering, Southeast University, Nanjing 210096, China
- Keywords:
- integrating; hologamous system; fault diagnosis; power transformer
- PACS:
- TM41
- DOI:
- 10.3969/j.issn.1003-7985.2004.04.022
- Abstract:
- This paper studies an integrative fault diagnostic system on the power transformer. On-line monitor items are grounded current of iron core, internal partial discharge and oil dissolved gas. Diagnostic techniques are simple rule-based judgment, fuzzy logistic reasoning and neural network distinguishing. Considering that much faults information is interactional, intellectualized diagnosis is implemented based on integrating the neural network with the expert system. Hologamous integrating strategies are materialized by information-based integrating monitor devices, shared information database on several levels and fusion diagnosis software along thought patterns. The expert system practices logic thought by logistic reasoning. The neural network realizes image thought by model matching. Creative conclusion is educed by their integrating. The diagnosis example shows that the integrative diagnostic system is reasonable and practical.
- 研究了变压器故障的集成融合诊断系统. 该系统中在线监测项目主要有铁心接地电流、局部放电和油中溶解气体; 分析手段包括简单规则判断、模糊逻辑推理和神经网络判别. 考虑到众多故障信息的相互影响, 基于神经网络和专家系统的集成实现智能化诊断. 其融合集成策略主要包括基于信息集成监测装置、多层次地共享信息库和遵循思维规律融合诊断等, 该专家系统实现了推理式的逻辑思维, 神经网络实现了模式化的形象思维, 它们相互结合可得出创造性的结论. 给出了本文系统的一个实例, 表明融合诊断更合理可行.
References:
[1] Kan Hisao, Miyamoto Teruo. Proposals for an improvement in transformers diagnosis using dissolved gas analysis(DGA)[J]. IEEE Trans on Electrical Insulation Magazine, 1995, 11(6): 15-21.
[2] Farag A S, Shewhdi M H, Jin X, et al. On-line partial discharge calibration and monitoring for power transformers [J]. Electric Power Systems Research, 1999, 50(1): 47-54.
[3] Zhou Jianhua, Hu Minqiang. A database-based diagnostic expert system of transformer’s faults [J]. Journal of Southeast University(Natural Science Edition), 1998, 28(6): 68-73.(in Chinese)
[4] Mazroua A A, Bartnikas R, Salama M M A. Discrimination between PD pulse shapes using different neural network paradigms [J]. IEEE Trans on Dielectrics and Electrical Insulation, 1994, 1(6): 1119-1131.
[5] Zhou Jianhua, Hu Minqiang, Zhou E. On the application of CP-BP algorithm for DGA-NN diagnosis in power transformer [J]. Proceedings of the CSEE, 1999, 19(3): 41-45.(in Chinese)
[6] Kang P, Birtwhistle D. Condition monitoring of power transformer on-load tap-changers, part 1: automatic condition diagnostics [J]. IEE Proceedings of Generation, Transmission and Distribution, 2001, 148(4): 301-306.
[7] Zhou Jianhua, Hu Minqiang, Zhou E. Integrating ES with ANN in fault diagnosis based on thinking-pattern [J]. Transactions of China Electrotechnical Society, 1999, 12(2): 1-4.(in Chinese)
[8] Qian Zheng, Yan Zhang, Luo Chengmu. A study on synthetic diagnosis method for insulation of power transformers [J]. Power System Technology, 2002, 26(2): 32-36.(in Chinese)
Memo
- Memo:
- Biographies: Zhou Jianhua(1968—), male, doctor, associate professor, zjhmax@seu.edu.cn; Hu Minqiang(1961—), male, doctor, professor, mqhu@seu.edu.cn.