Developing a new transformer fault diagnosis system through evolutionary fuzzy logic
- National Cheng Kung Univ., Tainan (Taiwan, Province of China). Dept. of Electrical Engineering
- Chung Yuan Christian Univ., Chung-Li (Taiwan, Province of China). Dept. of Electrical Engineering
To improve the diagnosis accuracy of the conventional dissolved gas analysis (DGA) approaches, this paper proposes an evolutionary programming (EP) based fuzzy system development technique to identify the incipient faults of the power transformers. Using the IEC/IEEE DGA criteria as references, a preliminary framework of the fuzzy diagnosis system is first built. Based on previous dissolved gas test records and their actual fault types, the proposed EP-based development technique is then employed to automatically modify the fuzzy if-then rules and simultaneously adjust the corresponding membership functions. In comparison to results of the conventional DGA and the artificial neural networks (ANN) classification methods, the proposed method has been verified to possess superior performance both in developing the diagnosis system and in identifying the practical transformer fault cases.
- OSTI ID:
- 492195
- Report Number(s):
- CONF-960725--
- Journal Information:
- IEEE Transactions on Power Delivery, Journal Name: IEEE Transactions on Power Delivery Journal Issue: 2 Vol. 12; ISSN ITPDE5; ISSN 0885-8977
- Country of Publication:
- United States
- Language:
- English
Similar Records
An expert system for transformer fault diagnosis using dissolved gas analysis
An expert system for fault section diagnosis of power systems using fuzzy relations