Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

ANN based transformer fault diagnosis using gas-in-oil analysis

Conference ·
OSTI ID:103711
; ;  [1];  [2]
  1. Virginia Polytechnic Inst. and State Univ., Blacksburg, VA (United States). Bradley Dept. of Electrical Engineering
  2. Doble Engineering Co., Watertown, MA (United States)

This paper presents an artificial neural network (ANN) approach to detect faults in oil-filled power transformers. The relationship between transformer faults of power transformers and gases dissolved in insulating oil is reviewed. ANN based data processing and diagnostic techniques are described. Preliminary simulation results show a 95% correct diagnosis rate for the ANN based method with modest amount of training data.

OSTI ID:
103711
Report Number(s):
CONF-950414--
Country of Publication:
United States
Language:
English

Similar Records

An artificial neural network approach to transformer fault diagnosis
Journal Article · Tue Oct 01 00:00:00 EDT 1996 · IEEE Transactions on Power Delivery · OSTI ID:422769

Developing a new transformer fault diagnosis system through evolutionary fuzzy logic
Journal Article · Mon Mar 31 23:00:00 EST 1997 · IEEE Transactions on Power Delivery · OSTI ID:492195

Nuclear power plant fault-diagnosis using neural networks with error estimation
Journal Article · Fri Dec 30 23:00:00 EST 1994 · Transactions of the American Nuclear Society · OSTI ID:89046