A neural network approach to the detection of incipient faults on power distribution feeders
- Electric Power Research Center, College of Engineering, North Carolina State Univ., Raleigh, NC (US)
A high-impedence fault is an abnormal event on an electric power distribution feeder which can not be easily detected by conventional overcurrent protective devices. This paper describes a neural network strategy for the detection of this type of incipient fault. Neural networks are particularly well-suited for solving difficult signal processing and pattern recognition problems. An optimization technique allows a network to learn rules for solving a problem by processing a set of example cases. The data preprocessing required to set up the training cases and the implementation of the neural network itself are described. The potential of the neural network approach is demonstrated by applying the detection scheme to high- impedence faults simulated on a model distribution system.
- OSTI ID:
- 7081011
- Journal Information:
- IEEE Transactions on Power Delivery (Institute of Electrical and Electronics Engineers); (USA), Vol. 5:2; ISSN 0885-8977
- Country of Publication:
- United States
- Language:
- English
Similar Records
Early detection of incipient faults in power plants using accelerated neural network learning
A microprocessor-based digital feeder monitor with high-impedance fault detection
Related Subjects
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
POWER DISTRIBUTION SYSTEMS
ELECTRICAL FAULTS
COMPUTERIZED CONTROL SYSTEMS
DATA PROCESSING
EQUIPMENT PROTECTION DEVICES
NEURAL NETWORKS
TRAINING
CONTROL SYSTEMS
PROCESSING
240100* - Power Systems- (1990-)
990200 - Mathematics & Computers