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), Journal Name: IEEE Transactions on Power Delivery (Institute of Electrical and Electronics Engineers); (USA) Vol. 5:2; ISSN 0885-8977; ISSN ITPDE
- Country of Publication:
- United States
- Language:
- English
Similar Records
A microprocessor-based digital feeder monitor with high-impedance & fault detection
Incipient fault detection and identification in process systems using accelerating neural network learning
Related Subjects
240100* -- Power Systems-- (1990-)
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
COMPUTERIZED CONTROL SYSTEMS
CONTROL SYSTEMS
DATA PROCESSING
ELECTRICAL FAULTS
EQUIPMENT PROTECTION DEVICES
NEURAL NETWORKS
POWER DISTRIBUTION SYSTEMS
PROCESSING
TRAINING