Training an artificial neural network to discriminate between magnetizing inrush and internal faults

Journal Article · Sat Jan 01 04:00:00 EST 1994 · IEEE Transactions on Power Delivery (Institute of Electrical and Electronics Engineers); (United States)

DOI:https://doi.org/10.1109/61.277715· OSTI ID:7115265

Perez, L G; Flechsig, A J; Meador, J L; Obradovic, Z ^[1]

---

1. Washington State Univ., Pullman, WA (United States). School of Electric Engineering and Computer Science

A feed forward neural network (FFNN) has been trained to discriminate between power transformer magnetizing inrush and fault currents. The training algorithm used was back-propagation, assuming initially a sigmoid transfer function for the network's processing units (neurons). Once the network was trained the units' transfer function was changed to hard limiters with thresholds equal to the biases obtained for the sigmoids during training. The off-line experimental results presented in this paper show that a FFNN may be considered as an alternative method to make the discrimination between inrush and fault currents in a digital relay implementation.

• OSTI ID: 7115265
• Journal Information: IEEE Transactions on Power Delivery (Institute of Electrical and Electronics Engineers); (United States), Journal Name: IEEE Transactions on Power Delivery (Institute of Electrical and Electronics Engineers); (United States) Journal Issue: 1 Vol. 9:1; ISSN ITPDE5; ISSN 0885-8977
• Country of Publication: United States
• Language: English

Related Subjects

24 POWER TRANSMISSION AND DISTRIBUTION
240100* -- Power Systems-- (1990-)
CURRENTS
EDUCATION
ELECTRIC CURRENTS
ELECTRICAL EQUIPMENT
ELECTRICAL FAULTS
ENERGY SYSTEMS
EQUIPMENT
NEURAL NETWORKS
POWER SYSTEMS
TRAINING
TRANSFORMERS