Neural net application to transmission line fault detection and classification /

areas of current research. Neural nets have some

Bibliographic Details
Main Author: Rikalo, Igor, 1967-
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1994.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:areas of current research. Neural nets have some
be complex, fault analysis is difficult to automate.
can not be performed by human operators in a short
circuit breakers under operation. In addition,
Common practice in power utility companies, today, is
compiled experience of a human expert. These systems
computationally more effective because of their
conceptualized as a pattern classification problem
consuming. Also, data processing is usually too slow
corresponding voltages and currents are recorded during
data is made readily available at the occurrence of a
detection and classification. Fault analysis is
digital relays and fault recorders. Such systems are
fault conditions.
fault due to the use of advanced communication systems,
fault hypotheses. 'These hypotheses are used as inputs
for next level of rules. After completion of
in power systems are various and relaying systems may
inferencing process, conclusions are given. The
intended to obtain data from contacts of the relays and
judgment. Hence, fault analysis, as the first step of
knowledge acquisition process is exhaustive and time
need for detailed knowledge acquisition part, because
Neural computing is one of the rapidly expanding
neural nets learn by example. This thesis presents
obvious advantages over expert systems. They are
parallel processing capabilities. Also, there is no
perform fault analysis by mapping fault indications to
power Systems after a fault occurred requires quick
prefault, fault and postfault periods. Restoration of
representing the power system state to one or more
restoration is very important. However, since faults
results of a study on using the new neural net system
rule-based system which embodies a portion of the
system is strongly desired. Traditional approaches to
that can perform both on-line and off-line fault
the problem of analysis is to construct a heuristic,
their knowledge about the power systems and experience
time. Therefore, on-line automated fault analysis
to be effectively applied in a real-time environment.
to perform fault analysis by expert operators using
Today, in electric power systems, a large amount of
which involves the association of input patterns
with complex fault situations, detailed fault analysis
with past faults. Because of the time required to deal
Item Description:"Major subject: Electrical Engineering".
Vita.
Physical Description:xii, 127 leaves : illustrations ; 28 cm.
Also available online.
Bibliography:Includes bibliographical references.