NOTE: This item is not available outside the Texas A&M University network. Texas A&M affiliated users who are off campus can access the item through NetID and password authentication or by using TAMU VPN. Non-affiliated individuals should request a copy through their local library's interlibrary loan service.
Neural net application to transmission line fault detection and classification
MetadataShow full item record
Today, in electric power systems, a large amount of data is made readily available at the occurrence of a fault due to the use of advanced communication systems, digital relays and fault recorders. Such systems are intended to obtain data from contacts of the relays and circuit breakers under operation. In addition, corresponding voltages and currents are recorded during prefault, fault and postfault periods. Restoration of power Systems after a fault occurred requires quick judgment. Hence, fault analysis, as the first step of restoration is very important. However, since faults in power systems are various and relaying systems may be complex, fault analysis is difficult to automate. Common practice in power utility companies, today, is to perform fault analysis by expert operators using their knowledge about the power systems and experience with past faults. Because of the time required to deal with complex fault situations, detailed fault analysis can not be performed by human operators in a short time. Therefore, on-line automated fault analysis system is strongly desired. Traditional approaches to the problem of analysis is to construct a heuristic, rule-based system which embodies a portion of the compiled experience of a human expert. These systems perform fault analysis by mapping fault indications to fault hypotheses. 'These hypotheses are used as inputs for next level of rules. After completion of inferencing process, conclusions are given. The knowledge acquisition process is exhaustive and time consuming. Also, data processing is usually too slow to be effectively applied in a real-time environment. Neural computing is one of the rapidly expanding areas of current research. Neural nets have some obvious advantages over expert systems. They are computationally more effective because of their parallel processing capabilities. Also, there is no need for detailed knowledge acquisition part, because neural nets learn by example. This thesis presents results of a study on using the new neural net system that can perform both on-line and off-line fault detection and classification. Fault analysis is conceptualized as a pattern classification problem which involves the association of input patterns representing the power system state to one or more fault conditions.
DescriptionDue to the character of the original source materials and the nature of batch digitization, quality control issues may be present in this document. Please report any quality issues you encounter to firstname.lastname@example.org, referencing the URI of the item.
Includes bibliographical references.
Rikalo, Igor (1994). Neural net application to transmission line fault detection and classification. Master's thesis, Texas A&M University. Available electronically from
Request Open Access
This item and its contents are restricted. If this is your thesis or dissertation, you can make it open-access. This will allow all visitors to view the contents of the thesis.