On the application of a machine learning technique to fault diagnosis of power distribution lines

Author

Togami, Masato ; Abe, Norihiro ; Kitahashi, Tadahiro ; Ogawa, Harunao

Author_Institution

Nagoya Mfg., Japan

Volume

10

Issue

4

fYear

1995

fDate

10/1/1995 12:00:00 AM

Firstpage

1927

Lastpage

1936

Abstract

This paper presents one method for fault diagnosis of power distribution lines by using a decision tree. The conventional method, using a decision tree, applies only to discrete attribute values. To apply it to fault diagnosis of power distribution lines in practice, it must be revised in order to treat attributes whose values range over certain widths. This is because the sensor value or attribute value varies owing to the resistance of the fault point or is influenced by noise. The proposed method is useful when the attribute value has such a property, and it takes into consideration the cost of acquiring the information and the probability of the occurrence of a fault

Keywords

decision theory; diagnostic expert systems; distribution networks; fault diagnosis; fault location; learning (artificial intelligence); neural nets; power system analysis computing; decision tree; discrete attribute values; expert systems; fault diagnosis; fault occurrence probability; fault point resistance; machine learning technique; neural nets; power distribution lines; Circuit faults; Decision trees; Diagnostic expert systems; Electrical fault detection; Fault diagnosis; Immune system; Machine learning; Power distribution; Power distribution lines; Sensor phenomena and characterization;

fLanguage

English

Journal_Title

Power Delivery, IEEE Transactions on

Publisher

ieee

ISSN

0885-8977

Type

jour

DOI

10.1109/61.473361

Filename

473361