A novel method for fault detection, classification and location in Ilam province's power transmission network
by Yavar Azarakhsh; Jafar Tavoosi
International Journal of Applied Pattern Recognition (IJAPR), Vol. 6, No. 4, 2021

Abstract: Due to the importance of continued energy supplying to subscribers, especially industrial subscribers, who are severely affected by any disruption in network parameters and network outages, we decided to use new technology and software to reduce network outages and even reducing the shutdown time. In this study, equipment and relays are used to diagnose and clear faults in transmission networks based on a novel Hopfield neural network. Then, the 230 kV power transmission network of Ilam province and its ten substations (63 kV) and several power plants located in the province are modelled using DIgSILENT Power Factory software. In this regard, first, the load distribution in normal network and the values of network parameters are recorded, then the values of network parameters are recorded in the faulty network. These values are fed to a novel fuzzy Hopfield neural network as training data, the results are compared with initial values and it is observed that fuzzy Hopfield neural network can quickly and accurately locate network faults.

Online publication date: Thu, 11-Nov-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Applied Pattern Recognition (IJAPR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com