Digital twin-based fault detection for intelligent power production lines
by You Zhou; Xuefeng Qian; Dan Xu; Can Zhao; Kejun Qian
International Journal of Computational Science and Engineering (IJCSE), Vol. 27, No. 4, 2024

Abstract: Digital twin technology realises real-time capture of system operation status, real-time monitoring and prediction of potential risks. In view of this, a fault detection method based on digital twin of power production line is proposed, where the attention technology required by virtual production line fault capture technology and model establishment combined with deep reinforcement learning model is used to analyse the power production line and realise fault detection. The method takes the node-related features of the visualisation equipment and power production line as input, analyses the possible production line faults through computer vision, and performs image recognition on all the collected pictures. The feature data collected by installing inspection equipment has rich information and spatiotemporal accompanying information of intelligent power production line, and the fault detection model of intelligent power production line constructed by digital twin has high confidence. The experimental results verified the effectiveness of the proposed method.

Online publication date: Fri, 05-Jul-2024

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 Computational Science and Engineering (IJCSE):
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