Research on anomaly identification of electric power metering device based on data driven model

Yan Li; Xi Li; Fating Zhang; Cunfen Yang; Shaonian Hu; Fengyu Liu

doi:10.1117/12.3004675

25 September 2023 Research on anomaly identification of electric power metering device based on data driven model

Yan Li, Xi Li, Fating Zhang, Cunfen Yang, Shaonian Hu, Fengyu Liu

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127885U (2023) https://doi.org/10.1117/12.3004675
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

In the process of judging the abnormality of power metering devices, the accuracy of identification results is relatively low due to the intersection of abnormal features. Therefore, a study on the abnormality identification of power metering devices based on data driven model is proposed. From the perspective of abnormal parts, the specific manifestations and causes of different abnormal types are analyzed, and the abnormalities of power metering devices are divided into 9 categories. In the process of analyzing the abnormal state of electric energy metering devices by constructing a data-driven model, a loss function is set for the data-driven model, and the interference of the cross identification results of abnormal features is avoided by using the conflict function between the output of the data-driven model and the field experience knowledge. Finally, the abnormal information that meets the requirements of the consistency check of the data-driven model is taken as the identification result of the abnormality of the power metering device. In the test results, the accurate identification of different types of power metering device anomalies by the design method is stable at 83.0%.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yan Li, Xi Li, Fating Zhang, Cunfen Yang, Shaonian Hu, and Fengyu Liu "Research on anomaly identification of electric power metering device based on data driven model", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127885U (25 September 2023); https://doi.org/10.1117/12.3004675

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available