Power equipment fault entity recognition based on BERT-CRF model

Yanfang Zhang; Yanru Zhong; Xiaonan Luo

doi:10.1117/12.3009433

16 October 2023 Power equipment fault entity recognition based on BERT-CRF model

Yanfang Zhang, Yanru Zhong, Xiaonan Luo

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128033H (2023) https://doi.org/10.1117/12.3009433
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

With the ongoing development of the national power grid, fault data from power equipment exhibits various characteristics, including a wide range of entity types, weak interrelationships, and high complexity. Consequently, traditional methods fail to extract adequate entity information and struggle with situations involving the multiple meanings of terminology in different contexts. To tackle these challenges, this paper proposes a method for recognizing power equipment fault entities based on the BERT-CRF model. The method initially employs web crawlers to retrieve literature related to power equipment faults. It then inductively designs five distinct types of power equipment fault entities and annotates a dataset accordingly. Subsequently, the BERT model is combined with the CRF model to recognize power equipment fault entities. The experimental results are then compared with those of the BiLSTM-CRF model and other domain datasets to evaluate the impact of power equipment fault entity types and label quantities. The experimental results confirm the feasibility and effectiveness of the BERT-CRF model, enabling the extraction of a wider range of power equipment fault entities from a smaller corpus of data.

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

Citation Download Citation

Yanfang Zhang, Yanru Zhong, and Xiaonan Luo "Power equipment fault entity recognition based on BERT-CRF model", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128033H (16 October 2023); https://doi.org/10.1117/12.3009433

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