
Entity Recognition for Power Equipment Data Based on Optional Word Vectors and Feature Fusion
Author(s) -
Min Chen,
Feixiang Liu,
Donggui Liang,
Shuying Zhong,
Yunting Li
Publication year - 2025
Publication title -
ieee access
Language(s) - English
Resource type - Magazines
SCImago Journal Rank - 0.587
H-Index - 127
eISSN - 2169-3536
DOI - 10.1109/access.2025.3598316
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
Power equipment is an essential part of the power system. Regular inspection and maintenance of power equipment are of great significance. However, the existing entity recognition methods for power equipment data have certain limitations. Therefore, this paper introduces continuous bag of words to optimize Convolutional Neural Network and Long Short-Term Memory network. Meanwhile, Variational Autoencoder is introduced to improve Conditional Generative Adversarial Network. These two methods are combined to form an algorithm that integrates textual data and image information features. On this basis, conditional random field is used for secondary optimization, and an intelligent recognition model is constructed. Its superiority and feasibility are verified by comparison with three traditional models. The results show that the proposed model achieves an accuracy of 96.8%, a recall of 97.6%, an average error of 0.11%, and a loss rate of 0.18%. In practical applications, the model achieves a recall of 97.6% and an Aear Under the Curve value of 0.831. When facing different datasets, its average sensitivity reaches 97.6%. Comparative experiments also demonstrate its robustness and generalization ability. All experimental data and results outperform the three comparative models. In conclusion, the proposed model ensures the quality of power equipment data entity recognition and effectively improves recognition efficiency, making an important contribution to the healthy development of the power system in China.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom