Deep multi-modal imaging temperature measurement method for detecting temperature rise in electrical equipment faults

In modern industry and power systems, electrical equipment serves as the backbone of numerous operations and infrastructure. Temperature rise is one of the primary indicators of emerging faults in electrical equipment. However, traditional temperature measurement methods face significant challenges....

Full description

Saved in:
Bibliographic Details
Main Authors: Jinxuan Wen, Jiangjiang Li, Yachao Zhang
Format: Article
Language:English
Published: Tamkang University Press 2025-07-01
Series:Journal of Applied Science and Engineering
Subjects:
Online Access:http://jase.tku.edu.tw/articles/jase-202603-29-03-0011
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In modern industry and power systems, electrical equipment serves as the backbone of numerous operations and infrastructure. Temperature rise is one of the primary indicators of emerging faults in electrical equipment. However, traditional temperature measurement methods face significant challenges. To overcome these limitations, this paper proposes a deep multi-modal image fusion method. The method integrates data from multiple imaging modalities and uses deep learning algorithms to fuse and analyze this information. By applying Bayes theorem and introducing a variational distribution, the method approximates the true posterior. A weight vector is used to aggregate the complementary and consistent information of hidden variables from various modalities, allowing the model to emphasize more informative modalities while incorporating information from others. Experimental results on two datasets demonstrate the effectiveness of our method in comparison with methods, showing the best detection results about accuracy, precision, recall, and F1 score.
ISSN:2708-9967
2708-9975