Air pressure prediction model based on the fusion of laser-induced plasma images and spectra

The vacuum switch uses vacuum as the insulation and arc-extinguishing medium. It is the core equipment in high-voltage transmission and distribution power systems. Online detection of the vacuum level for vacuum switches is an international challenge that has not been effectively addressed for over...

Full description

Saved in:
Bibliographic Details
Published in:Journal of analytical atomic spectrometry 2024-07, Vol.39 (7), p.1824-1837
Main Authors: Ke, W, Luo, H. C, Lv, S. M, Yuan, H, Wang, X. H, Yang, A. J, Chu, J. F, Liu, D. X, Rong, M. Z
Format: Article
Language:English
Subjects:
Accuracy
Effectiveness
Feature extraction
High voltages
Insulation
Laser plasmas
Lasers
Modules
Performance prediction
Plasma
Pneumatics
Prediction models
Spectra
Vacuum switches
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The vacuum switch uses vacuum as the insulation and arc-extinguishing medium. It is the core equipment in high-voltage transmission and distribution power systems. Online detection of the vacuum level for vacuum switches is an international challenge that has not been effectively addressed for over 70 years. In a previous work, our team first proposed an online detection method for the vacuum level for vacuum switches based on laser-induced plasma (LIP), which holds the potential for achieving safe and reliable vacuum level detection. However, the accuracy of vacuum level detection based on a single variable is low and has difficulty in meeting the requirements of high-voltage transmission power systems. Considering the practical engineering application, where inspection personnel only need to know the order of magnitude of the vacuum level to assess the reliability of the vacuum switch, this study proposes a vacuum level prediction model based on the fusion of laser-induced plasma images and spectra. The proposed model comprises two modules: the Image module and Spectra module. The Image module fuses plasma and spectral images to extract features while the Spectra module extracts features from 1D spectral data. Ultimately, features from both images and 1D spectral data are combined for the final air pressure prediction. Experimental results revealed that the fusion of images and spectra improved the macro-precision (MacP) of air pressure prediction, achieving an accuracy of 96.83%. In comparison to utilizing only images or solely 1D spectral data for air pressure prediction, the MacP was increased by approximately 1.41% and 6.83%, respectively. Compared to other baseline models, this model has superior predictive performance. These findings underscore the effectiveness of the proposed air pressure prediction model that combines images and spectral results. This study establishes a foundation for the implementation of the proposed method for the online detection of the vacuum level based on laser-induced plasma in vacuum switches. The feature fusion of laser-induced plasma images and spectra is used for air pressure prediction.
ISSN:0267-9477
1364-5544
DOI:10.1039/d4ja00040d