Open AccessHyper-spectral Imaging Technology Based on Linear Gradient Bandpass Filter for Electricity Power Equipment Status Monitoring Application
Author(s) -
Cheng Li,
Ziwen Shang,
Minzhen Wang,
Liu Li,
Guangxin Zhang,
Jian Zhang,
Zhao Liyin,
Xiao Zhang,
Hongxia Ni,
Daji Qiao
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2011/1/012091
Subject(s) - computer science , hyperspectral imaging , miniaturization , power (physics) , electric power transmission , filter (signal processing) , electronic engineering , artificial intelligence , computer vision , electrical engineering , engineering , physics , quantum mechanics
Hyperspectral imaging technology has been applied to the status monitoring of power transmission line and equipment as its continuous and narrow-band induction characteristics, which provides a solution for the operation monitoring of lossless large-area power equipment. However, the optical and electronic equipment is complex, and the related products are large and expensive on the market. This paper describes a preparation method of a linear gradient filter that is cost performance and miniaturization, which can be used to realize the prototype hyper-spectral imaging camera. The high precision preparation process and principle make the camera show good spectral performance, which can scan with precision step length of 2nm between 400nm and 1000nm. The feature extraction and classification algorithm can be used to determine the health conditions of power equipment, such as partial discharge, with an accuracy of about 77%. The equipment collocation algorithm can also be used to identify defects in power equipment, which has been proved to be able to distinguish between aging insulators, icing of conductors and heating of wire clips. This method are promising for an entry-level, low-cost hyper-spectral imaging solution for power detection applications.