Analysis of Tasks of Forming Thermal Imaging of Electrical Devices

Author(s):  
Elena A. Punt ◽  
Sergey P. Khalyutin ◽  
Albert O. Davidov
2021 ◽  
Vol 278 ◽  
pp. 01029
Author(s):  
Marta Stempniak

Underground fires are phenomena that pose a possibly fatal threat to human life, and they are particulary dangerous in the environment of underground workings where the amount of space and number possible escape routes are limited. Therefore, it is important to carefully control changes in temperature and the condition of machinery and equipment used in mine in order to avoid critical situations. The most common cause of fires are defects in mechanical and electrical devices, in order to conduct an analysis of their condition thermal imaging is perfectly suitable. In this article approximed a problem of underground fires, thermal imaging diagnostic method, temperature measurements taken in the KWK ROW Ruch Chwałowice in Rybnik, made an analysis of publicly available data from the KGHM mines and methods of combating the factors leading to the fire emergency been proposed.


Author(s):  
Christian Herglotz ◽  
Simon Grosche ◽  
Akarsh Bharadwaj ◽  
Andre Kaup

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2853
Author(s):  
Adam Glowacz

The paper presents an analysis and classification method to evaluate the working condition of angle grinders by means of infrared (IR) thermography and IR image processing. An innovative method called BCAoMID-F (Binarized Common Areas of Maximum Image Differences—Fusion) is proposed in this paper. This method is used to extract features of thermal images of three angle grinders. The computed features are 1-element or 256-element vectors. Feature vectors are the sum of pixels of matrix V or PCA of matrix V or histogram of matrix V. Three different cases of thermal images were considered: healthy angle grinder, angle grinder with 1 blocked air inlet, angle grinder with 2 blocked air inlets. The classification of feature vectors was carried out using two classifiers: Support Vector Machine and Nearest Neighbor. Total recognition efficiency for 3 classes (TRAG) was in the range of 98.5–100%. The presented technique is efficient for fault diagnosis of electrical devices and electric power tools.


2009 ◽  
Vol 5 (1) ◽  
pp. 31-35
Author(s):  
F.F. Sizov ◽  
◽  
V.V. Zabudsky ◽  
A.G. Golenkov ◽  
S.L. Kravchenko ◽  
...  

2013 ◽  
Vol 133 (7) ◽  
pp. 274-279
Author(s):  
Tomoyuki Takahata ◽  
Kiyoshi Matsumoto ◽  
Isao Shimoyama

Science Scope ◽  
2016 ◽  
Vol 039 (07) ◽  
Author(s):  
Jeffrey Nordine ◽  
Susanne Wessnigk

Sign in / Sign up

Export Citation Format

Share Document