Using Siamese Neural Networks on Threshold Maps of Infrared Images to Detect Equipment Faults

Condition monitoring of electrical equipment is used to detect faults in order to make repairs before an expensive or even catastrophic failure. For example, Infrared Thermography (IRT) cameras are able to detect hot spots indicative of such problems. Machine learning is a good tool to classify IRT...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE Eighth International Conference on Big Data Computing Service and Applications (BigDataService) pp. 167 - 172
Main Authors Gitzel, Ralf, Kaul, Holger, Dix, Marcel
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2022
Subjects
artificial intelligence
Cameras
Condition monitoring
electrical equipment
infrared thermography
Machine learning
Maintenance engineering
Neural networks
Siamese neural networks
Switchgear
thresholding
Training data
Online AccessGet full text

Cover

More Information
Summary:Condition monitoring of electrical equipment is used to detect faults in order to make repairs before an expensive or even catastrophic failure. For example, Infrared Thermography (IRT) cameras are able to detect hot spots indicative of such problems. Machine learning is a good tool to classify IRT images into healthy (no hot spot) and faulty (hot spot). In this paper, we explore the use of Siamese neural networks to compare black and white thresholded images derived from the original infrared images to detect hot spots. The network is trained on synthetic data. It is tested on experimental data derived from a low voltage switchgear panel. The algorithm shows good results on the experimental data, being able to detect all faults and not giving a false alarm on the healthy experiment.
DOI:10.1109/BigDataService55688.2022.00034