Statistical analysis of infrared thermogram for CNN-based electrical equipment identification methods
- 24 November 2021
- journal article
- research article
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
Abstract
It is essential to develop infrared (IR) thermogram identification technologies to establish automatic diagnosis systems in power substations. The convolutional neural network (CNN) based methods show the highest accuracy in this field. The IR thermograms of electrical equipment are very different from general digital images, which means the present methods need further improvements. For data-driven CNN methods, it is necessary to study the characteristics of the IR data. This paper collected 11817 thermograms from substations and structured the dataset according to equipment types. The statistical features of mean, variance, skewness, kurtosis and contrast are analyzed and compared with other five image datasets. Several tricks are revealed from the analysis and tested on CNN models. Firstly, greycaling the Iron pseudo-color images extracts the temperature information and makes it possible to design models with fewer channels. The test shows it could reduce over 35% computational costs. Secondly, the sparse information of color and edges of thermograms makes it necessary to keep the original aspect ratio. The image preprocessing method of cropping shows better performance than padding and rescaling. Thirdly, the 0–1 normalization can boost the training process for about 100 epochs, which is related to the particular background of thermograms.Keywords
Funding Information
- STATE GRID of China Corporation Headquarter’s Science and Technology Project (5200-201915256A)
This publication has 17 references indexed in Scilit:
- Temperature Monitoring for Electrical Substations Using Infrared Thermography: Architecture for Industrial Internet of ThingsIEEE Transactions on Industrial Informatics, 2018
- A Deep Learning Approach for Oriented Electrical Equipment Detection in Thermal ImagesIEEE Access, 2018
- On-rail solution for autonomous inspections in electrical substationsInfrared Physics & Technology, 2018
- Failure detection in industrial electric motors through the use of infrared-based isothermal representation2017
- Aggregating Deep Convolutional Feature Maps for Insulator Detection in Infrared ImagesIEEE Access, 2017
- Analyzing the influence of contrast in large-scale recognition of natural imagesIntegrated Computer-Aided Engineering, 2016
- Multi-modal RGB–Depth–Thermal Human Body SegmentationInternational Journal of Computer Vision, 2016
- A novel intelligent fault diagnosis method for electrical equipment using infrared thermographyInfrared Physics & Technology, 2015
- Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermographyInfrared Physics & Technology, 2013
- Perception of shape from shadingNature, 1988