Journal
2019 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA)
Volume -, Issue -, Pages 1067-1072Publisher
IEEE
DOI: 10.1109/icma.2019.8816512
Keywords
Battery face imaging; voltage classification; convolutional neural network; linear discriminant analysis; wavelet transform
Funding
- China Scholarship Council
Ask authors/readers for more resources
By using a three-dimensional (3D) radio-frequency based sensor, which is called Walabot, and machine learning (ML) algorithm, this paper presents a contactless way to generate lithium-ion battery face images for battery voltage classification. First, Walabot was applied to sampling images, which can reflect inside physic structure of lithium-ion batteries (LIBs). Second, these images were preprocessed by data enhancement or wavelet transform. Finally, these preprocessed images were set as inputs of a convolutional neural network (CNN). After images network training, the CNN can be applied to validating test images in different voltage values. Experiment results of five LIBs illustrate that the proposed contactless battery face imaging method provides a totally new way to conduct voltage classification for LIBs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available