Dynamic Battery Type Detection Using Neural Networks
Dynamically detecting battery chemistries, including LiFePO4, Ni-MH, and Lead Acid, is explored through extensive simulations. Utilizing discharge curves as training data, three neural network architectures-Single Hidden Layer, Double Hidden Layer, and Radial Basis Transfer Function-are employed for...
Saved in:
Published in | 2023 IEEE 20th International Conference on Smart Communities: Improving Quality of Life using AI, Robotics and IoT (HONET) pp. 1 - 5 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
04.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Dynamically detecting battery chemistries, including LiFePO4, Ni-MH, and Lead Acid, is explored through extensive simulations. Utilizing discharge curves as training data, three neural network architectures-Single Hidden Layer, Double Hidden Layer, and Radial Basis Transfer Function-are employed for pattern recognition across diverse discharge profiles. The objective is to enable the identification of connected battery types and optimize charging control. This research holds significance in real-time Electric Vehicle (EV) charging optimization, offering the capability to discern various battery chemistries. Additionally, in Peer-to-Peer (P2P) energy markets, the dynamic contribution of batteries to the grid requires safe and efficient charging for interoperable systems. The findings presented in this study introduce adaptable systems, fostering innovation in sustainable energy practices. |
---|---|
ISSN: | 1949-4106 |
DOI: | 10.1109/HONET59747.2023.10374630 |