| Title |
CNN based State-of-Charge Estimation of Lithium-ion Battery using Heat Distribution Image |
| Authors |
김재영(Jaeyeong Kim) ; 권상욱(Sanguk Kwon) ; 박성윤(Seongyun Park) ; 조인호(Inho Cho) ; 이건복(Gunbok Lee) ; 김종훈(Jonghoon Kim) |
| DOI |
https://doi.org/10.5573/ieie.2021.58.10.77 |
| Keywords |
Lithium-ion battery; Convolutional neural network; State-of-charge; Heat distribution image |
| Abstract |
Lithium-ion batteries are currently applied to variety of energy systems, and the importance of the battery management system(BMS) is emerging for stable and efficient battery use. State-of-charge(SOC) is one of the most important battery state information for efficient control of BMS, and various studies have been conducted for accurate SOC estimation. In this paper, we propose an artificial intelligence convolutional neural network(CNN)-based SOC estimation method using thermal imaging techniques, which efficiently represent the thermal characteristics of lithium-ion batteries. The training dataset of the CNN models, which is required to estimate the SOC, is composed of heat distribution images in each SOC interval with the high current discharge test higher than a standard charging current of 0.5C-rate. To evaluate the capability of the proposed SOC estimation method, we use the area under the curve(AUC), which is an indicator of performance evaluation of the receiver operator characteristic curve(ROC curve). |