State‐of‐Charge Estimation of Lithium Battery Based on Fiber Grating Sensing and Deep Learning

Fig. 8. FBG sensing results. (a) Wavelength drift in second experiment; (b) spectrum position in second experiment; (c) wavelength drift in third experiment; (d) spectrum position in third experiment

Download full size

Fig. 9. Predicted results of SOC and absolute errors. (a) Predicted results of SOC in second experiment; (b) absolute errors in second experiment; (c) predicted results of SOC in third experiment; (d) absolute errors in third experiment

Download full size

Table 1. Performance parameters of lithium-ion battery

View table

Table 1. Performance parameters of lithium-ion battery

Parameter	Value
Rated capacity	6000 mA·h
Standard voltage	3.2 V
Mass	500 g
	Thickness of 5 mm，
Size	width of 162 mm， and
	height of 227 mm（without taps）
Charge cut-off voltage	3.6 V
Discharge cut-off voltage	3 V
Internal resistance	≤0.6 $m Ω$

Table 2. Characteristic wavelengths of FBG sensors
View table
Table 2. Characteristic wavelengths of FBG sensors
FBG Reference FBG Sensing FBG
Wavelength/nm 1539.70 1550.00

Table 3. Estimated errors of lithium-battery SOC
View table
Table 3. Estimated errors of lithium-battery SOC
Model Experiment No. RMSE /% MAE /% R²
GRU 1 3.512 3.036 0.941
2 3.639 2.919 0.937
3 3.662 3.055 0.936
CNN-GRU 1 2.911 2.481 0.959
2 2.974 2.563 0.957
3 3.197 2.507 0.951

Tools

Get Citation

Copy Citation Text

Wenjuan Sheng, Junfeng Pan, G D Peng. State‐of‐Charge Estimation of Lithium Battery Based on Fiber Grating Sensing and Deep Learning[J]. Chinese Journal of Lasers, 2025, 52(6): 0610001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites