State of health estimation for lithium-ion batteries using recurrent neural networks with gated recurrent unit

Shaoyu Zhang; Chunhui Wu; Wenyuan Xiong

doi:10.3788/IRLA20200339

Journals >Infrared and Laser Engineering >Volume 50 >Issue 2 >Page 20200339 > Article

Infrared and Laser Engineering
Vol. 50, Issue 2, 20200339 (2021)

State of health estimation for lithium-ion batteries using recurrent neural networks with gated recurrent unit

Shaoyu Zhang¹, Chunhui Wu², and Wenyuan Xiong¹

Author Affiliations

¹Center of Experimental Teaching, Guangdong University of Finance, Guangzhou 510091, China

²School of Internet Finance and Information Engineering, Guangdong University of Finance, Guangzhou 510091, China

show less

DOI: 10.3788/IRLA20200339 Cite this Article

Shaoyu Zhang, Chunhui Wu, Wenyuan Xiong. State of health estimation for lithium-ion batteries using recurrent neural networks with gated recurrent unit[J]. Infrared and Laser Engineering, 2021, 50(2): 20200339 Copy Citation Text

show less

Fig. 1. [in Chinese]

Download full size | View in the Article

Fig. 2. [in Chinese]

Download full size | View in the Article

Fig. 3. [in Chinese]

Download full size | View in the Article

Fig. 4. [in Chinese]

Download full size | View in the Article

Fig. 5. [in Chinese]

Download full size | View in the Article

Fig. 6. [in Chinese]

Download full size | View in the Article

Name	NASA-Randomized Battery Usage Data Set	Oxford Battery Degradation Dataset
Manufacturer	LG Chem	Kokam
Form factor	18650	Pouch
Voltage	4.2 V	4.2 V
Capacity	2.1 Ah	0.74 Ah
Q range	2.1→0.80 Ah	0.74→0.43 Ah
Samples	842	519
Battery number	28	8
Cycling	7 groups each with different regime	All cells cycled with same regime

Table 1. [in Chinese]

View in the Article

Battery number	SVR		GPR		GRU-RNN
Battery number	MAE	MAX	MAE	MAX	MAE	MAX
#16	3.92%	9.64%	2.34%	9.13%	2.36%	4.79%
#20	2.53%	5.99%	1.12%	4.47%	2.63%	5.62%
#24	2.16%	17.18%	1.93%	7.03%	1.44%	2.39%
#28	2.46%	3.45%	1.76%	4.93%	0.74%	2.30%
Overall	2.76%	17.64%	2.17%	9.13%	1.40%	5.62%

Table 2. [in Chinese]

View in the Article

Battery number	SVR		GPR		GRU-RNN
Battery number	MAE	MAX	MAE	MAX	MAE	MAX
4#	4.02%	11.35%	2.23%	3.43%	1.10%	1.87%
8#	4.83%	9.73%	2.76%	5.19%	1.32%	1.25%
Overall	4.51%	11.35%	2.49%	5.19%	1.25%	2.34%

Table 3. [in Chinese]

Download Citation

Save the article for my favorites

Paper Information