State-of-health estimation using a neural network trained on vehicle data
Source abstract
Abstract
Abstract The validation of battery aging models in automotive applications requires reliable aging data to compare the accuracy of each proposed model. Using a sample of 704 vehicles aged up to eight years under diverse nominal conditions two aging estimation models are proposed. By analyzing relevant automobile battery data a more relevant fit of a semi-empirical holistic model is provided with an Arrhenius temperature dependence and pseudo-Tafel voltage dependence. As a comparison, a neural network capturing the aging behavior using the most correlated variables available in the data-set was also developed. Over 110,000 measurements from seven relevant indicators are available as aging predictors, as well as, highly-accurate capacity measurements which is used as the ground truth capacity targets to train and validate the proposed models. Against these points the Semi-Empirical and Neural Network models achieved a root mean squared error of 3.4%-SOH and 3.0%-SOH, respectively.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Reliability and Maintenance Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (31)
Show source-provided references
1. 2020
2. Remaining useful life estimation- a review on the statistical data driven approaches10.1016/j.ejor.2010.11.018 ↗
3. Critical review of the methods for monitoring of lithium-ion batteries in electric and hybrid vehicles10.1016/j.jpowsour.2014.02.064 ↗
4. Critical review of state of health estimation methods of li-ion batteries for real applications10.1016/j.rser.2015.11.042 ↗
5. Machine learning applied to electrified vehicle battery state of charge and state of health estimation: State-of-the-art10.1109/ACCESS.2020.2980961 ↗
6. Data-driven health estimation and lifetime predictino of lithium-ion batteries: A review
7. Kollmeyer · 2018
8. Data-driven predictino of battery cycle life before capactiy degradation10.1038/s41560-019-0356-8 ↗
9. Realistic lifetime prediction approach for li-ion batteries10.1016/j.apenergy.2015.10.115 ↗
10. Comprehensive modeling of temperature-deendent degradation mechanisms in lithium iron phosphate batteries10.1149/2.1181714jes ↗
11. A holistic aging medel for li(nimnco)o2 based 18650 lithium-ion batteries
12. Gaussian process regression for forcasting battery state of health10.1016/j.jpowsour.2017.05.004 ↗
13. Investigation of path dependence in commercial lithium-ion cells chosen for plug-in hybrid vehicle duty cycle protocols10.1016/j.jpowsour.2010.05.058 ↗
14. Path dependence of lithium ion cells aging under storage conditions10.1016/j.jpowsour.2016.03.043 ↗
15. Calendar ageing analysis of a lifepo4/graphite cell with dynamic model validations: Towards realistic lifetime predictions10.1016/j.jpowsour.2014.08.051 ↗
16. Analysis and modeling of calendar aging of a commercial lifepo4/graphite cell
17. Degradation of lithium ion batteries under complex conditions of use10.1524/zpch.2012.0170 ↗
18. Discrimination of degradation process in lithium-ion cells based on the sensitivity of aging indicators towards capactiy loss10.1016/j.jpowsour.2015.02.130 ↗
19. Bruce · 2017
20. Gaussian process regression for forcasting battery state of health10.1016/j.jpowsour.2017.05.004 ↗
21. Some methods for classification and analysis of multivariate observations
22. K-means++: The advantages of careful seeding
23. Burkov · 2019
24. An analysis of variance test for normality10.1093/biomet/52.3-4.591 ↗
25. Simulation and measurement of local potentials of modified commerical cylindrical cells: Ii: Multi-dimensional modeling and validation10.1149/2.0431514jes ↗
26. Quantitative validation of calendar aging models for lithium-ion batteries10.1016/j.jpowsour.2018.08.019 ↗
27. Python Software Foundation · 2020
28. Chollet · 2020
29. Chollet · 2018
30. Achen · 1982
31. Rawlings · 1989