Rapid measurement method for lithium‐ion battery state of health estimation based on least squares support vector regression

2020 ◽  
Author(s):  
Bin Xiao ◽  
Bing Xiao ◽  
Luoshi Liu
Keyword(s):  
Least Squares ◽  
Support Vector Regression ◽  
Lithium Ion Battery ◽  
Measurement Method ◽  
Lithium Ion ◽  
Support Vector ◽  
State Of Health ◽  
Rapid Measurement

State-of-health estimation for the lithium-ion battery based on support vector regression

2018 ◽  
Vol 227 ◽  
pp. 273-283 ◽  
Author(s):  
Duo Yang ◽  
Yujie Wang ◽  
Rui Pan ◽  
Ruiyang Chen ◽  
Zonghai Chen
Keyword(s):  
Support Vector Regression ◽  
Lithium Ion Battery ◽  
Lithium Ion ◽  
Support Vector ◽  
State Of Health

scholarly journals A New Lithium-Ion Battery SOH Estimation Method Based on an Indirect Enhanced Health Indicator and Support Vector Regression in PHMs

Energies ◽  
2020 ◽  
Vol 13 (4) ◽  
pp. 830 ◽  
Author(s):  
Zhengyu Liu ◽  
Jingjie Zhao ◽  
Hao Wang ◽  
Chao Yang
Keyword(s):  
Support Vector Regression ◽  
Lithium Ion Battery ◽  
Estimation Method ◽  
Lithium Ion ◽  
Health Indicators ◽  
Support Vector ◽  
Health Indicator ◽  
De Algorithm ◽  
Key Factor ◽  
Charging And Discharging Processes

An accurate lithium-ion battery state of health (SOH) estimate is a key factor in guaranteeing the reliability of electronic equipment. This paper proposes a new method that is based on an indirect enhanced health indicator (HI) and uses support vector regression (SVR) to estimate SOH values. First, three original features that can describe the dynamic changes of the battery charging and discharging processes are extracted. Considering the coupling relationship between pairs of the original health indicators, we use the differential evolution (DE) algorithm to optimize their corresponding feature parameters and combine them to form an enhanced health indicator. Second, this paper modifies the kernel function of the SVR model to describe the trend of SOH as the number of cycles increases, with simultaneous hyperparameters optimization via DE algorithm. Third, the proposed model and other published methods are compared in terms of accuracy on the same NASA datasets. We also evaluated the generalization performance of the model in dynamic discharging experiments. The simulation results demonstrate that the proposed method can provide more accurate SOH estimation values.

scholarly journals A Novel State of Charge Approach of Lithium Ion Battery Using Least Squares Support Vector Machine

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 195398-195410
Author(s):  
Jiabo Li ◽  
Min Ye ◽  
Wei Meng ◽  
Xinxin Xu ◽  
Shengjie Jiao
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Lithium Ion Battery ◽  
Lithium Ion ◽  
State Of Charge ◽  
Support Vector
Sign in / Sign up

Export Citation Format

Share Document