TY - JOUR
T1 - Multiobjective Optimization of Data-Driven Model for Lithium-Ion Battery SOH Estimation with Short-term Feature
AU - Cai, Lei
AU - Meng, Jinhao
AU - Stroe, Daniel-Ioan
AU - Peng, Jichang
AU - Guangzhao, Luo
AU - Teodorescu, Remus
PY - 2020
Y1 - 2020
N2 - As a favorable energy storage component, Lithium-ion (Li-ion) battery has been widely used in the Battery Energy Storage Systems (BESS) and Electric Vehicles (EV). Data driven methods estimate the battery State of Health (SOH) with the features extracted from the measurement. However, excessive features may reduce the estimation accuracy and also increases the human labor in the lab. By proposing an optimization process with Non-dominated Sorting Genetic Algorithm II (NSGA-II), this paper is able to establish a more efficient SOH estimator with Support Vector Regression (SVR) and the short-term features from the current pulse test. NSGA-II optimizes the entire process of establishing a SOH estimator considering both the measurement cost of the feature and the estimation accuracy. A series of non-dominated solutions are obtained by solving the multi-objective optimization problem, which also provides more flexibility to establish the SOH estimator at various conditions. The degradation features in this paper are the knee points at the transfer instants of the voltage in the short-term current pulse test, which is fairly convenient and easy to be obtained in real applications. The proposed method is validated on the measurement from two LiFePO4/C batteries aged with the mission profile providing the Primary Frequency Regulation (PFR) service to the grid.
AB - As a favorable energy storage component, Lithium-ion (Li-ion) battery has been widely used in the Battery Energy Storage Systems (BESS) and Electric Vehicles (EV). Data driven methods estimate the battery State of Health (SOH) with the features extracted from the measurement. However, excessive features may reduce the estimation accuracy and also increases the human labor in the lab. By proposing an optimization process with Non-dominated Sorting Genetic Algorithm II (NSGA-II), this paper is able to establish a more efficient SOH estimator with Support Vector Regression (SVR) and the short-term features from the current pulse test. NSGA-II optimizes the entire process of establishing a SOH estimator considering both the measurement cost of the feature and the estimation accuracy. A series of non-dominated solutions are obtained by solving the multi-objective optimization problem, which also provides more flexibility to establish the SOH estimator at various conditions. The degradation features in this paper are the knee points at the transfer instants of the voltage in the short-term current pulse test, which is fairly convenient and easy to be obtained in real applications. The proposed method is validated on the measurement from two LiFePO4/C batteries aged with the mission profile providing the Primary Frequency Regulation (PFR) service to the grid.
KW - State of health estimation
KW - Multi-objective optimization
KW - Feature selection
KW - Lithium-ion battery
UR - http://www.scopus.com/inward/record.url?scp=85086883350&partnerID=8YFLogxK
U2 - 10.1109/TPEL.2020.2987383
DO - 10.1109/TPEL.2020.2987383
M3 - Journal article
SN - 0885-8993
VL - 35
SP - 11855
EP - 11864
JO - I E E E Transactions on Power Electronics
JF - I E E E Transactions on Power Electronics
IS - 11
M1 - 9069426
ER -