Novel Feature Selection Strategy for Cyclic Loss Prediction of Lithium-ion Electric Vehicle Battery
Authors:
- 16 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Battery cyclic loss is a key parameter to assess lithium-ion battery degradation in electric vehicles (EVs), while machine learning (ML) methods can be used in evaluating and predicting the degradation trend of battery health due to cyclic loss. The accuracy of ML methods is influenced by the input parameter selection of the model. This paper develops a feature selection strategy based on the utilization of a data pre-processing method, which extracts useful model input parameters from the battery data. To show the advantages of the method, eight widely used ML algorithms are applied to a case study and compared for battery cyclic loss prediction. The results show that the developed feature selection method has improved the prediction accuracy by at least 9%, in the case of LASSO regression The results also depict that the random forest (RF) regression, Gaussian Process Regression (GPR), and XGBoost methods, when applied in combination with the developed feature selection method, show an improvement of 44%, 48% and 52% in the prediction accuracy, respectively.Keywords
Funding Information
- Lahore University of Management Sciences
- Center for Advanced Life Cycle Engineering
- University of Maryland
This publication has 9 references indexed in Scilit:
- Battery monitoring system using machine learningJournal of Energy Storage, 2021
- A Flexible State-of-Health Prediction Scheme for Lithium-Ion Battery Packs With Long Short-Term Memory Network and Transfer LearningIEEE Transactions on Transportation Electrification, 2021
- Predictive Battery Health Management With Transfer Learning and Online Model CorrectionIEEE Transactions on Vehicular Technology, 2021
- Economic model predictive control of Li‐ion battery cyclic aging via online rainflow‐analysisEnergy Storage, 2021
- A trajectory-based energy consumption estimation method considering battery degradation for an urban electric vehicle networkTransportation Research Part D: Transport and Environment, 2019
- Predictive modeling of battery degradation and greenhouse gas emissions from U.S. state-level electric vehicle operationNature Communications, 2018
- Degradation diagnosis of lithium-ion batteries with a LiNi0.5Co0.2Mn0.3O2 and LiMn2O4 blended cathode using dV/dQ curve analysisJournal of Power Sources, 2018
- Systematic aging of commercial LiFePO 4 |Graphite cylindrical cells including a theory explaining rise of capacity during agingJournal of Power Sources, 2017
- A review on lithium-ion battery ageing mechanisms and estimations for automotive applicationsJournal of Power Sources, 2013