Data-driven state of charge estimation of lithium-ion batteries: Algorithms, implementation factors, limitations and future trends. (20th December 2020)

• Record Type: Journal Article
• Authors: Hossain Lipu, M.S.; Hannan, M.A.; Hussain, Aini; Ayob, Afida; Saad, Mohamad H.M.; Karim, Tahia F.; How, Dickson N.T.
• Is Part Of: Journal of cleaner production. Volume 277(2020)
• Publication Date: 2020-12-20
• Subjects: State of charge -- Lithium-ion battery -- Electric vehicle -- Data-driven methods -- Training and testing -- Optimization; Factory and trade waste -- Management -- Periodicals; Manufactures -- Environmental aspects -- Periodicals; Déchets industriels -- Gestion -- Périodiques; Usines -- Aspect de l'environnement -- Périodiques; 628.5
• DOI: 10.1016/j.jclepro.2020.124110
• Languages: English
• ISSNs: 0959-6526

Abstract

Abstract: Global carbon emissions caused by fossil fuels and diesel-based vehicles have urged the necessity to move toward the development of electric vehicles and related battery storage systems. Lithium-ion batteries are the ideal candidate for electric vehicle due to their superior performance with regard to high energy density and long lifespan. The state of charge of lithium-ion batteries is one of the crucial evaluation indicators of the battery management system that confirms the extended battery life, better charging-discharging profiles, and safe driving of electric vehicles. However, the accuracy of the state of charge is influenced by several issues such as battery aging cycles, noise effects, and temperature impacts. Therefore, this review presents a detailed classification of the recent data-driven state of charge estimation highlighting algorithm, input features, configuration, execution process, strength, weakness and estimation error. This review critically investigates the various key implementation factors of the data-driven algorithms in terms of data preprocessing, hyperparameter adjustment, activation function, evaluation criteria, computational cost and robustness validation under uncertainties. In addition, the review explores the deficiencies of existing data-driven state of charge estimation algorithms to identify the gaps for future research. Finally, the review provides some effective future directions that would be beneficial to the automobile researchers and industrialists to design an accurate and robust state of charge estimation technique toward future sustainable electric vehicle applications. Highlights of the Manuscript: Data-driven algorithms can deliver accurate and robust SOC estimation results. A comprehensive review of data-driven SOC estimation algorithms is outlined. The various key implementation factors are investigated in detail. The key challenges to identify the gaps for future research are explored. Effective future directions are provided toward SOC performance enhancement.