Immediate remaining capacity estimation of heterogeneous second-life lithium-ion batteries <i>via</i> deep generative transfer learning
Shengyu Tao, Ruohan Guo, Jaewoong Lee, Scott Moura, Lluc Canals Casals, Shida Jiang, Junzhe Shi, Stephen J. Harris, Tongda Zhang, C. Y. Chung, Guangmin Zhou, Jinpeng Tian, Xuan Zhang
Abstract
This work proposes a novel deep generative transfer learning algorithm to estimate the relative remaining capacity of second-life batteries using minimal field data, enabling safe and sustainable reuse under data scarce and heterogeneous conditions.
Topics & Concepts
ReuseLithium (medication)Transfer of learningEstimationIonPower (physics)Energy storageEnvironmental scienceComputer scienceArtificial intelligenceChemistryEngineeringPsychologyWaste managementPhysicsSystems engineeringThermodynamicsPsychiatryOrganic chemistryAdvanced Battery Technologies ResearchAdvancements in Battery MaterialsElectric Vehicles and Infrastructure