Park, Cheolhwi Kim, Taehun Sung, Yung-Eun Ryu, Kanghyun Park, Jungjin 2024-10-10T07:30:16Z 2024-10-10T07:30:16Z 2024-10-10 2026-01 0256-1115 https://pubs.kist.re.kr/handle/201004/150774 Electrochemical degradation diagnoses for evaluating the state of health (SOH) in lithium-ion batteries (LIBs) have been extensively utilized for real-time assessments in electric vehicles (EVs) and for determining the reusability of spent batteries. However, the criteria for the accuracy of these diagnostic methods have not yet been established, highlighting the need to develop methods for validating or cross-checking ones. This review encompasses cutting-edge and innovative diagnostic approaches that incorporate machine learning (ML)-applied analyses to expedite big-data-based electrochemical analyses and enhance their accuracy. Moreover, it introduces emerging non-electrochemical analysis methods, particularly imaging-based degradation diagnosis, which can provide the atomic, particle and electrode level examinations, for assessing the SOH in LIBs. Lastly, this paper provides a comprehensive perspective on the future of rechargeable battery diagnostic fields through the integrated concepts of electrochemical and imaging diagnostics in conjunction with data-driven informatics analyses. English 한국화학공학회 Comprehensive Review of Data-Driven Degradation Diagnosis of Lithium-Ion Batteries through Electrochemical and Multi-scale Imaging Analyses Article 10.1007/s11814-024-00277-0 1 Korean Journal of Chemical Engineering, v.43, no.1, pp.1 - 18 Korean Journal of Chemical Engineering 43 1 1 18 N scie scopus kci ART003291203 001321574500002 2-s2.0-85205316465 Chemistry, Multidisciplinary Engineering, Chemical Chemistry Engineering Review OF-HEALTH ESTIMATION POLYMER BATTERIES THERMAL RUNAWAY STATE GAUSSIAN PROCESS REGRESSION SUPPORT VECTOR MACHINE IMPEDANCE CAPACITY PERFORMANCE MODEL Lithium-ion batteries Degradations Electrochemical diagnoses Imaging diagnoses Data informatics