Accurately estimating the state of health (SOH) and predicting the remaining useful life (RUL) of retired lithium-ion power batteries is of great significance for ensuring their operational safety and promoting secondary utilization. Traditional SOH detection methods are inefficient and lack effective ways for evaluating the value of retired batteries. Data-driven artificial intelligence methods offer unique advantages in this field. From a practical application perspective

this paper reviews the latest research progresses in SOH estimation and RUL prediction. First

the methods for estimating SOH and predicting RUL of lithium-ion batteries are introduced

with a focus on data-driven approaches. Then

the advantages and disadvantages of different methods are compared. Finally

key issues in current research are presented

potential solutions are proposed

and future development directions are discussed.