The online estimation of battery state-of-health is an ever significant issue for the intelligent energy management of the autonomous electric vehicles. Machine-learning based approaches are promising for online state-of-health estimation. This paper proposes a machine-learning based algorithm for the online state-of-health estimation of Li-ion battery. A predictive diagnosis model used in the algorithm is established based on support vector machine (SVM). The support vectors, which reflects the intrinsic characteristics of the Li-ion battery, are determined from the charging data of fresh cells. Furthermore, the coefficients of the SVMs for cells at different state-of-health are identified once the support vectors are determined. The algorithm functions by comparing partial charging curves with the stored SVMs. Similarity factor is defined after comparison to quantify the state-of-health of the data under evaluation. The operation of the algorithm only requires partial charging curves, e.g. 15min charging curves, making fast on-board diagnosis of battery state-of-health into reality. The partial charging curves can be intercepted from a wide range of voltage section, thereby relieving the pain that there is little chance that the driver charges the battery pack from a predefined state-of-charge. Train, validation, and test are conducted for two commercial Li-ion batteries with Li(NiCoMn)1/3O2 cathode and graphite anode, indicating that the algorithm can estimate the battery state-of-health with less than 2% error for 80% of all the cases, and less than 3% error for 95% of all the cases.

Lithium plating leads to severe capacity fading and possible safety problems in lithium-ion batteries. Thus, non-destructive detection methods for lithium plating are critical for safe and reliable operation of lithium-ion batteries. In this paper, an electrochemical model incorporated with lithium plating and stripping reactions is established to investigate the lithium plating-stripping process at low temperature. The model is validated at different current rates and temperatures and can successfully predict the characteristic voltage plateau during the rest period after low temperature charging. Modeling analysis helps to develop detection method for lithium plating via differential analysis on the voltage plateau. Distinct local minima can be found in the differential voltage curves of the batteries with plated lithium. The time when the local minima occurs in the differential voltage curves exhibits a linear relationship with the amount of reversible lithium, and thus can be applied as a quantitative indicator for detection of lithium plating. The detection of lithium plating based on differential voltage analysis is further extended to the discharge voltage profiles of the batteries after low temperature charging, considering the effects of rest time.