A framework of lithium-ion battery health monitoring model is established. A new grey prediction model is proposed. The proposed model is validated on a publicly available dataset. Accurate assessment of the state of health of lithium-ion batteries using relevant factors is crucial for the maintenance of lithium-ion batteries in electric vehicles.
(1) This paper presents a novel approach for multivariate prediction of lithium-ion battery health based on a consideration of the impact of other indicators. By analysing the degree of correlation among various indicators, the main factor that affects the degradation of lithium-ion batteries can be identified.
The combined use of classical modelling and machine learning is also often used to assess the health status of lithium-ion batteries. For example, Wei et al. used particle filtering and support vector regression machine jointly to diagnose the health status of lithium-ion batteries .
Monitoring the health status of lithium-ion batteries is a valuable research problem, and a stable monitoring model can provide accurate results that are crucial for the subsequent utilization of these batteries. The authors of this study propose a monitoring model that has been validated using public datasets.
While it is possible to divide the research models for lithium-ion batteries into these two categories, the two types of models are not cut and dried. The combined use of classical modelling and machine learning is also often used to assess the health status of lithium-ion batteries.
The increasing adoption of batteries in a variety of applications has highlighted the necessity of accurate parameter identification and effective modeling, especially for lithium-ion batteries, which are preferred due to their high power and energy densities.