Lithium battery pack health state online prediction method based on multiphysics field simulation and neural network

Abstract

The invention relates to a lithium battery pack health state online estimation method based on multiphysics field simulation and a neural network. The method comprises the following steps: constructing a lithium battery pack multiphysics field simulation model, and carrying out a lithium battery pack multiphysics field simulation test and model verification and analysis through working load analysis; on the basis of a simulation test analysis result and in combination with experimental data, constructing and training a neural network model oriented to lithium battery pack health state prediction, including a neural network model oriented to multiphysics field simulation and health state degradation; and in the use stage of the lithium battery pack, collecting and processing local operation data, and carrying out global physical characterization analysis and lithium battery monomer degradation analysis by applying the neural network model so as to predict the health state of the lithium battery pack. According to the method, the advantages of a model-based method and a data-based method are fused, and rapid online lithium battery pack health state prediction can be realized.

Description

[0001] Technical field [0002] The present invention relates to the field of health status prediction, especially A lithium battery based on multiphysics simulation and neural network On-line prediction method of pool health status . Background technique [0003] Lithium batteries have the characteristics of good safety performance and long cycle life, and have been widely used in power systems such as aviation, aerospace, and automobiles. The lithium battery pack is composed of multiple lithium battery cells connected in series and parallel. It is a highly nonlinear system including complex physical and chemical changes. Its degradation mechanism is complex and affected by the coupling effects of multiple physical fields such as heat, electricity, and flow. The state of health is often used to describe the current performance state of the lithium battery pack relative to the capacity of the new battery pack, and it is quantitatively described in the form of a percentage. ...

AI Technical Summary

Problems solved by technology

The models involved in lithium battery packs mainly include electrochemical models, equivalent circuit models, thermal models, fluid dynamics models, etc. Due to the complexity of calculating and solving these models, it is difficult to directly apply them to online real-time health state estimation of lithium battery packs

Images