Intelligent modeling for thermal management of cylindrical lithium ion batteries

Effective thermal management is crucial to the optimal operation of lithium ion batteries and its health management. Since only the surface temperature of battery can be measured, an accurate mathematical model describing the thermal process is needed to estimate the temperature distribution of batteries. Furthermore, the thermal behaviors of batteries are governed by complex chemical process whose parameters will degrade over time and different environment. Advanced identification algorithms should be developed for the model to be able to be updated in real time application. In this paper, a neural network based model is developed for thermal management of cylindrical lithium ion batteries. The relative identification algorithms are introduced. The developed model is simple enough for online thermal management, and numerical simulations demonstrate the effectiveness of the proposed model.