Dual Separation-based Spatiotemporal Modeling Methodology for Battery Thermal Process Under Nonhomogeneous Boundary Conditions

The monitoring of temperature distribution is critical to the safety performance and cycle life of lithium-ion batteries. This paper introduces a systematic solution for real-time modeling of the battery thermal process under non-homogeneous boundary conditions. The proposed method integrates the non-homogeneity separation and the time-space (T/S) separation. First, the non-homogeneity separation is designed to homogenize the boundary conditions. Then, the spatio-temporal dynamics can be decomposed by the T/S separation. With the T/S separation, a set of spatial basis functions are designed to deal with the spatial complexity, and then a corresponding temporal model is constructed to capture the temporal non-linearity. According to the Rademacher complexity, the generalization bound of the developed model is deduced, thereby ensuring the modeling performance. Experimental studies demonstrate the validity of the proposed modeling method.