A nonlinear spatiotemporal modeling method combined with t-distributed stochastic neighbor embedding and broad learning system for the lithium-ion battery thermal process.

Time/space separation-based methods have been extensively employed in modeling the lithium-ion battery (LIB) thermal process. However, these methods often adopt linear separation and reconstruction models that heavily depend on spatial basis functions to separate and reconstruct the spatiotemporal domain of the thermal process, which fails to handle highly nonlinear thermal dynamics. To cope with this problem, a nonlinear spatiotemporal modeling method combined with t-distributed stochastic neighbor embedding (t-SNE) and broad learning system (BLS) is presented in this paper. First, a parametric t-SNE is designed to transform the spatiotemporal domain of the LIB thermal process into the time domain. Compared with traditional linear separation models, the proposed t-SNE can better preserve the nonlinear information of spatiotemporal temperature data. Then, BLS is utilized for dynamic temporal model construction. Finally, BLS is also employed to establish a nonlinear reconstruction model for the spatiotemporal domain. To improve the modeling accuracy and reduce the structural complexity of these two BLS-based models, a two-stage selection strategy of activation functions is designed. Since both t-SNE and BLS can handle nonlinear complexity, the proposed method provides significant benefits for nonlinear modeling. The efficiency of the proposed method is demonstrated by experimental findings on a 32 Ah ternary LIB. • A novel temperature distribution estimation method for batteries is proposed. • t-SNE is introduced to realize spatiotemporal decoupling. • Broad learning system is designed to enhance the modeling performance. • Experimental results on a battery confirm the effectiveness of this model. [ABSTRACT FROM AUTHOR]