Performance benchmarks for open source porous electrode theory models.

The electrochemical response characteristics of existing and emerging porous electrode theory (PET) models was benchmarked to establish a common basis to assess their physical reaches, limitations, and accuracy. Three open source PET models: dualfoil, MPET, and LIONSIMBA were compared to simulate the discharge of a LiMn2O4-graphite cell against experimental data. For C-rates below 2C, the simulated discharge voltage curves matched the experimental data within 4% deviation for dualfoil, MPET, and LIONSIMBA, while for C-rates above 3C, dualfoil and MPET show smaller deviations, within 5%, against experiments. The electrochemical profiles of all three codes exhibit significant qualitative differences, despite showing the same macroscopic voltage response, leading the user to different conclusions regarding the battery performance and possible degradation mechanisms of the analyzed system.

Artificial intelligence inferred microstructural properties from voltage-capacity curves.

The quantification of microstructural properties to optimize battery design and performance, to maintain product quality, or to track the degradation of LIBs remains expensive and slow when performed through currently used characterization approaches. In this paper, a convolution neural network-based deep learning approach (CNN) is reported to infer electrode microstructural properties from the inexpensive, easy to measure cell voltage versus capacity data. The developed framework combines two CNN models to balance the bias and variance of the overall predictions. As an example application, the method was demonstrated against porous electrode theory-generated voltage versus capacity plots. For the graphite|LiMn[Formula: see text]O[Formula: see text] chemistry, each voltage curve was parameterized as a function of the cathode microstructure tortuosity and area density, delivering CNN predictions of Bruggeman's exponent and shape factor with 0.97 [Formula: see text] score within 2 s each, enabling to distinguish between different types of particle morphologies, anisotropies, and particle alignments. The developed neural network model can readily accelerate the processing-properties-performance and degradation characteristics of the existing and emerging LIB chemistries.