Machine Learning Approaches for Designing Mesoscale Structure of Li-Ion Battery Electrodes

Abstract

We have proposed a data-driven approach for designing the mesoscale porous structures of Li-ion battery electrodes, using three-dimensional virtual structures and machine learning techniques. Over 2000 artificial 3D structures, assuming a positive electrode composed of randomly packed spheres as the active material particles, are generated, and the charge/discharge specific resistance has been evaluated using a simplified physico-chemical model. The specific resistance from Li diffusion in the active material particles (diffusion resistance), the transfer specific resistance of Li+ in the electrolyte (electrolyte resistance), and the reaction resistance on the interface between the active material and electrolyte are simulated, based on the mass balance of Li, Ohm’s law, and the linearized Butler–Volmer equation, respectively. Using these simulation results, regression models, using an artificial neural network (ANN), have been created in order to predict the charge/discharge specific resistance from porous structure features. In this study, porosity, active material particle size and volume fraction, pressure in the compaction process, electrolyte conductivity, and binder/additives volume fraction are adopted, as features associated with controllable process parameters for manufacturing the battery electrode. As a result, the predicted electrode specific resistance by the ANN regression model is in good agreement with the simulated values. Furthermore, sensitivity analyses and an optimization of the process parameters have been carried out. Although the proposed approach is based only on the simulation results, it could serve as a reference for the determination of process parameters in battery electrode manufacturing.

Predicting the state of charge and health of batteries using data-driven machine learning

“…The combined database and machine learning approach have been applied to design and predict the material properties of electrodes such as voltage, crystallinity and chemical stability, from atomic scale to mesoscale 83,[94][95][96][97][98][99] . In addition, such an approach has been applied to design new liquid electrolytes and additives [100][101][102][103][104][105] , and solid-state electrolytes with fast Li-ion transport [106][107][108] and mechanical 82 properties.…”

Quasi-3D Modeling of Li-ion Batteries Based on Single 2D Image

“…Using these radii, we estimated the 3D active material radius R3D by a Bayesian inference as described in Eq. (16). Fig.…”

“…Recently, many studies of charge/discharge simulations based on the mesoscale three-dimensional (3D) structure of porous electrodes have been reported [11][12][13][14][15][16][17][18][19][20][21][22]. In these cases, porous electrodes were modeled by random packed spheres/hemispheres [11][12][13][14][15] or actual structures based on Scanning Electron Microscopy equipped with a Focused Ion Beam (FIB-SEM) results [17][18][19][20][21][22] to evaluate the 3D distribution of Li in the active material particles, Li-ion concentration in the electrolyte, and the stress distribution and temperature field of electrodes.…”

Towards the digitalisation of porous energy materials: evolution of digital approaches for microstructural design

“…For example, DEM can capture aspects of the manufacturing process and particle-particle interactions that are relevant in determining the characteristics of the microstructure. Takagishi et al 248 and Lombardo et al 249 employed a mesoscopic coarse grained molecular dynamics model to digitalise the manufacturing process of Li-ion battery electrodes which involves multi-scale materials such as slurry, consisting of active materials, carbon additives, binders and solvents. Consequently, data-driven models can be further introduced to predict the properties of microstructures generated in a manufacturing process under specific conditions.…”