Machine learning for optimal electrode wettability in lithium ion batteries

• DOI: 10.1016/j.powera.2023.100114
• Publication Date: 2023-03-24T11:01:46Z
• Authors: Amina El Malki; Mark Asch; Oier Arcelus; Abbos Shodiev; Jia Yu; Alejandro A. Franco
• Keywords: [CHIM.MATE] Chemical Sciences/Material chemistry; Industrial electrochemistry; Electrolyte wettability; Machine learning; Lattice Boltzmann method; [CHIM.MATE]Chemical Sciences/Material chemistry; Electric apparatus and materials. Electric circuits. Electric networks; TK452-454.4; 7. Clean energy; 3. Good health; 620; Lithium ion battery; TP250-261

Electrode wetting is a critical step in the Lithium-Ion Battery manufacturing process. The injection of electrolyte electrodes' porosity requires application pressure-vacuum pumping strategies without warranty that full will be fully occupied with at end this process step. electrode wettability strongly depends on contact angle between and electrode, microstructure characterized by its porosity, pore network tortuosity factor, viscosity density. Computational fluid dynamics approaches such as Lattice Boltzmann Method can provide relevant information filling process, yet these come significant computational cost. use machine learning techniques surrogate models for optimization multi-parameter both chemical physical properties. Within context, we propose general workflow realizing objective detailed simulation-based experiments. These physics-informed open path to tractable, rapid solutions parameter identification design problems. They also applications other optimal battery material