Publication review

10 standout papers shaping our industrial models.

Digital twins of electrode manufacturing, hybrid physics-AI workflows, microstructure-resolved mechanical models. These landmark publications are the research that sits under Aikemics.

Read the research DNA →Contact us

A grid of peer-reviewed journal covers featuring the research group's battery work

Why this review matters

The science behind practical battery manufacturing.

The selection covers publications that combine mechanistic electrochemistry, manufacturing process simulation and data-driven engineering.

These works are the evidence behind our commitment to transparency, model validation and industrially relevant prediction.

The abstracts below are ultra-short summaries of the advances that feed Aikemics Studio.

Top 10 publications

Landmark papers with direct industrial relevance.

Ultra-short abstracts from the most notable papers in our network.

Surrogate modeling for electrode manufacturing

Physics-based manufacturing models get combined with deep-learning surrogates to predict electrode quality faster, so process optimization moves at engineering speed.

→

Hybrid physics-AI manufacturing workflows

A coupled physics and AI framework shows how battery process parameters can be inverted to hit performance and yield targets.

→

Digital twin of Li-ion battery manufacturing

The ARTISTIC digital model links slurry preparation, coating, drying and calendering to electrochemical performance predictions.

→

3D microstructure-resolved stress in solid-state electrodes

A microstructure-aware model quantifies mechanical stress in solid-state battery electrodes and guides robust cell assembly.

→

AI-assisted slurry drying simulation

Time-dependent physics models of slurry drying get accelerated with AI, cutting uncertainty on coating and porosity outcomes.

→

Experimentally validated multiscale modeling linking electrode manufacturing with electrochemical performance

A validated 3D model reveals how battery manufacturing parameters (slurry formulation, calendering) dictate electrode microstructure and performance.

→

Multiobjective optimization of battery manufacturing for electrode inverse design

A validated ML pipeline uses physics-based simulations for fast, multi-objective optimization and inverse design of battery electrode manufacturing.

→

Data-driven digitalization for manufacturing

A modeling workflow extracts process-parameter interdependencies from experimental and simulation databases for practical optimization.

→

Surrogate electrode calendering model capturing the impact of calendering conditions on electrode architecture and springback phenomena

A novel deep learning model predicts 3D electrode microstructures during calendering faster than physics simulations, enabling real-time optimization.

→

Machine learning surrogate of electrolyte infiltration in battery electrodes

A fast ML model accurately predicts 3D electrolyte infiltration and wetting times in electrodes, enabling massive screening for cell optimization.

→

Read the full output

See how peer-reviewed research feeds our platform.

These publications are the foundation of Aikemics models for slurry, coating, calendering, assembly and cell performance.

Read the research DNA →Talk to our scientific team