4BLIFE

ADEME-funded project focused on diagnostics and prognostics of lithium-ion batteries for sustainable mobility and energy systems.

Overview

4BLIFE is a French national research project funded by ADEME and dedicated to the development of advanced methodologies for battery diagnostics, health estimation and lifetime prediction.

The project brings together academic and industrial partners with the objective of improving the reliability, sustainability and operational management of lithium-ion batteries used in transportation and stationary energy applications.

My contribution focused on the development of artificial intelligence methods for battery state estimation, degradation analysis and prognostics.

Funding

ADEME

Consortium

Academic partners:

  • Université Gustave Eiffel (LICIT-ECO7)
  • LAAS-CNRS
  • UTC Compiègne (AVENUE)
  • SATIE

Industrial partners:

  • BATCONNECT
  • SIREA

The project consortium is explicitly listed in my research dossier. :contentReference[oaicite:1]{index=1}

Scientific Context

Lithium-ion batteries are becoming essential components of modern energy systems.

Their deployment in:

  • Electric vehicles
  • Renewable energy systems
  • Smart grids
  • Stationary storage

creates a growing need for accurate diagnostic and prognostic tools capable of estimating battery condition throughout their operational life.

Traditional approaches often rely on simplified empirical indicators that do not fully capture battery aging mechanisms.

Main Objectives

  • Estimate battery State of Health (SOH).
  • Predict battery lifetime.
  • Identify degradation mechanisms.
  • Improve maintenance planning.
  • Develop AI-based prognostic tools.
  • Support second-life battery applications.

Methodology

The project combines battery measurements, physical understanding and machine learning approaches.

Artificial intelligence framework for battery diagnostics, health estimation and lifetime prediction.

Axis 1 – Data Acquisition

  • Current measurements
  • Voltage measurements
  • Temperature monitoring
  • Cycling data

Axis 2 – Feature Engineering

  • Aging indicators
  • Capacity evolution
  • Internal resistance indicators
  • Health signatures

Axis 3 – Artificial Intelligence

  • Machine learning
  • Health estimation
  • Prognostics
  • Remaining useful life prediction

Axis 4 – Decision Support

  • Maintenance planning
  • Asset management
  • Reliability optimization

Main Contributions

During the project, I contributed to:

  • Battery health estimation methodologies.
  • Artificial intelligence models for degradation analysis.
  • Prognostic frameworks for lifetime prediction.
  • Interpretation of battery aging behaviors.

Expected Outcomes

  • Advanced SOH estimators.
  • Remaining useful life prediction tools.
  • Scientific publications.
  • Technology transfer opportunities.
  • Contributions to sustainable mobility.

Scientific Impact

4BLIFE contributes to improving the sustainability of battery technologies by enabling more reliable health estimation and better lifecycle management.

The methodologies developed within the project are applicable to electric mobility, renewable energy integration and future smart-grid infrastructures.

Keywords

Lithium-Ion Batteries · Battery Health · State of Health · Remaining Useful Life · Prognostics · Artificial Intelligence · Predictive Maintenance · Energy Storage

Project Status

Completed

References