Can I read Unveiling the Performance Impact of Module Level Features on Parallel-connected Lithium-ion Cells via Explainable Machine Learning Techniques on a Full Factorial Design of Experiments on EtoBox?

Unveiling the Performance Impact of Module Level Features on Parallel-connected Lithium-ion Cells via Explainable Machine Learning Techniques on a Full Factorial Design of Experiments by Piombo, Gabriele (author);Fasolato, Simone (author);Heymer, Robert (author);Hidalgo, Marc (author);Faraji Niri, Mona (author);Onori, Simona (author);Marco, James (author) is a Engineering article available to read on EtoBox.

What is Unveiling the Performance Impact of Module Level Features on Parallel-connected Lithium-ion Cells via Explainable Machine Learning Techniques on a Full Factorial Design of Experiments about?

Parallel string performance imbalances are unavoidable due to manufacturing-related cell-to-cell inhomogeneities (e.g. capacity, internal resistance), suboptimal pack and cooling system design. Understanding the most important features at a single cell and module level influencing the heterogeneity propagation inside the modules/packs is therefore crucial to limiting the phenomenon. In this article, a methodology combining wellestablished non-invasive single-cell characterisation tests with data-driven modelling tools is proposed. Two batches of twenty new, commercial NMC and NCA cells are first characterised to identify out-of-manufacture internal resistance and capacity distributions. Then, a 54 test condition full-factorial Design of Experiment campaign on four cells ladder-parallel connected modules is performed. The experiments inform about how the cells' current, State of Charge, temperature distributions and time to self-balance under 0.75C constant current discharge loads are affected by interconnection resistance, operating temperature, different chemistry combination and ageing. The multivariate linear model analysis confirms that combining NMC and NCA cells in parallel i

Who reads Unveiling the Performance Impact of Module Level Features on Parallel-connected Lithium-ion Cells via Explainable Machine Learning Techniques on a Full Factorial Design of Experiments?

Author

Piombo, Gabriele (author);Fasolato, Simone (author);Heymer, Robert (author);Hidalgo, Marc (author);Faraji Niri, Mona (author);Onori, Simona (author);Marco, James (author)

Publisher

Elsevier BV

Published

2024

Language

EN

Field

Engineering (Physical Sciences)