Closed-loop optimization of fast-charging protocols for batteries with machine learning

By Peter M. Attia, Aditya Grover, Norman Jin, Kristen A. Severson, Todor Markov, Yang-Hung Liao, Michael H. Chen, Bryan Cheong, Nicholas Perkins, Zi Yang and 6 more. Nature, 2020

946 citations recorded by the source corpus.

Subfields: Automotive Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/cbff26682ca59509b58b350a955978974d967a60

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Emerging materials intelligence ecosystems propelled by machine learning (2020, background): “…scattering experiments 178,179 , sparse dynamic sampling to reduce image acquisition time 180 , prediction of battery cycle life from early-cycle discharge voltage curves 181,182 and on-the-fly analysis of X-ray diffraction patterns for rapid phase identification and distribution analysis 183–185 .”
Battery digital twins: Perspectives on the fusion of models, data and artificial intelligence for smart battery management systems (2020, methodology): “Attia et al. [58] for instance used a linear model trained via elastic net regression to predict the ﬁnal lifetime of LFP-Gr batteries from the ﬁrst 100 cycles under diﬀerent fast charging algorithms.”
Machine learning pipeline for battery state-of-health estimation (2021, methodology): “The current approaches to capacity fade estimation involves parameter estimation using either of the following modelling types, equivalent circuit models (ECMs) [8], [9], [10], electrochemical models [11], [12], [13], or data-driven models [14], [15], [16], [17], [18], [19].”
Physics-informed neural network for lithium-ion battery degradation stable modeling and prognosis (2024, neutral): “Given the dif ﬁ culty in establishing physical models and the dif ﬁ - culty in obtaining complete discharge capacity, many studies have used data-driven methods 20 – 24 to estimate SOH based on current and voltage curves during charge and discharge.”
Machine learning for a sustainable energy future (2022, background): “38 and redox active electrolyte for RFBs 39 ML has also aided battery management, for example, through state of charge determination, 40 state of health evaluation 41,42 and remaining life prediction 43,44 .”
Review—"Knees" in Lithium-Ion Battery Aging Trajectories (2022, neutral): “The onset of lithium plating is also sensitive to the charging protocol, with many studies demonstrating that informed design of charging protocols can substantially extend cell lifetime by preventing lithium plating.(63,68,69) Optimizing electrode architectures to improve electrolyte transport kine”
Current and future lithium-ion battery manufacturing (2021, methodology): “The prediction of battery life and degradation is possible with the involvement of the AI, and when combined with a Bayesian optimization algorithm, the AI can explore the parameters for fast charging efficiently (Pan et al., 2018; Severson et al., 2019; Attia et al., 2020; Bhowmik and Vegge, 2020).”