Data-driven prediction of battery cycle life before capacity degradation

By Kristen A. Severson, Peter M. Attia, Norman Jin, Nicholas Perkins, Benben Jiang, Zi Yang, Michael H. Chen, Muratahan Aykol, Patrick K. Herring, Dimitrios Fraggedakis and 4 more. Nature Energy, 2019

2,606 citations recorded by the source corpus.

Subfields: Automotive Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/242a5c2ecb74cbbc2f9d9bdb6e76bb1ca36cdcb9

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

Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning (2020, methodology): “Features derived from the charging and discharging curve are by far the most commonly used inputs because typical battery management systems collect current – voltage data 13 – 18 .”
Closed-loop optimization of fast-charging protocols for batteries with machine learning (2020, methodology): “The early predictor is a linear model trained via elastic net regression(27) on features extracted from the charging data of the first 100 cycles (Supplementary Table 1), similar to that presented in Severson et al.(5).”
Technoeconomic model of second-life batteries for utility-scale solar considering calendar and cycle aging (2020, background): “require larger datasets [10], and other machine learning approaches using neural networks that again require large datasets [11].”
Machine Learning Applied to Electrified Vehicle Battery State of Charge and State of Health Estimation: State-of-the-Art (2020, methodology): “The dataset available in [72], for example, was obtained from 124 LFP cells acquired at fast-charging conditions at varying SOC ranges.”
Power Electronics Reliability: State of the Art and Outlook (2021, methodology): “The prediction for degradation curves based on early testing results is applied for film capacitors [115] and batteries [116, 117].”
Review—"Knees" in Lithium-Ion Battery Aging Trajectories (2022, positive): “Data-driven models may be well suited for knee pathways with bulk electrochemical signals; for instance, the high predictive performance of features sourced from the cell voltage responses during discharge in Severson et al.(37) was largely attributed to the detectability of the knee pathway via bul”
Battery digital twins: Perspectives on the fusion of models, data and artificial intelligence for smart battery management systems (2020, methodology): “A notable application of a data driven used for the RUL estimation in batteries is shown by Severson et al. [54] who demonstrated how a simple linear regression model, when combined with diﬀerential voltage data for LFP-Gr cells cycled under fast charging proﬁles could be used to estimate the RUL…”
The challenge and opportunity of battery lifetime prediction from field data (2021, methodology): “[52] showed that using features generated from changes between different cycles can give very accurate predictions of lifetime, even using a simple regularized linear regression model.”