Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3363063

BatteryPro: A Python Toolkit for Battery Data Analysis and Machine Learning Predictions

Warner, Micah Allen [Idaho National Laboratory]·Park, Bumjun [Idaho National Laboratory] (ORCID:0000000237791315)·Gering, Kevin L [Idaho National Laboratory] (ORCID:0000000228214057)
View original source ↗Read source document ↗Export metadata ↓

Abstract

Analyzing battery test data for research & development can be time-consuming since battery tests often run on the order of months to years, generating large volumes of data. BatteryPro is a comprehensive Python package and software designed to facilitate advanced analysis and performance predictions for battery test data. Developed for battery researchers, it supports data types from widely used battery testing instruments, including MACCOR and Biologic cycling systems. The software provides a variety of tools for extracting and plotting key battery parameters such as time, voltage, capacity, current, and pressure. In addition to its extensive data analysis capabilities, BatteryPro features a dedicated machine learning module that employs a Bayesian Gaussian Mixture Model (GMM) to predict battery performance and degradation. Users can generate synthetic capacity fade data, calculate fade metrics, and leverage predictive models to forecast long-term battery behavior. The software's graphical user interface (GUI) enhances usability, allowing researchers to upload, merge, and analyze multiple data files with full customizability. The GUI also supports machine learning predictions, enabling users to fit models and make predictions based on selected data and parameters. BatteryPro is built using QtDesigner, scikit-learn, matplotlib, and pandas, ensuring a high level of customization, flexibility, and accuracy in battery data analysis. This tool aims to empower researchers with the ability to perform detailed battery analysis and make informed predictions, ultimately advancing the field of battery research.

Explore related subjects

25 - ENERGY STORAGEBattery PerformanceBattery TestingData AnalysisMachine LearningPython

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Warner, Micah Allen [Idaho National Laboratory], Park, Bumjun [Idaho National Laboratory] (ORCID:0000000237791315), Gering, Kevin L [Idaho National Laboratory] (ORCID:0000000228214057). 2025-08-15. BatteryPro: A Python Toolkit for Battery Data Analysis and Machine Learning Predictions. https://www.osti.gov/biblio/3363063

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

An Accelerated Testing and Analysis Framework for Qualification of Battery Materials

The continuously growing demand for batteries used within automotive, aviation, and grid applications has exacerbated the need to supplement critical battery material feedstocks, such as those for anode and cathode active materials. New or supplementary material sources, however, universally comprise unique material properties that can significantly affect the lifetime and performance of resultant batteries. As such, the influence of composition, microstructure, and morphology on electrochemical performance should be characterized quickly and accurately to accelerate commercialization of new material sources. This work introduces a tiered framework to quickly assess new material viability and understand the influence of physicochemical properties on battery performance. The Tier 1 testing described here is rapid and lower-effort to quickly recognize materials with fundamental flaws and potentially disqualify them. Later testing would require more time and effort but provide higher fidelity information with a goal of validating materials for specific applications. A case study examining various commercial sources of LiFePO4 (LFP) is presented, using Tier 1 of the protocol to identify rapid electrochemical and physicochemical signals that correlate with performance and to provide early go/no-go decisions on LFP materials without the need for long-term cycling data.

25 - ENERGY STORAGE↗
DOE OSTI2026

Surface heterogeneity propagation and homogenization for pouch cell-scale Li metal anodes

Li metal anode is a promising candidate for next-generation energy storage systems and is widely explored in Li-ion and solid-state batteries. Despite its potential, Li metal anodes face instabilities during long-term cycling, especially when paired with NMC or sulfur-based cathodes, where Li is cycled at high capacities of 6-8 mAh/cm2, equivalent to a thickness of 30-40 µm. During such extensive utilization, degradation mechanisms such as excessive solid electrolyte interphase (SEI), dendrites, and dead Li emerge, and ultimately lead to sudden failure and reduced cycle life. The origin of the degradation mechanisms stem from surface heterogeneities introduced during Li foil manufacturing and storage [1, 2]. As cycling progresses, the local heterogeneities propagate, resulting in uneven Li utilization and degradation-prone regions across the electrode [3], which consequently induce performance variations at the cell level. This heterogeneity propagation is particularly pronounced in large-format pouch cells in practical applications, where the surface effects are magnified. Without a clear understanding of the multi-scale heterogeneities and the development of surface homogenization methods, the performance consistency will be compromised, hindering the commercialization of Li metal batteries. In this presentation, we investigate the evolution of surface heterogeneity propagation on commercially available Li foils. We discover that inhomogeneous Li utilization appears as early as the first half-cycle of formation, manifesting as localized clusters and pits. In pouch cell configurations, these features exhibit areal density variations across the electrode on a scale of millimeters. To improve Li utilization homogeneity, a scalable mechanical brushing method is introduced to remove the chemically heterogeneous surface passivation layer. Furtherore, the influence of utilization homogeneity on cell-to-cell consistency is evaluated using 32 Li-NMC811 pouch cells divided into as-received and brushed Li groups. On the brushed Li, clusters and pits are no longer observable, and the cells exhibit significantly improved consistency in discharge capacity trajectories and cycle lifetime. Overall, this study highlights the role of Li surface utilization homogeneity on long-term cycling performance. Our research provides a pathway for improving large-area electrode uniformity and establishing evaluation methods for cell-to-cell consistency, both are key steps toward the commercialization of Li metal batteries and beyond. [1] Otto, Svenja-K., et al. "In-depth characterization of lithium-metal surfaces with XPS and ToF-SIMS: toward better understanding of the passivation layer." Chemistry of Materials 33.3 (2021): 859-867. [2] Hatzell, Kelsey, et al. "Aligning lithium metal battery research and development across academia and industry." Joule (2024). [3] Kim, Sangwook, et al. "Calendar life of lithium metal batteries: Accelerated aging and failure analysis." Energy Storage Materials 65 (2024): 103147.

25 - ENERGY STORAGE↗
DOE OSTI2026

Machine Learning Digital Twin for Lithium Ion Battery State of Health Predictions

A digital twin system has been established to model the long term degradation of the state of health of lithium ion batteries. Two data streams result from the computational model of the system and from the physical experiment measurements. A machine learning pipeline has been developed at the nexus of these data streams. Leveraging the unique data sources in multiple transfer learning approaches has lead to the development of multiple cell specific machine learning digital twins. Our discussion on this first of its kind technology will cover challenges in data ingestion, scalability, architecture and orchestration, and research findings.

25 - ENERGY STORAGE↗