Thermal Data-driven Model Reduction for Enhanced Battery Health Monitoring

Michael Khasin; Mohit R Mehta; Chetan Kulkarni; John W Lawson

NASA NTRS · 20230015788

Thermal Data-driven Model Reduction for Enhanced Battery Health Monitoring

Michael Khasin·Mohit R Mehta·Chetan Kulkarni·John W Lawson

View original source ↗Read source document ↗Export metadata ↓

Abstract

Electric aviation faces a major challenge of avoiding potentially catastrophic consequences of the battery’s thermal runaway while keeping the weight of the battery low. Detection of early warning signals of battery failures requires accurate monitoring of the battery’s health throughout its lifespan. However, identifying the parameters of the battery from field data is notoriously difficult. We investigate this problem within the framework of modeling the temperature dynamics of a Li-ion cell during tests simulating loading in electric aircraft flights. It is found that the parameters of a higher-fidelity physics-based thermal model cannot be identified from the simulated flight data. To resolve this issue, we reduce the higher-fidelity thermal model to a model with fewer parameters. The resulting reduced-order model can predict temperature dynamics accurately and is identifiable throughout the cell’s lifespan which allows using the model’s parameters to monitor the state-of-health of the aging cell and detect anomalies in thermal behavior.

Explore related subjects

Li ion batteries Reduce-order models Battery Management Systems

Keep this discovery

BibTeX RIS

Michael Khasin, Mohit R Mehta, Chetan Kulkarni, John W Lawson. Thermal Data-driven Model Reduction for Enhanced Battery Health Monitoring. https://ntrs.nasa.gov/citations/20230015788

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

Discover connections

Lithium-ion batteries material Battery Management Systems subject Li ion batteries subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related discoveries

NASA NTRS2024

Ejecta Management in a Safe Lithium Ion Battery Design

As lithium-ion battery energy densities continue to rise, managing the heat and pressure generated during failure events has become increasingly critical. Safety systems must effectively relieve pressure without releasing sparks, flames, or particulate matter, requiring robust filtration solutions. The challenge is compounded by the reduced free volume available for gas expansion in high-density designs, which increases the demands on these filters. While significant progress has been made through experimental studies and modeling efforts to understand the behavior of ejecta during battery failures, there remains a pressing need for practical, rule-of-thumb sizing parameters. These parameters would help correlate high-energy waste streams with appropriate filter design, ensuring reliable containment and safety. This talk will explore recent experimental findings in this area and discuss the potential pathways for developing these essential sizing guidelines.

Ejecta Management↗

NASA NTRSDate not supplied

Li-ion Battery Aging with Hybrid Physics-Informed Neural Networks and Fleet-wide Data

In this work, we propose a hybrid model for Li-ion battery discharge and aging prediction that leverages fleet-wide data to predict future capacity drops.The model is built upon an hybrid approach merging physics-based and empirical equations, as well as neural network models in a recurrent neural network cell. The hybrid physics-informed neural network can predict voltage discharge cycles given the loading profile, and estimate the used capacity of the battery under random-loading conditions by tracking aging parameters connected to the residual capacity of the battery. By merging information on the battery aging parameters with existing fleet-wide aging data, the model can predict the future residual capacity of the battery that is being monitored, and therefore enable predictions of voltage discharge curves far ahead in the battery life cycle. We validated the approach using the NASA Prognostics Data Repository Battery data-set, which contains experimental data on Li-ion batteries discharged at random loading conditions in a controlled environment. The approach also allows the identification of discrepancies between the battery aging trend and the trend observed at the fleet level, so that batteries behaving differently from the rest of the fleet can be subject to closer monitoring and further testing to refine predictions.

PINN↗

NASA NTRSDate not supplied

Usage-based Lifing of Lithium-Ion Battery with HybridPhysics-Informed Neural Networks

Lithium-ion batteries are commonly used to power unmanned aircraft vehicles (UAVs).The ability to model and forecast the remaining useful life of these batteries enables UAV reliability assurance. Building accurate models for battery state of charge and state of health based on first principles is challenging due to the complex electrochemistry that governs battery operations and computational complexity required to solve them. Therefore, reduced order models are often used due to their ability to capture the overall battery discharge. Un-fortunately, these simplifications lead to residual discrepancy between model predictions and observed data. In this paper, we present a hybrid modeling approach merging reduced-order models and neural networks. In this approach, while most of the input-output relationship is captured by Nernst and Butler-Volmer equations, data-driven kernels reduce the gap between predictions and observations. We validate our approach using data publicly available through the NASA Prognostics Center of Excellence repository. Results showed that our hybrid battery prognosis model can be successfully calibrated, even with a limited number of observations.

Lithium-ion Battery↗