Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries
In this study, we investigate the use of artificial neural networks as a potentially efficient method to determine the rate capability of electrodes for lithium-ion batteries with different porosities. The performance of a lithium-ion battery is, to a large extent, determined by the microstructure (...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-03-01
|
Series: | Batteries |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-0105/10/3/99 |
_version_ | 1797242073747816448 |
---|---|
author | Patrick Deeg Christian Weisenberger Jonas Oehm Denny Schmidt Orsolya Csiszar Volker Knoblauch |
author_facet | Patrick Deeg Christian Weisenberger Jonas Oehm Denny Schmidt Orsolya Csiszar Volker Knoblauch |
author_sort | Patrick Deeg |
collection | DOAJ |
description | In this study, we investigate the use of artificial neural networks as a potentially efficient method to determine the rate capability of electrodes for lithium-ion batteries with different porosities. The performance of a lithium-ion battery is, to a large extent, determined by the microstructure (i.e., layer thickness and porosity) of its electrodes. Tailoring the microstructure to a specific application is a crucial process in battery development. However, unravelling the complex correlations between microstructure and rate performance using either experiments or simulations is time-consuming and costly. Our approach provides a swift method for predicting the rate capability of battery electrodes by using machine learning on microstructural images of electrode cross-sections. We train multiple models in order to predict the specific capacity based on the batteries’ microstructure and investigate the decisive parts of the microstructure through the use of explainable artificial intelligence (XAI) methods. Our study shows that even comparably small neural network architectures are capable of providing state-of-the-art prediction results. In addition to this, our XAI studies demonstrate that the models are using understandable human features while ignoring present artefacts. |
first_indexed | 2024-04-24T18:33:26Z |
format | Article |
id | doaj.art-7319561c8eb24512aa593a20bcd3dc51 |
institution | Directory Open Access Journal |
issn | 2313-0105 |
language | English |
last_indexed | 2024-04-24T18:33:26Z |
publishDate | 2024-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Batteries |
spelling | doaj.art-7319561c8eb24512aa593a20bcd3dc512024-03-27T13:21:14ZengMDPI AGBatteries2313-01052024-03-011039910.3390/batteries10030099Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion BatteriesPatrick Deeg0Christian Weisenberger1Jonas Oehm2Denny Schmidt3Orsolya Csiszar4Volker Knoblauch5Materials Research Institute Aalen (IMFAA), Aalen University, Beethovenstr. 1, 73430 Aalen, GermanyMaterials Research Institute Aalen (IMFAA), Aalen University, Beethovenstr. 1, 73430 Aalen, GermanyMaterials Research Institute Aalen (IMFAA), Aalen University, Beethovenstr. 1, 73430 Aalen, GermanyMaterials Research Institute Aalen (IMFAA), Aalen University, Beethovenstr. 1, 73430 Aalen, GermanyMaterials Research Institute Aalen (IMFAA), Aalen University, Beethovenstr. 1, 73430 Aalen, GermanyMaterials Research Institute Aalen (IMFAA), Aalen University, Beethovenstr. 1, 73430 Aalen, GermanyIn this study, we investigate the use of artificial neural networks as a potentially efficient method to determine the rate capability of electrodes for lithium-ion batteries with different porosities. The performance of a lithium-ion battery is, to a large extent, determined by the microstructure (i.e., layer thickness and porosity) of its electrodes. Tailoring the microstructure to a specific application is a crucial process in battery development. However, unravelling the complex correlations between microstructure and rate performance using either experiments or simulations is time-consuming and costly. Our approach provides a swift method for predicting the rate capability of battery electrodes by using machine learning on microstructural images of electrode cross-sections. We train multiple models in order to predict the specific capacity based on the batteries’ microstructure and investigate the decisive parts of the microstructure through the use of explainable artificial intelligence (XAI) methods. Our study shows that even comparably small neural network architectures are capable of providing state-of-the-art prediction results. In addition to this, our XAI studies demonstrate that the models are using understandable human features while ignoring present artefacts.https://www.mdpi.com/2313-0105/10/3/99CNNdeep learningmachine learningimage regressionlithium-ion batteries |
spellingShingle | Patrick Deeg Christian Weisenberger Jonas Oehm Denny Schmidt Orsolya Csiszar Volker Knoblauch Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries Batteries CNN deep learning machine learning image regression lithium-ion batteries |
title | Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries |
title_full | Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries |
title_fullStr | Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries |
title_full_unstemmed | Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries |
title_short | Swift Prediction of Battery Performance: Applying Machine Learning Models on Microstructural Electrode Images for Lithium-Ion Batteries |
title_sort | swift prediction of battery performance applying machine learning models on microstructural electrode images for lithium ion batteries |
topic | CNN deep learning machine learning image regression lithium-ion batteries |
url | https://www.mdpi.com/2313-0105/10/3/99 |
work_keys_str_mv | AT patrickdeeg swiftpredictionofbatteryperformanceapplyingmachinelearningmodelsonmicrostructuralelectrodeimagesforlithiumionbatteries AT christianweisenberger swiftpredictionofbatteryperformanceapplyingmachinelearningmodelsonmicrostructuralelectrodeimagesforlithiumionbatteries AT jonasoehm swiftpredictionofbatteryperformanceapplyingmachinelearningmodelsonmicrostructuralelectrodeimagesforlithiumionbatteries AT dennyschmidt swiftpredictionofbatteryperformanceapplyingmachinelearningmodelsonmicrostructuralelectrodeimagesforlithiumionbatteries AT orsolyacsiszar swiftpredictionofbatteryperformanceapplyingmachinelearningmodelsonmicrostructuralelectrodeimagesforlithiumionbatteries AT volkerknoblauch swiftpredictionofbatteryperformanceapplyingmachinelearningmodelsonmicrostructuralelectrodeimagesforlithiumionbatteries |