Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning

Electric vehicles are shaping the future of the automotive industry. The traction battery is one of the most important components of electric cars. To ensure that the battery operates safely, it is essential to physically and electrically separate the cells facing each other. Coating a cell with var...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Johannes Maximilian Vater, Florian Gruber, Wulf Grählert, Sebastian Schneider, Alois Christian Knoll
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	coating adhesion battery cells hyperspectral imaging machine learning AI prediction Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/bf042985fab8478ea84f1d7b73cc1e20
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bf042985fab8478ea84f1d7b73cc1e20
record_format	dspace
spelling	oai:doaj.org-article:bf042985fab8478ea84f1d7b73cc1e202021-11-25T17:16:45ZPrediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning10.3390/coatings111113882079-6412https://doaj.org/article/bf042985fab8478ea84f1d7b73cc1e202021-11-01T00:00:00Zhttps://www.mdpi.com/2079-6412/11/11/1388https://doaj.org/toc/2079-6412Electric vehicles are shaping the future of the automotive industry. The traction battery is one of the most important components of electric cars. To ensure that the battery operates safely, it is essential to physically and electrically separate the cells facing each other. Coating a cell with varnish helps achieve this goal. Current studies use a destructive method on a sampling basis, the cross-cut test, to investigate the coating quality. In this paper, we present a fast, nondestructive and inline alternative based on hyperspectral imaging and artificial intelligence. Therefore, battery cells are measured with hyperspectral cameras in the visible and near-infrared (VNIR and NIR) parts of the electromagnetic spectrum before and after cleaning then coated and finally subjected to cross-cut test to estimate coating adhesion. During the cross-cut test, the cell coating is destroyed. This work aims to replace cross-cut tests with hyperspectral imaging (HSI) and machine learning to achieve continuous quality control, protect the environment, and save costs. Therefore, machine learning models (logistic regression, random forest, and support vector machines) are used to predict cross-cut test results based on hyperspectral data. We show that it is possible to predict with an accuracy of ~75% whether problems with coating adhesion will occur. Hyperspectral measurements in the near-infrared part of the spectrum yielded the best results. The results show that the method is suitable for automated quality control and process control in battery cell coating, but still needs to be improved to achieve higher accuracies.Johannes Maximilian VaterFlorian GruberWulf GrählertSebastian SchneiderAlois Christian KnollMDPI AGarticlecoating adhesionbattery cellshyperspectral imagingmachine learningAIpredictionEngineering (General). Civil engineering (General)TA1-2040ENCoatings, Vol 11, Iss 1388, p 1388 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	coating adhesion battery cells hyperspectral imaging machine learning AI prediction Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	coating adhesion battery cells hyperspectral imaging machine learning AI prediction Engineering (General). Civil engineering (General) TA1-2040 Johannes Maximilian Vater Florian Gruber Wulf Grählert Sebastian Schneider Alois Christian Knoll Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning
description	Electric vehicles are shaping the future of the automotive industry. The traction battery is one of the most important components of electric cars. To ensure that the battery operates safely, it is essential to physically and electrically separate the cells facing each other. Coating a cell with varnish helps achieve this goal. Current studies use a destructive method on a sampling basis, the cross-cut test, to investigate the coating quality. In this paper, we present a fast, nondestructive and inline alternative based on hyperspectral imaging and artificial intelligence. Therefore, battery cells are measured with hyperspectral cameras in the visible and near-infrared (VNIR and NIR) parts of the electromagnetic spectrum before and after cleaning then coated and finally subjected to cross-cut test to estimate coating adhesion. During the cross-cut test, the cell coating is destroyed. This work aims to replace cross-cut tests with hyperspectral imaging (HSI) and machine learning to achieve continuous quality control, protect the environment, and save costs. Therefore, machine learning models (logistic regression, random forest, and support vector machines) are used to predict cross-cut test results based on hyperspectral data. We show that it is possible to predict with an accuracy of ~75% whether problems with coating adhesion will occur. Hyperspectral measurements in the near-infrared part of the spectrum yielded the best results. The results show that the method is suitable for automated quality control and process control in battery cell coating, but still needs to be improved to achieve higher accuracies.
format	article
author	Johannes Maximilian Vater Florian Gruber Wulf Grählert Sebastian Schneider Alois Christian Knoll
author_facet	Johannes Maximilian Vater Florian Gruber Wulf Grählert Sebastian Schneider Alois Christian Knoll
author_sort	Johannes Maximilian Vater
title	Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning
title_short	Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning
title_full	Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning
title_fullStr	Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning
title_full_unstemmed	Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning
title_sort	prediction of coating adhesion on laser-cleaned metal surfaces of battery cells using hyperspectral imaging and machine learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/bf042985fab8478ea84f1d7b73cc1e20
work_keys_str_mv	AT johannesmaximilianvater predictionofcoatingadhesiononlasercleanedmetalsurfacesofbatterycellsusinghyperspectralimagingandmachinelearning AT floriangruber predictionofcoatingadhesiononlasercleanedmetalsurfacesofbatterycellsusinghyperspectralimagingandmachinelearning AT wulfgrahlert predictionofcoatingadhesiononlasercleanedmetalsurfacesofbatterycellsusinghyperspectralimagingandmachinelearning AT sebastianschneider predictionofcoatingadhesiononlasercleanedmetalsurfacesofbatterycellsusinghyperspectralimagingandmachinelearning AT aloischristianknoll predictionofcoatingadhesiononlasercleanedmetalsurfacesofbatterycellsusinghyperspectralimagingandmachinelearning
_version_	1718412555645353984

Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning

Ejemplares similares