Lithium Metal Battery Quality Control via Transformer–CNN Segmentation
Lithium metal battery (LMB) has the potential to be the next-generation battery system because of its high theoretical energy density. However, defects known as dendrites are formed by heterogeneous lithium (Li) plating, which hinders the development and utilization of LMBs. Non-destructive techniqu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/9/6/111 |
| _version_ | 1797594059659804672 |
|---|---|
| author | Jerome Quenum Iryna V. Zenyuk Daniela Ushizima |
| author_facet | Jerome Quenum Iryna V. Zenyuk Daniela Ushizima |
| author_sort | Jerome Quenum |
| collection | DOAJ |
| description | Lithium metal battery (LMB) has the potential to be the next-generation battery system because of its high theoretical energy density. However, defects known as dendrites are formed by heterogeneous lithium (Li) plating, which hinders the development and utilization of LMBs. Non-destructive techniques to observe the dendrite morphology often use X-ray computed tomography (XCT) to provide cross-sectional views. To retrieve three-dimensional structures inside a battery, image segmentation becomes essential to quantitatively analyze XCT images. This work proposes a new semantic segmentation approach using a transformer-based neural network called TransforCNN that is capable of segmenting out dendrites from XCT data. In addition, we compare the performance of the proposed TransforCNN with three other algorithms, U-Net, Y-Net, and E-Net, consisting of an ensemble network model for XCT analysis. Our results show the advantages of using TransforCNN when evaluating over-segmentation metrics, such as mean intersection over union (mIoU) and mean Dice similarity coefficient (mDSC), as well as through several qualitatively comparative visualizations. |
| first_indexed | 2024-03-11T02:17:18Z |
| format | Article |
| id | doaj.art-577640534d2c4c87bdea98275ff98505 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-11T02:17:18Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-577640534d2c4c87bdea98275ff985052023-11-18T11:04:21ZengMDPI AGJournal of Imaging2313-433X2023-05-019611110.3390/jimaging9060111Lithium Metal Battery Quality Control via Transformer–CNN SegmentationJerome Quenum0Iryna V. Zenyuk1Daniela Ushizima2Department of Electrical Engineering and Computer Science, Berkeley College of Engineering, University of California, Berkeley, CA 94720, USADepartment of Chemical & Biomolecular Engineering, National Fuel Cell Research Center, University of California Irvine, Irvine, CA 92697, USAApplied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USALithium metal battery (LMB) has the potential to be the next-generation battery system because of its high theoretical energy density. However, defects known as dendrites are formed by heterogeneous lithium (Li) plating, which hinders the development and utilization of LMBs. Non-destructive techniques to observe the dendrite morphology often use X-ray computed tomography (XCT) to provide cross-sectional views. To retrieve three-dimensional structures inside a battery, image segmentation becomes essential to quantitatively analyze XCT images. This work proposes a new semantic segmentation approach using a transformer-based neural network called TransforCNN that is capable of segmenting out dendrites from XCT data. In addition, we compare the performance of the proposed TransforCNN with three other algorithms, U-Net, Y-Net, and E-Net, consisting of an ensemble network model for XCT analysis. Our results show the advantages of using TransforCNN when evaluating over-segmentation metrics, such as mean intersection over union (mIoU) and mean Dice similarity coefficient (mDSC), as well as through several qualitatively comparative visualizations.https://www.mdpi.com/2313-433X/9/6/111deep learningsemantic segmentationquality controlTransformer–CNNbattery |
| spellingShingle | Jerome Quenum Iryna V. Zenyuk Daniela Ushizima Lithium Metal Battery Quality Control via Transformer–CNN Segmentation Journal of Imaging deep learning semantic segmentation quality control Transformer–CNN battery |
| title | Lithium Metal Battery Quality Control via Transformer–CNN Segmentation |
| title_full | Lithium Metal Battery Quality Control via Transformer–CNN Segmentation |
| title_fullStr | Lithium Metal Battery Quality Control via Transformer–CNN Segmentation |
| title_full_unstemmed | Lithium Metal Battery Quality Control via Transformer–CNN Segmentation |
| title_short | Lithium Metal Battery Quality Control via Transformer–CNN Segmentation |
| title_sort | lithium metal battery quality control via transformer cnn segmentation |
| topic | deep learning semantic segmentation quality control Transformer–CNN battery |
| url | https://www.mdpi.com/2313-433X/9/6/111 |
| work_keys_str_mv | AT jeromequenum lithiummetalbatteryqualitycontrolviatransformercnnsegmentation AT irynavzenyuk lithiummetalbatteryqualitycontrolviatransformercnnsegmentation AT danielaushizima lithiummetalbatteryqualitycontrolviatransformercnnsegmentation |