High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning
Abstract Nickel‐rich layered oxides (LiNixCoyMnzO2, NCM) are among the most promising cathode materials for high‐energy lithium‐ion batteries, offering high specific capacity and output voltage at a relatively low cost. However, industrial‐scale co‐precipitation presents significant challenges, part...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-07-01
|
| Series: | InfoMat |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/inf2.70031 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839628020213612544 |
|---|---|
| author | Junyoung Seo Taekyeong Kim Kisung You Youngmin Moon Jina Bang Waunsoo Kim Il Jeon Im Doo Jung |
| author_facet | Junyoung Seo Taekyeong Kim Kisung You Youngmin Moon Jina Bang Waunsoo Kim Il Jeon Im Doo Jung |
| author_sort | Junyoung Seo |
| collection | DOAJ |
| description | Abstract Nickel‐rich layered oxides (LiNixCoyMnzO2, NCM) are among the most promising cathode materials for high‐energy lithium‐ion batteries, offering high specific capacity and output voltage at a relatively low cost. However, industrial‐scale co‐precipitation presents significant challenges, particularly in maintaining particle sphericity, ensuring a stable concentration gradient, and preserving production yield when transitioning from lab‐scale compositions. This study addresses a critical issue in the large‐scale synthesis of nickel‐rich NCM (x = 0.8381): nickel leaching, which compromises particle uniformity and battery performance. To mitigate this, we optimize the reaction process and develop an artificial intelligence‐driven defect prediction system that enhances precursor stability. Our domain adaptation based machine learning model, which accounts for equipment wear and environmental variations, achieves a defect detection accuracy of 97.8% based on machine data and process conditions. By implementing this approach, we successfully scale up NCM precursor production to over 2 tons, achieving 83% capacity retention after 500 cycles at a 1C rate. In addition, the proposed approach demonstrates the formation of a concentration gradient in the composition and a high sphericity of 0.951 (±0.0796). This work provides new insights into the stable mass production of NCM precursors, ensuring both high yield and performance reliability. |
| format | Article |
| id | doaj-art-f9c861f29ea6433c9b466981f6d74f9c |
| institution | Matheson Library |
| issn | 2567-3165 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | InfoMat |
| spelling | doaj-art-f9c861f29ea6433c9b466981f6d74f9c2025-07-16T04:01:09ZengWileyInfoMat2567-31652025-07-0177n/an/a10.1002/inf2.70031High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learningJunyoung Seo0Taekyeong Kim1Kisung You2Youngmin Moon3Jina Bang4Waunsoo Kim5Il Jeon6Im Doo Jung7Department of Mechanical Engineering Ulsan National Institute of Science and Technology Ulsan Republic of KoreaDepartment of Mechanical Engineering Ulsan National Institute of Science and Technology Ulsan Republic of KoreaSafety and Health Research Group Research Institute of Industrial Science and Technology Pohang Republic of KoreaSafety and Health Research Group Research Institute of Industrial Science and Technology Pohang Republic of KoreaSafety and Health Research Group Research Institute of Industrial Science and Technology Pohang Republic of KoreaDepartment of Cathode Production POSCO FUTURE M Pohang Republic of KoreaDepartment of Nano Engineering, Department of Nano Science and Technology SKKU Advanced Institute of Nanotechnology (SAINT), Sungkyunkwan University (SKKU) Suwon Republic of KoreaDepartment of Mechanical Engineering Ulsan National Institute of Science and Technology Ulsan Republic of KoreaAbstract Nickel‐rich layered oxides (LiNixCoyMnzO2, NCM) are among the most promising cathode materials for high‐energy lithium‐ion batteries, offering high specific capacity and output voltage at a relatively low cost. However, industrial‐scale co‐precipitation presents significant challenges, particularly in maintaining particle sphericity, ensuring a stable concentration gradient, and preserving production yield when transitioning from lab‐scale compositions. This study addresses a critical issue in the large‐scale synthesis of nickel‐rich NCM (x = 0.8381): nickel leaching, which compromises particle uniformity and battery performance. To mitigate this, we optimize the reaction process and develop an artificial intelligence‐driven defect prediction system that enhances precursor stability. Our domain adaptation based machine learning model, which accounts for equipment wear and environmental variations, achieves a defect detection accuracy of 97.8% based on machine data and process conditions. By implementing this approach, we successfully scale up NCM precursor production to over 2 tons, achieving 83% capacity retention after 500 cycles at a 1C rate. In addition, the proposed approach demonstrates the formation of a concentration gradient in the composition and a high sphericity of 0.951 (±0.0796). This work provides new insights into the stable mass production of NCM precursors, ensuring both high yield and performance reliability.https://doi.org/10.1002/inf2.70031domain adaptationmachine learningmass productionnickel‐rich layered oxides cathodeprocess monitoringschedule optimization |
| spellingShingle | Junyoung Seo Taekyeong Kim Kisung You Youngmin Moon Jina Bang Waunsoo Kim Il Jeon Im Doo Jung High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning InfoMat domain adaptation machine learning mass production nickel‐rich layered oxides cathode process monitoring schedule optimization |
| title | High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning |
| title_full | High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning |
| title_fullStr | High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning |
| title_full_unstemmed | High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning |
| title_short | High quality large‐scale nickel‐rich layered oxides precursor co‐precipitation via domain adaptation‐based machine learning |
| title_sort | high quality large scale nickel rich layered oxides precursor co precipitation via domain adaptation based machine learning |
| topic | domain adaptation machine learning mass production nickel‐rich layered oxides cathode process monitoring schedule optimization |
| url | https://doi.org/10.1002/inf2.70031 |
| work_keys_str_mv | AT junyoungseo highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT taekyeongkim highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT kisungyou highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT youngminmoon highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT jinabang highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT waunsookim highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT iljeon highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning AT imdoojung highqualitylargescalenickelrichlayeredoxidesprecursorcoprecipitationviadomainadaptationbasedmachinelearning |