{"id":2010,"date":"2021-07-14T09:30:00","date_gmt":"2021-07-14T07:30:00","guid":{"rendered":"http:\/\/cirpicme.org\/?page_id=2010"},"modified":"2021-07-13T18:57:02","modified_gmt":"2021-07-13T16:57:02","slug":"potential-of-a-machine-learning-based-cross-process-control-in-lithium-ion-battery-production","status":"publish","type":"page","link":"https:\/\/cirpicme.org\/index.php\/assembly-battery-production\/potential-of-a-machine-learning-based-cross-process-control-in-lithium-ion-battery-production\/","title":{"rendered":"Potential of a machine learning based cross-process control in lithium-ion battery production"},"content":{"rendered":"\n

by Julia Meiners, Arian Froehlich, Klaus Droeder<\/em><\/em> (Germany)<\/em><\/p>\n\n\n\n

<\/p>\n\n\n\n

Abstract<\/strong><\/p>\n\n\n\n

Lithium-ion battery production consists of numerous successive process steps whose parameters and intermediate product properties are highly interdependent across all process steps. Due to these dependencies, propagating defects lead to high costs and rejects. For the detection and compensation of cross-process defect propagation in the process chain, this paper derives and validates a generic cross-process control architecture and describes the linkage with machine learning methods to analyze the parameter dependencies. For the cross-process control architecture approaches such as a run-to-run control are being considered. As a result, the developed cross-process control can significantly reduce rejects along the process chain in lithium-ion battery production.<\/p>\n\n\n\n

Keywords<\/strong>: Battery production, Cross-process control, Process optimization, Machine learning, Control architecture<\/p>\n\n\n\n

<\/div>\n\n\n\n

Video presentation<\/strong><\/p>\n\n\n\n