Machine learning offers a high potential for the prediction of manufacturing lead times. In practical operations the lack of defined processes and high-quality input data are a major obstacle for the use of machine learning. The method of process mining creates a better transparency of such workflows and enriches related data. This paper develops a method, which combines the benefits of machine learning and process mining with the goal of high accuracy lead time prediction. The method is focused on high variance processes and verified with a case study containing real industrial data from heavy engine assembly processes.
CITATION STYLE
Welsing, M., Maetschke, J., Thomas, K., Gützlaff, A., Schuh, G., & Meusert, S. (2021). Combining Process Mining and Machine Learning for Lead Time Prediction in High Variance Processes. In Lecture Notes in Production Engineering (Vol. Part F1136, pp. 528–537). Springer Nature. https://doi.org/10.1007/978-3-662-62138-7_53
Mendeley helps you to discover research relevant for your work.