Lutz B, Kißkalt D, Regulin D, Franke J (2020)
Publication Type: Journal article
Publication year: 2020
Book Volume: 93
Pages Range: 1382-1387
Conference Proceedings Title: Procedia CIRP
Journal Issue: 53rd CIRP Conference on Manufacturing Systems 2020
URI: https://www.sciencedirect.com/science/article/pii/S2212827120307344?via=ihub
DOI: 10.1016/j.procir.2020.04.100
Open Access Link: https://www.sciencedirect.com/science/article/pii/S2212827120307344?via=ihub
A significant difference in the machinability of hard-to-machine materials can be observed among different batches of the same specified material. Thus, for cost-efficient machining, the ideal point of operation may vary for each batch. To investigate this, more than 1000 experiments at different cutting conditions with ten material batches are carried out. This data is used to train a support vector machine, capable of predicting a machinability index based on the material batch and the cutting conditions. The derived model is implemented as a cloud-based service, enabling its integration into a smart manufacturing assistant. It can be used for process optimization by predicting the machinability for given situations and, thus, finding the point of operation with favorable machinability.
APA:
Lutz, B., Kißkalt, D., Regulin, D., & Franke, J. (2020). AI-based approach for predicting the machinability under consideration of material batch deviations in turning processes. Procedia CIRP, 93(53rd CIRP Conference on Manufacturing Systems 2020), 1382-1387. https://doi.org/10.1016/j.procir.2020.04.100
MLA:
Lutz, Benjamin, et al. "AI-based approach for predicting the machinability under consideration of material batch deviations in turning processes." Procedia CIRP 93.53rd CIRP Conference on Manufacturing Systems 2020 (2020): 1382-1387.
BibTeX: Download