Machining is a commonly used process in variety of industries such as automotive, aerospace, machinery, energy etc.
For increased performance, predictive methods based on process models must be used to determine important factors
such as cutting forces, temperatures, vibrations etc. to select optimal operational conditions.
Analytical and numerical predictive models need fundamental data on machining characteristics of the work material such as
shear yield stress, friction with the tool and shear angle which can be obtained from cutting tests.
The objective of this project is to predict those machining characteristics from basic properties of metals using
"physics informed machine learning (PIML)" approach where simulated values will be combined with experimental data
to increase accuracy of the models.
The students are expected to have fundamental knowledge on materials, mechanics and manufacturing processes.
The experiments will be carried out in Manufacturing Research Laboratory on Sabancı University Campus.
Term:
2024-2025 Fall
Faculty Department of Project Supervisor:
Faculty of Engineering and Natural Sciences
Number of Students:
3
Related Areas of Project:
Materials Science ve Nano Engineering
Mechatronics Engineering
Industrial Engineering