Presentation Information
[2F03]Machine Learning Molecular Dynamics Insights into Carbon Detachment from Diamond Tools in Iron Cutting
*Bao Anh Nguyen Trinh1, John Isaac Guinto Enriquez1, Harry Handoko Halim1, Hiroyuki Ogiwara2, Takahiro Yamasaki2, Masato Michiuchi2, Tamio Oguchi3, Yoshitada Morikawa1 (1. Graduate School of Engineering, The University of Osaka, 2. Sumitomo Electric Industries, Ltd, 3. Center for Spintronics Research Network, The University of Osaka)
Diamond tools are widely used in ultra-precision machining due to their exceptional hardness and surface finish quality. However, rapid wear occurs when cutting ferrous metals like iron, mainly due to thermo-chemical reactions at the Fe–C interface. To investigate these atomistic wear mechanisms, we employed machine learning molecular dynamics (ML-MD) simulations using an interatomic potential trained on ~6,000 structures, achieving RMSEs of ~130 meV/Å for forces and ~4 meV/atom for energies. The model accurately captures properties of iron, carbon, and Fe–C systems. Cutting simulations with over 8,000 atoms and 1 fs timesteps were performed across different diamond surfaces and temperatures. Results show higher wear when the diamond surface acts as the clearance face. Lower temperatures reduce wear rates, and the (111) surface shows the best resistance. Though early wear rates exceed experimental values, longer simulations are expected to improve agreement. ML-MD provides key insights into wear and tool design for ferrous machining.