TY - JOUR A1 - Epishin, A. I. A1 - Petrushin, N. V. A1 - Svetlov, I. L. A1 - Nolze, Gert T1 - Model for Forecasting Temperature Dependence of γ/γ' Misfit in Heat-Resistant Nickel Alloys N2 - An analytical model for forecasting the temperature dependence of γ/γ' misfit in heat-resistant nickel alloys is proposed. The model accounts for the concentration dependences of the periods of crystalline lattices of the γ and γ' phases (Vegard law), thermal expansion of the γ and γ' lattices, and dissolution of the γ' phase at high temperatures. Adequacy of calculations of misfit is confirmed by comparison with the results of measurements using methods of X-ray and neutron diffraction. The model is applied for development of a nickel alloy with positive misfit. KW - Heat-resistant nickel alloys KW - Dimensional mismatch of crystalline lattice periods (misfit) KW - Microstructure evolution PY - 2022 DO - https://doi.org/10.1134/S2075113322010105 SN - 2075-1133 VL - 13 IS - 1 SP - 7 EP - 16 PB - Springer AN - OPUS4-54379 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Elfetni, Seif A1 - Darvishi Kamachali, Reza T1 - PINNs-MPF: A Physics-Informed Neural Network framework for Multi-Phase-Field simulation of interface dynamics N2 - We present PINNs-MPF framework, an application of Physics-Informed Neural Networks (PINNs) to handle Multi-Phase-Field (MPF) simulations of microstructure evolution. A combination of optimization techniques within PINNs and in direct relation to MPF method are extended and adapted. The numerical resolution is realized through a multi-variable time-series problem by using fully discrete resolution. Within each interval, space, time, and phases/grains are treated separately, constituting discrete subdomains. PINNs-MPF is equipped with an extended multi-networking (parallelization) concept to subdivide the simulation domain into multiple batches, with each batch associated with an independent NN trained to predict the solution. To ensure continuity across the spatio-temporal-phasic subdomains, a Master NN efficiently is to handle interactions among the multiple networks and facilitates the transfer of learning. A pyramidal training approach is proposed to the PINN community as a dual-impact method: to facilitate the initialization of training when dealing with multiple networks, and to unify the solution through an extended transfer of learning. Furthermore, a comprehensive approach is adopted to specifically focus the attention on the interfacial regions through a dynamic meshing process, significantly simplifying the tuning of hyper-parameters, serving as a key concept for addressing MPF problems using machine learning. We perform a set of systematic simulations that benchmark foundational aspects of MPF simulations, i.e., the curvature-driven dynamics of a diffuse interface, in the presence and absence of an external driving force, and the evolution and equilibrium of a triple junction. The proposed PINNs-MPF framework successfully reproduces benchmark tests with high fidelity and Mean Squared Error (MSE) loss values ranging from 10^−6 to 10^−4 compared to ground truth solutions. KW - Machine learning KW - PINNs KW - Phase-field method KW - Microstructure evolution KW - Parallel training KW - Neural networks PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-629740 DO - https://doi.org/10.1016/j.enganabound.2025.106200 SN - 0955-7997 VL - 176 SP - 1 EP - 22 PB - Elsevier CY - Amsterdam AN - OPUS4-62974 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -