Computational Discovery of Energy-Efficient Heat Treatment for Microstructure Design using Deep Reinforcement Learning

no code implementations • 22 Sep 2022 • Jaber R. Mianroodi, Nima H. Siboni, Dierk Raabe

In particular, the agent is capable of controlling the temperature to reach the desired microstructure starting from a variety of initial conditions.

Reinforcement Learning (RL)

Accelerating phase-field-based simulation via machine learning

no code implementations • 4 May 2022 • Iman Peivaste, Nima H. Siboni, Ghasem Alahyarizadeh, Reza Ghaderi, Bob Svendsen, Dierk Raabe, Jaber R. Mianroodi

Training input for this network is obtained from the results of the numerical solution of initial-boundary-value problems (IBVPs) based on the Fan-Chen model for grain microstructure evolution.

BIG-bench Machine Learning

Lossless Multi-Scale Constitutive Elastic Relations with Artificial Intelligence

no code implementations • 5 Aug 2021 • Jaber Rezaei Mianroodi, Shahed Rezaei, Nima H. Siboni, Bai-Xiang Xu, Dierk Raabe

To demonstrate the accuracy and the efficiency of the trained CNN model, a Finite Element Method (FEM) based result of an elastically deformed nanoporous beam equipped with the CNN as constitutive law is compared with that by a full atomistic simulation.

Machine-learning-enhanced time-of-flight mass spectrometry analysis

no code implementations • 2 Oct 2020 • Ye Wei, Rama Srinivas Varanasi, Torsten Schwarz, Leonie Gomell, Huan Zhao, David J. Larson, Binhan Sun, Geng Liu, Hao Chen, Dierk Raabe, Baptiste Gault

Mass spectrometry is a widespread approach to work out what are the constituents of a material.

BIG-bench Machine Learning