Training-Validation-Testing Dataset for "Real-Time Prediction of Thermal History and Hardness in Laser Powder Bed Fusion Using Deep Learning"

This repository provides a comprehensive dataset for the development and evaluation of deep learning models aimed at real-time prediction of thermal history and resulting hardness in Laser Powder Bed Fusion (PBF-LB). The dataset comprises high-resolution, spatiotemporal thermal field data alongside corresponding hardness values, generated under varying process conditions. In addition, it includes engineered input features such as laser parameters, geometric descriptors, and distance-based measures to capture the local process state.
The dataset was created with the previously published multiscale FEM simulation model for the quenched and tempered steel 42CrMo4 / AISI 4140 (https://doi.org/10.1080/17452759.2023.2271455).

Full-text publication:
Code repository: https://doi.org/10.35097/dg39f4p0wxqdnfxy
Trained model dataset: https://doi.org/10.35097/37da9d66y4t27q55
Full-text publication for the FEM simulation model: https://doi.org/10.1080/17452759.2023.2271455