Integration of physics-based data in deep learning model training for predicting the effect of sulfur content in the directed energy deposition process
Journal Title: International Journal of AI for Materials and Design - Year 2024, Vol 1, Issue 1
Abstract
The training of a machine learning model solely on experimental data, encompassing both pre- and post-process information, can reveal the general relationship of the directed energy deposition process. However, models trained in this manner encounter limitations in capturing critical in-process information occurring during deposition. This paper details the training of a deep learning model through the integration of in-process physics-based simulation information and a pre-process experiment dataset. The sulfur content of stainless steel 316L was selected as critical in-process information affecting the final track geometry and was captured using computational fluid dynamics simulation of a single-track deposition process, which cannot be captured accurately through experimentation. The physics-based simulation dataset was generated by obtaining the contour of deposition and dilution of the solidified track cross-section. The experiment was conducted using central composite design, and data augmentation was achieved through curve fitting using a response surface methodology regression model. Statistical analysis assessing the quality of simulation and experiment data was conducted. Among six baseline models, a deep learning model with a specified training sequence of experiment and simulation data, denoted as DL-AugExp-Sim-Exp, exhibited the best-performing R2 and root mean square error prediction accuracy for cross-section track shape. Notably, deep learning models trained with both experiment and simulation information demonstrated a lower R2 value compared to models trained solely with experiment data, revealing a tradeoff between R2 value and additional prediction capability. In summary, in this study, the integration of a physics-based simulation dataset demonstrated the additional prediction capability concerning the effect of sulfur content on track geometry.
Authors and Affiliations
Stanley Jian Liang Wong|1 Department of Singapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Republic of Singapore 2 Makino Asia Pte Ltd, Singapore, Republic of Singapore, Chengxi Chen|1 Department of Singapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Republic of Singapore 2 Makino Asia Pte Ltd, Singapore, Republic of Singapore, Eddie Zhi’En Tan| Makino Asia Pte Ltd, Singapore, Republic of Singapore , Hua Li|Department of Singapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Republic of Singapore
Keywords
Related Articles
- EP ID EP767343
- DOI 10.36922/ijamd.2355
- Views 16
- Downloads 0
A unified industrial large knowledge model framework in Industry 4.0 and smart manufacturing
The recent emergence of large language models (LLMs) demonstrates the potential for artificial general intelligence, revealing new opportunities in Industry 4.0 and smart manufacturing. However, a notable gap exists in a...
Integration of physics-based data in deep learning model training for predicting the effect of sulfur content in the directed energy deposition process
The training of a machine learning model solely on experimental data, encompassing both pre- and post-process information, can reveal the general relationship of the directed energy deposition process. However, models tr...
Machine learning applications for quality improvement in laser powder bed fusion: A state-of-the-art review
As one of the most popular additive manufacturing methods, laser powder bed fusion (L-PBF) builds 3D components with complex geometries layer by layer using alloy powders. This technique has found widespread adoption in...
Joint angle prediction for a cable-driven gripper with variable joint stiffness through numerical modeling and machine learning
Soft grippers in automation, particularly those with variable joint stiffness, offer promising possibilities for precise manipulation tasks. However, accurately predicting finger joint bending angles in this field poses...
Machine learning-driven prediction of gel fraction in conductive gelatin methacryloyl hydrogels
Gelatin methacryloyl (GelMA) hydrogels, combined with conductive fillers like Poly(3,4-ethylenedioxythiophene) polystyrene sulfonate (PEDOT:SPSS), present significant promise for tissue regeneration due to their biocompa...