Suyog Ghungrad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Suyog Ghungrad has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Azadeh Haghighi
Department of Mechanical and Industrial Engineering, University of Illinois, Chicago, USA
3 shared publications Benjamin Gould
1 shared publication- Benjamin Gould
Applied Materials Division, Argonne National Laboratory, Lemont, USA
1 shared publication Farhad Imani
1 shared publication- Mojtaba Soltanalian
ECE Departement, University of Illinois at Chicago, Chicago, IL, USA
1 shared publication Reihane Arabpoor
1 shared publication
Latest Publications
- 11 March 2026
- Published by Elsevier in Robotics and Computer-Integrated Manufacturing
- Vol. 101
Kinematics-guided multi-task learning for transferable models in robotic manufacturing
- 11 March 2026
- Published by Elsevier in Robotics and Computer-Integrated Manufacturing
- Vol. 101
Kinematics-guided multi-task learning for transferable models in robotic manufacturing
- 27 June 2022
- Published by ASME International
Physics-Informed Artificial Intelligence for Temperature Prediction in Metal Additive Manufacturing: A Comparative Study
Prediction of the temperature history of printed paths in additive manufacturing is crucial towards establishing the process-structure-property relationship. Traditional approaches for predictions such as physics-based simulations are computationally costly and time-consuming, whereas data driven approaches are highly dependent on huge, labeled datasets. Moreover, these labeled datasets are mostly scarce and costly in additive manufacturing owing to its unique application domain (mass customization) and complicated data-gathering stage. Recently, model-based or physics-informed artificial intelligence approaches have shown promising potential in overcoming the existing limitations and challenges faced by purely analytical or data driven approaches. In this work, a novel physics-informed artificial intelligent structure for scenarios with limited data is presented and its performance for temperature prediction in the selective laser melting additive manufacturing process is compared with one of the state-of-the-art data driven approaches, namely long short-term memory (LSTM) neural networks. Temperature data for training and testing was extracted from infrared images of single-track layer-based experiments for Ti64 material with different combinations of process parameters. Compared to LSTM, the proposed approach has higher computational efficiency and achieves better accuracy in limited data scenarios, making it a potential candidate for real-time closed-loop control of the additive manufacturing process under limited and sparse data scenarios. In other words, the proposed model is capable to learn more efficiently under such scenarios in comparison to LSTM model.
- 27 June 2022
- Published by ASME International
Physics-Informed Artificial Intelligence for Temperature Prediction in Metal Additive Manufacturing: A Comparative Study
Prediction of the temperature history of printed paths in additive manufacturing is crucial towards establishing the process-structure-property relationship. Traditional approaches for predictions such as physics-based simulations are computationally costly and time-consuming, whereas data driven approaches are highly dependent on huge, labeled datasets. Moreover, these labeled datasets are mostly scarce and costly in additive manufacturing owing to its unique application domain (mass customization) and complicated data-gathering stage. Recently, model-based or physics-informed artificial intelligence approaches have shown promising potential in overcoming the existing limitations and challenges faced by purely analytical or data driven approaches. In this work, a novel physics-informed artificial intelligent structure for scenarios with limited data is presented and its performance for temperature prediction in the selective laser melting additive manufacturing process is compared with one of the state-of-the-art data driven approaches, namely long short-term memory (LSTM) neural networks. Temperature data for training and testing was extracted from infrared images of single-track layer-based experiments for Ti64 material with different combinations of process parameters. Compared to LSTM, the proposed approach has higher computational efficiency and achieves better accuracy in limited data scenarios, making it a potential candidate for real-time closed-loop control of the additive manufacturing process under limited and sparse data scenarios. In other words, the proposed model is capable to learn more efficiently under such scenarios in comparison to LSTM model.
- 1 August 2021
- Published by Elsevier in Manufacturing Letters
- Vol. 29, 94-98
Model-based deep learning for additive manufacturing: New frontiers and applications
- 1 August 2021
- Published by Elsevier in Manufacturing Letters
- Vol. 29, 94-98
Model-based deep learning for additive manufacturing: New frontiers and applications