Additive manufacturing and welding research. We use the emerging tools of mechanistic modeling and machine learning to improve additive manufacturing and welding without expensive and time-consuming trial-and-error testing.
Sir, I truly appreciate the detailed explanations of these concepts. I have read several of your papers and find your work inspiring. I hope to meet you in person one day and receive your blessings. Thank you!
This is amazing! Love the channel. Is the semi-analytical heat transfer model that you are employing available by any chance? I am using FEA but it can indeed be slow for real geometries. Regards :)
Dear Professor DebRoy, Thank you and your outstanding research group for sharing this valuable video which clearly indicates the importance of physics-informed machine learning. As a researcher, I am very interested in utilizing this trick to fabricate defect-free parts by reducing the needed variables. Sincerely yours, Reza Motallebi
I am so happy to hear that you liked it. This video is mainly made by Barnali and Tuhin. We are doing well. I also saw the short video that you created using your iPhone while riding a motorcycle. When you have time and energy, please do write to me. All the best, Tarasankar DebRoy
Dear Professor, Thank you for this short but clear video about the importance of reducing the variables for machine learning. It will surely add value to my research work.
The procedure works because the behavior of many complex engineering systems is often accurately described by a group of variables rather than individual variables. An example is the well-studied problem of the flow of fluid in a pipe. In principle, four variables, i.e., the pipe diameter, average fluid velocity, and the density and viscosity of the fluid can predict if the flow is laminar or turbulent. However, it is well accepted that the nature of the flow, laminar or turbulent, can be predicted by only one variable, the Reynolds number. The reduction in the number of variables can make many problems tractable. All the best in your research. T. DebRoy
