Hands-on machine learning in additive manufacturing that everyone can use
HTML-код
- Опубликовано: 28 июл 2024
- 00:00:00 Introduction
00:01:22 Metal additive manufacturing and its uniqueness and opportunities
00:08:08 Why we need machine learning?
00:10:03 Different types of machine learning in additive manufacturing
00:12:25 Control of grain size using machine learning
00:14:12 Control of residual stresses using machine learning
00:20:39 Control of lack of fusion defects using machine learning
00:27:08 Control of solidification cracking using machine learning
00:30:55 How to use an open-source machine learning package WEKA
00:33:38 Worked-out example 1
00:42:43 Worked-out example 2
00:53:54 Practice problem
00:55:45 Important considerations before using machine learning
00:59:07 Takeaways
01:01:39 Quantum computing: a big opportunity
The talk is presented by Dr. Tuhin Mukherjee at a short-term training program on the Application of Soft-computing Techniques and Numerical Modeling in “Additive Manufacturing and Materials Processing” (A2MP 2022) at Sardar Vallabhbhai National Institute of Technology, Surat, India on 19th December 2022.
Unlike welding and casting technologies that matured largely through many decades of trial and error testing, additive manufacturing is uniquely positioned to benefit from the powerful tools of data science. Experiments supported by machine learning can control structure, properties, and defects. The availability of open-source computer programs has enabled everyone to apply machine learning to solve important issues in additive manufacturing. Research in the virtual world using digital tools has the potential to make the world a more inclusive and welcoming place for all.
#additivemanufacturing #3dprinting #machinelearning #modeling #training #seminar #manufacturing #SVNIT #mechanicalengineering #materials #materialsprocessing Наука
Thank you for the insightful talk, Dr. Mukherjee.
Great talk, really liked the worked examples. Thanks!
Very great discussion
Great talk
Plz provide the dataset
Great job dear