Share with your friends
Fee: $80 (~₹ 6500 Ex 18% GST)
Only limited seats to make the course lively and interactive.
Workshop Details:
This workshop aims to provide an introduction to some of the technique of machine learning and its application in computational fluid dynamics (CFD). Machine learning has gained popularity in recent years due to its ability to extract meaningful patterns and trends from large datasets. CFD, on the other hand, is a powerful tool for simulating fluid dynamics and understanding complex flow phenomena.
The workshop will cover the fundamentals of machine learning and CFD, including the different types of machine learning algorithms and their applications in CFD. It will also explore the challenges and limitations of using machine learning in CFD and how to overcome them.
Participants will have the opportunity to learn through a combination of lectures, hands-on exercises, and case studies. They will gain practical experience in applying machine learning techniques to CFD problems and develop an understanding of the benefits and limitations of using machine learning in CFD.
The workshop is designed for researchers, engineers, and students who are interested in exploring the potential of machine learning in CFD and wish to develop their skills in this area. By the end of the workshop, participants will have a solid understanding of the fundamentals of machine learning and its application to CFD, enabling them to apply these techniques to their own research or industrial applications.
Key information:
- Course Instructor: Dr. Azeddine Rachih
Senior CFD Engineer-Eramet
PhD: Toulouse INP, France
MS: CentraleSupélec, France - Date: Sessions over 3 weekends (25-26 March, 1-2 April, 8-9 April 2023)
- Time: 9.00 am UK (2.30 IST)
- Total access to recordings of live sessions: 12 Months
- Computer requirement: Minimum 4 GB RAM and i3 processor
- Software: Guidance on installations will be provided before the workshop
- Mode of class: Zoom video call (Once you make the payment, log in details will be shared.)
More Information
- Introduction to Scikit learn machine learning library
- Deep learning Neural Networks (DNN)
- Convolutional Neural Networks (CNN)
- Linear regression to predict heat transfer coefficient using datasets obtained from OpenFOAM simulations
- Solving transient heat diffusion equation with DNN and CNN,
- Predict the time history of simulation results
- Introduction to Physics Informed Neural Networks (PINN)
- CFD/FEA Engineers who want to learn machine learning to implement in their workflow
- Engineering students pursuing BTech, Mtech or Ph.D. for their academic projects
- Professors/Lecturers who want to teach or guide their students about Machine learning
- Do I get a certificate?
Yes, based on your attendance and completion of tutorials, you will be given the certificate. - Do I need a powerful workstation/computer to learn this course?
No, a normal laptop with 4 or 8GB RAM and a decent processor (i3) is good enough for this course. - What if I don’t understand some portion or need to clarify some doubts?
We will support you through emails and zoom meetings/discussion sessions to clear all doubts and questions - Should I know the programming to learn this course?
No, you don’t need. - Is there any prerequisite?
No
Ratings and Reviews
Kanav Dhawan
• This course builds a very strong foundation for Working Engineers, PhD Researchers who wants to add ML into their portfolio but do not know where to start • It is an interactive course which touches the critical portions of ML theory and then convert that into a workable code in real time • The frequent Quiz between the session keeps you active and competitive for an entire session ★★★★★ 5/5
Aditya Manoj
I found this workshop to be extremely useful primarily because of the hands-on practice sessions. It would be ideal for someone with previous experience in computational methods and programming (preferably in Python but any language would help). One can expect to get a good appreciation for the data-driven paradigm of scientific investigation and how it differs from a physics-based approach.
The workshop offers a comprehensive introduction to the principles of ML. Participants gain a solid grasp of the basics before progressing to engineering problems. As it progresses, problems become more complex, with an emphasis on comparing model performance against traditional methods. PINNS, a growing and interesting area, is also introduced. Python experience is a plus but not mandatory.