Machine Learning for Real-time Parametric CAE Simulations, Optimization and Robustness with CADLM

content image

Date and Time: 20 May, 2020 at:
10:00 AM India (GMT+5:30)
12:30 PM Singapore (GMT+8)
02:30 PM Sydney NSW, Australia (GMT+10)
04:30 PM Wellington, New Zealand(GMT+12)

Duration: 60 Minutes

During the past few decades, there has been tremendous progress in the field of simulations. The maturity of the algorithms, the validation of the software, the speed of the implementations and the scalability to run in parallel. We also have seen many-fold increase in HPC capacity.

The effect of the above is that today all scenarios can be simulated, and we can replace the physical testing altogether. This speeds up the overall development process and saves costs. Because of the much smaller development cycle, we would now like to validate/simulate more number of design iterations.

While the cost to evaluate a few design iterations via simulation remains low, the evaluation of multiple design parameter combinations early in the design stage can lead to non-viable computation times in an industrial context. Machine learning techniques can provide performance predictions instantly by leveraging existing knowledge, which can, in turn, be generated by simulation.

Join us to learn how CADLM’s machine learning platform, ODYSSEE, can provide better, reliable, reproducible engineering judgments from the existing knowledge pool of simulations. It will also cover how Machine Learning can be used in the field of optimizations.

Who should attend?


  • Anyone who does engineering simulations as their profession
  • Analysts who use any kind of non-linear simulations or where the simulation time is longer
  • Analysts who use any kind of simulations which is repetitive in nature
  • All domains, Crash, CFD, MBD, NVH, Durability
  • Project Managers
  • Engineering Managers



Speaker

Kambiz Kayvantash,
CEO, CADLM

Kambiz Kayvantash has a Ph.D. in Numerical methods and optimization of multi-physics problems (1989) as well as an MBA (2005). He has been a Professor/Chair of Automotive Technology at Cranfield University (UK) as well as various other academic positions (Assistant Professor at Essen University (Germany), Professor of optimization, reliability, and robustness at ESILV (France) and Professor of AI/ML/Optimization at ESTP (France)). He has occupied the position of the director of CIC (Cranfield Crash Centre, UK) with experience in Motorsport crash testing. His career covers over 35 years of engineering, numerical analysis, and optimization and has included working with more than 200 OEM's in automotive, aeronautic, manufacturing, etc. in particular in the field of Crash and Safety Optimization. Kambiz has initiated the application of ML and ROM at CADLM, and since the launch of this start-up company has pioneered many innovative and solutions based on combinations of CAE, Machine Learning, and Model reduction. He is currently the Chief Technology Officer at CADLM.

grey box
Upcoming Webinar:

Developing New Products Cost Effectively for Handling & Lifting Equipment

Date: Thursday, 21 May, 2020

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis fringilla enim sit amet justo ultricies varius. Phasellus eget erat rhoncus diam scelerisque auctor nec ac lectus. Vestibulum quis orci magna. Nunc at felis laoreet, porttitor velit a, laoreet velit. Fusce elementum semper massa in tempus. Aenean at dui nunc. Sed.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis fringilla enim sit amet justo ultricies varius. Phasellus eget erat rhoncus diam scelerisque auctor nec ac lectus. Vestibulum quis orci magna. Nunc at felis laoreet, porttitor velit a, laoreet velit. Fusce elementum semper massa in tempus. Aenean at dui nunc. Sed.

grey box

Lorem Ipsum

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Phasellus rutrum justo eu odio finibus, in lobortis ipsum consequat.

grey box

Lorem Ipsum

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Phasellus rutrum justo eu odio finibus, in lobortis ipsum consequat.