Machine Learning and Artificial Intelligence (AI) for CAE
Creating real-time simulation models
ODYSSEE is an innovative new state-of-the-art Machine Learning based software package for real-time parametric design and optimization. CADLM, based in Paris, has been a pioneer in implementing Artificial Intelligence (Al) technology in CAE. MSC Software has selected their solutions to add to the MSC One product portfolio, globally.
With the ODYSSEE software suite you are able to develop predictive, real-time CAE simulations based on Machine Learning techniques using only a fraction of the number of
datasets required for traditional response surface methods.
"With ODYSSEE we could significantly reduce the DOE-Runs by a factor of 10 while retaining the quality of results. The always upcoming answer of different mount setups can now be answered within seconds, instead of performing new exhausting simulations. We strongly believe in the great potential Of ODYSSEE to boost the engineer's comprehension of complex nonlinear mechanical systems."
Dr. Stefan Uhler, Audi
A remarkable feature of this technology is the reduced number of simulations or tests required to predict new result sets for different input parameter values. In one case study, Audi showed how they reduced the number of DOE simulations by a factor of 10 while retaining the quality of their results. With the resulting models, they can now answer questions about different mounting setups in seconds, rather than performing new time consuming simulations.
In another example, images of tyre thread patterns were linked to known sound spectrums it will produce at various speeds. Using machine learning techniques, the sound spectrum of a new thread pattern can be predicted almost instantly without utilising costly and time consuming tests or simulations.
In a case study from Autoliv, detailed crash simulations were executed in only 3% of the time required for a detailed crash simulation, with the main difference being that the 47hour FEM simulations were run on a 32 core cluster while the ODYSSEE simulations were run on a normal 4 core laptop. With only 6 complete analyses available, a Reduced Order Model (ROM) was obtained, including the 3D simulation results of a passenger dummy impacting the deployed airbag.
ODYSSEE doesn't limit the types of simulations, tests or data types that can be processed to produce new datasets in a fraction of the time. In this example from PSA Group, a vibro acoustic analysis result from MSC Nastran with a new parameter set was predicted accurately from a created Reduced Order Model (ROM).
Multi-physics type simulations are also excellent candidates for Reduced Order Modelling due to their complexity and time consuming simulations, especially when certain target behaviours are sought. In this example, a co-simulation model of a pump with a flexible valve was used to find the correct membrane thickness to obtain the desired flow characteristics.
"At AUTOLIV we are concerned with safety of real humans (and not only dummies). This requires a yet challenging computing effort for evaluation of our safety solutions. CADLM's ODYSSEE.Lunar software is a real breakthrough and provides a very promising perspective in order to reduce computing time drastically and optimize our designs"
- Bengt Pipkorn, Director Simulation and Active Structures, Autoliv Research
The Toyota Motor Corporation has been using ODYSSEE since October 2016 with great success across a variety of simulation types from crash testing to structural analysis and CFD (Computational Fluid Dynamics). Not only did it reduce the cost and time of crash test modelling, but it provided them with new perspectives in validation and exploitation of parametric models.
Other applications
But the applicability and utilization of the ODYSSEE products are not limited to CAE either. In high volume manufacturing facilities, ODYSSEE can be deployed to assist with real-time quality control on produced items by using imagery and a reference set to identify known faults. In this example, instead of using limited physical testing of electronic components, photographic imagery is used to identify defects on every product.
But apart from the CAE and manufactuirng environments, the medical industry has also found use for ML and AI. In this example from the INRS, MRI scans of a hand and AI was used to construct the most accurate and representative anatomical details of a hand in CAD format. This opened the door for the future to have real-time dynamic models of the hand for teaching and research purposes.
The medical industry has also seen the value in Machine Learning from doctors' diagnoses to assist in large scale screening of patients when the Covid-19 pandemic hit. With limited resources and availability of specialists, Machine Learning was employed to screen patients instantly and use the specialists on borderline or special cases.
The question isn't anymore if you can utilise ML and AI in your environment, it's just a matter of seeing the opportunities of what real-time simulation and analysis can do for you.
Don't ever risk your career by using cracked software!
THE EXCUSES: I only used it for my studies, I only wanted to evaluate the software, I didn't use if for commercial purposes, I only installed it, but never used it... Unfortunately, no reason holds up in court for the possession of stolen goods.
THE FINE? The full commercial purchase price of the software (for everything you had access to, whether or not it was even used!)
Students (under- or post-graduate) also has no recourse since they can get access to free legal student versions, or the full commercial versions through their respective universities. If you wish to evaluate any software or module that you do not have access to, please contact us, we will gladly arrange for evaluation licenses, even emergency licenses.
There is just no reason to access illegal software.
ID used to identify users for 24 hours after last activity
24 hours
_gat
Used to monitor number of Google Analytics server requests when using Google Tag Manager
1 minute
_gac_
Contains information related to marketing campaigns of the user. These are shared with Google AdWords / Google Ads when the Google Ads and Google Analytics accounts are linked together.
90 days
__utma
ID used to identify users and sessions
2 years after last activity
__utmt
Used to monitor number of Google Analytics server requests
10 minutes
__utmb
Used to distinguish new sessions and visits. This cookie is set when the GA.js javascript library is loaded and there is no existing __utmb cookie. The cookie is updated every time data is sent to the Google Analytics server.
30 minutes after last activity
__utmc
Used only with old Urchin versions of Google Analytics and not with GA.js. Was used to distinguish between new sessions and visits at the end of a session.
End of session (browser)
__utmz
Contains information about the traffic source or campaign that directed user to the website. The cookie is set when the GA.js javascript is loaded and updated when data is sent to the Google Anaytics server
6 months after last activity
__utmv
Contains custom information set by the web developer via the _setCustomVar method in Google Analytics. This cookie is updated every time new data is sent to the Google Analytics server.
2 years after last activity
__utmx
Used to determine whether a user is included in an A / B or Multivariate test.
18 months
_ga
ID used to identify users
2 years
_gali
Used by Google Analytics to determine which links on a page are being clicked
30 seconds
_ga_
ID used to identify users
2 years
Marketing cookies are used to follow visitors to websites. The intention is to show ads that are relevant and engaging to the individual user.
Google Maps is a web mapping service providing satellite imagery, real-time navigation, and location-based information.