Realtime CFD: the advent of AI/ML and operational CFD digital twins

Very rarely in one’s career does something happen which is simultaneously a paradigm shift and a game-changer related to the industry that you’ve devoted most of your career to but recently, I have seen something I thought I would never see in my long career – a viable approach to realtime Computational Fluid Dynamics, CFD, (and indeed realtime CAE, Computer-Aided Engineering) that delivers repeatable engineering-level fidelity suitable for engineering simulation analysts.

Back in 2011, at the NAFEMS World Congress in Boston I presented on the theme of Historical Trends within the CFD industry with ‘Realtime CFD’ being identified as the ultimate ‘Holy Grail of CFD’. I posited then that with realtime, engineering-fidelity CFD, a true democratisation of CFD should occur in every industry for every engineer and plant operator in a world that could, in theory, benefit from CFD engineering simulation.

Gas Turbine Product Lifecycle Digital Twin

Click to enlarge

Since then, this area has still not really been democratised and the CFD world has continued on relatively unchanged until Hexagon acquired CADLM in April 2021. CADLM is a fast-growing Paris-based ‘AI and ML for CAE’ simulation company run by Professor Kambiz Kayvantash. What Hexagon has done is to quickly take CADLM’s tried-and-proven general-purpose AI/ML algorithms for CAE embedded within their product suite called ODYSSEE CAE, and, along with a recently released product called ODYSSEE A-EYE extended even more into AI applications. These products both include and extend beyond trusted design space techniques like design of experiment (DoE), process integration and design optimisation (PIDO), and design space optimisation (DSO) that all have their place in CFD / CAE simulation workflows today; but they are well over ten-year-old methodologies and technologies now. The diagram below shows the way modern AI/ML algorithms can be viewed in the context of this spectrum of DoE / PIDO / DSO tools and you can read more on the theory behind ODYSSEE in an AI/ML whitepaper released by Kambiz in 2020. Indeed, ODYSSEE CAE includes all capabilities to the left of machine learning on the diagram, as well as new and exciting capabilities and algorithms tailored for the CAE and manufacturing worlds. ODYSSEE A-Eye can fuse data from different sources such as virtual CAE simulation, real world scanning data, and even photos and video images; plus financial and costing data can even have ML and AI analysis applied in order to derive actionable outcomes very quickly! You can read more of how AI/ML has impacted metal forming simulation and costing inside Hexagon in this recent FormingSuite magazine article by my Canadian colleague, Mike Lee.

Click to enlarge

ODYSSEE can actually measure the complexity of a model, a system or a process and uses a concept related to entropy in chemistry for robust optimisation of capabilities such as cost engineering in ODYSSEE A-Eye. Reducing complexity equates to increasing robustness in CAE models of any other process. ODYSSEE software can even fuse multiphysics ROM (reduced order model) data from different CAE solver types that typically would require very different timescales to converge due to the numerical intensity of their mathematical techniques – 3D FEA structures, 1D MBD, 3D FV CFD – in near real-time. This is a game-changer for the CFD and CAE industries in my opinion by virtue of unleashing new levels of productivity without losing quality and opens the prospect of operational digital twins that can democratise trained CFD and CAE simulations to non-experts such as plant operators. Hence, tens of millions of engineers and plant operators, and even the general public, could benefit from realtime CFD and CAE simulation!

What has amazed me the most is the many customer examples inside Hexagon Design & Engineering where 3D CFD simulation data (and other 3D point physics simulation types like structures, acoustics, crash, materials, multibody dynamics…) trained inside ODYSSEE CAE has led to interpolated and optimised predictions in seconds rather than minutes, hours or days (and all do-able on a laptop!) This has involved 2, 3 and sometimes even higher orders of magnitude reductions of overall computational time to achieve these outputs. It has produced major productivity benefits for companies such as Yamaha in Japan and Stellantis in Europe – check out our recent Hexagon Design & Engineering Live 2021 conference AI/ML track for real-world examples from companies such as Ford, Faurecia, Autoliv, Mahindra and Eta. This approach has been proven in industries as diverse as automotive, aerospace, electronics, chemical process and the built environment.

Let me briefly outline two CFD-related examples, one from Europe and one from Japan, involving Cradle CFD from Hexagon, technically the most multiphysics-focused CFD code in the world, and ODYSSEE CAE:

Realtime operational CFD digital twin of Hexagon’s Archidona solar farm

In this example, Hexagon created a 3D Cradle CFD model of our new Hexagon | R-evolution subsidiary’s Archidona Solar Farm in SW Spain  by capturing Hexagon’s Leica BLK247 real world scanned data of the actual as-installed solar panel tracks on our 8 MWp solar farm. We took this real data into a Cradle CFD geometrical model of the plant and incorporated 3D geo-scanning data for the landscape around Archidona so we could fuse the real and virtual data. We then carried out a series of meteorological simulations for the solar plant, and solar panels oriented at different angles to the vertical on a rotating single axis to represent their typical movement. Each full 3D Cradle CFD simulation took 1 hour to solve in the 3D Cradle CFD model on a large desktop machine but once a full CFD digital twin of the solar farm and panels was created inside ODYSSEE CAE, all sorts of “what if..?” questions could be determined for optimal operation of the solar plant on a laptop; typically only taking 2s per simulation.

This approach now allows us to couple real-world weather forecast data to next-day solar farm operations in an actionable way to optimise electricity generation with our thermo-fluid operational CFD digital twin of the site. It can therefore be directly linked to actions that maximise power generation efficiency on site and the profitability of the site. Ultimately, we have a powerful tool to educate solar farm operators onsite with real-time augmented reality CFD visualisations that they can hold up in front of themselves to understand what is happening in a thermo-fluid sense. This was done by coupling Hexagon’s powerful XALT dashboarding technologies to Cradle CFD simulation predictions to provide a powerful AR visualisation of the solar plant in real time on an iPad or on an iPhone with the upcoming Cradle CFD 2022 product release this month. This fusing of real world as-installed and as-operated solar farm scanned data and our virtual Cradle CFD prediction data in a CFD digital twin is, we believe, a world first and a new Smart Digital Reality that gives Hexagon a unique means of optimising the performance and outputs of our solar farm on a daily basis.

Click to enlarge – Cradle CFD’s Operational Digital Twin flow prediction at Hexagon’s Archidona Solar Farm in Augmented Reality iPad viewer for the Solar Farm operators to use

Click to enlarge – CFD Digital Twin of Hexagon’s Spanish Solar Farm – 3d Cradle CFD Simulations feeding 0d AI/ML ODYSSEE CAE ROM to get real-time weather predictions into operational performance

Optimising HVAC duct location and flowrate inside a restaurant using CFD

In this second example, we were investigating the optimal location in a restaurant to position HVAC air flow vents to ensure good mixing – especially now in the era of COVID-19 – plus we wanted to determine the optimal duct vent flow rate. This is inherently a transient non-linear CFD simulation, and the complete 3D simulation took 40 minutes to solve on a 4-core desktop machine for one operating condition. A series of bounding 3D CFD simulations were then run and used to train ODYSSEE CAE for this application. The 0D ODYSSEE ROM model interpolated the CFD predictions to provide almost the same level of fidelity as the 3D CFD simulations in just 30 seconds for other conditions and helped to determine the optimum air flow rate for this restaurant, table layout and vent scenario.

Click to enlarge

See another demonstration below of the power of Cradle CFD and XALT in this incredible video showing CFD predictions of HVAC flows in the Hexagon Japan Office in Tokyo that are viewable on an iPad:

Concluding remarks

If you want to know more about all of these technologies and have a CFD or CAE application that could benefit from being sped up several orders of magnitude, while improving your or your company’s CFD / CAE analyst productivity, then call your local Hexagon office and ask more about the ODYSSEE suite of software and trial it yourself and see if we can do your application in near real-time with AI/ML and Cradle CFD for instance! The same applies for any of the Hexagon multiphysics simulation types mentioned in this article and also co-simulations between the different point physics types. All can be handled inside the ODYSSEE suite. I foresee a brave new world of CFD ahead of us all especially related to smart manufacturing that fuses real and virtual data in a seamless way and I believe that democratisation of CFD is definitely within our grasp.


  • Keith Hanna

    Dr. Keith Hanna is MSC Software’s Vice President of Marketing and has nearly 30 years of technical and marketing experience in the CFD, CAE, EDA and PLM industries. He holds BSc and PhD engineering degrees from the University of Birmingham, England, and is a respected commentator on the CFD/CAE industry, as well as a pioneer in the use of CFD in sport.

  • Join our HxGN LIVE Events Worldwide

    Hexagon hosts exciting HxGN LIVE events around the globe! Experience our technology innovations in a location near you.

  • Recent Posts