IBM, Dallara partner on AI for aerodynamic design

Key Takeaways

• IBM and Dallara partner to advance vehicle design and optimization using AI and quantum computing
• The collaboration combines Dallara's expertise in high-performance vehicle engineering with IBM's leadership in AI for physics and quantum computing
• The partnership aims to accelerate aerodynamic design and simulation workflows
• AI models can speed up computational fluid dynamics (CFD) analyses from hours to seconds
• The collaboration has the potential to cut days of simulation time down to minutes

Introduction to the Partnership

IBM and the Dallara Group have announced a collaboration to advance vehicle design and optimization using AI and explore the use of quantum computing. This partnership brings together Dallara's expertise in high-performance vehicle engineering and IBM's leadership in AI for physics and quantum computing. The goal is to investigate how to accelerate aerodynamic design and open a path to even more advanced simulation workflows.

Dallara's Expertise and Experience

Dallara has over 50 years of experience designing and supplying high-performance vehicles for top racing series, including IndyCar, Formula 2, and Formula 3. The company's breadth of racing programs provides a unique ability to validate simulation results against real-world vehicle performance. Dallara also applies its engineering expertise to high-performance road vehicles and aerospace.

The Role of AI in Aerodynamic Design

Engineers rely heavily on computational fluid dynamics (CFD) to predict aerodynamic forces and optimize vehicle performance. However, these simulations are computationally expensive and can take hours or even weeks to complete. IBM and Dallara are using AI to speed up these workflows without replacing the underlying physics. The AI models leverage Dallara's high-fidelity aerodynamic simulation data and technical expertise to produce compelling early results.

Comparison of Traditional and AI-Based Approaches

Preliminary Results and Future Directions

In one early example, the AI model completed evaluations of multiple configurations of a conceptual Le Mans Prototype 2 (LMP2)-like race car in about 10 seconds, identifying the same optimal design with roughly the same error margins as CFD. Applied to a typical complete set of hundreds of geometry configurations, such a speedup could cut days of simulation time down to minutes. The teams aim to integrate validated measurements of real vehicles in wind tunnels and on the track in future steps.

Bottom Line

The partnership between IBM and Dallara has the potential to revolutionize the field of aerodynamic design and simulation. By leveraging AI and quantum computing, the companies can accelerate the design process, reduce simulation time, and improve overall vehicle performance. With the ability to cut days of simulation time down to minutes, this collaboration can have a significant impact on the automotive and aerospace industries.