Will AI-Based Simulation Hit a Home Run?

At the 2024 NAFEMS Americas conference in Louisville, KY, in July, simulation users, software providers, integrators, and academics converged to discuss the latest developments in engineering simulation – and as expected, the use of artificial intelligence (AI) in simulation was a hot topic during the conference. 

NAFEMS is the international association for engineering modeling analysis and simulation, with chapters around the globe. To kick off the conference, Tim Morris, NAFEMS CEO, outlined the agenda for the three-day event, and highlighted some of the major developments in the industry, with AI at the top of the list.

“AI is particularly relevant to our world in simulation,” he said. “We are learning a lot about how it can be applied in our environments.” Other notable developments included the growth of systems simulation and model-based systems engineering; increased access to high-performance computing; CAE vendor consolidation; and simulation certification efforts.

Of those, however, AI generated a lot of buzz at the show, including several standing-room only sessions as part of an AI-focused conference track. Keynote speaker Anthony Petrella, director of the Computational Biomechanics Group at the Colorado School of MINES, was asked about AI in the context of discussion of the future of engineering education.

“Using AI is something that every student is doing,” he said. “I think we should avoid viewing it as a threat. We should view it as a tool that we should leverage to its maximum extent. We are all still mid-stream in discovering the right ways to do that.”

Petrella described higher-ed efforts to increase training in simulation and modeling and to structure coursework that helps prepare engineers for the market. He said there is a demand for credentials that are more than a bachelor's degree, but less than a masters, and a shift to job-related competencies. He also said there is demand for more adaptability and customization in higher ed for engineering.

NAFEMS stalwart Alice Popescu-Gatlan, recently retired from John Deere where she spearheaded simulation efforts for roughly 30 years, provided the second day keynote. She described the evolution of simulation at John Deere and across the industry over the past several decades, and said that engineers should consider how their work affects the world.

“Think about the power you have with simulation and analysis to influence not just the products that your company puts out, but also the lives of people at large,” she said.

She also emphasized the importance of harnessing AI to increase the value of simulation. “I think we are at the point where if we don’t have enough data, let's make it up. Let's use AI. Let's just dream bigger because now we know how to, and we have more tools to do so.”

Attendees were also treated to a tour of the nearby Louisville Slugger bat manufacturing facility. The tour kicked off with a presentation from Matt Bynum of parent company Hillerich & Bradsby, who described how the company uses motion capture and SOLIDWORKS software to custom design bats for major league baseball players. By manipulating the center of gravity and what he called the moment of inertia of the bat, the company can redesign and mill a sample bat for a player in less than 30 minutes. (SOLIDWORKS partner Goengineer implemented the CAD portion of the solution.)

The majority of the major software vendors in attendance have already announced AI-based simulation tools, including Ansys, Altair, Siemens Digital Industries Software, and Dassault Systèmes.

Ansys and NVIDIA presented a workshop titled Leveraging AI to Boost Computation-Intensive Simulations that explored how AI is applied to engineering simulations across industries, and the challenges posed by high computational demands. 

Mustafa Kaddoura, Senior Application Engineer at Ansys, said that the AI models can be efficiently trained on NVIDIA GPUs with large datasets to provide faster insights to engineers. 

“AI can be very powerful for repeated simulations where there are lots of design iterations,” Kaddoura said. 

However, because the application of AI in these workflows is relatively new, most customers will need to investigate the size of the data set needed to train these models for their specific use cases. Kaddoura said Ansys recommends testing the model against an actual Design of Experiments (DOE) to ensure accuracy. 

You can learn more about the NAFEMS Americas conference here.

More Altair Coverage

More NAFEMS Coverage