The potential of AI in automotive simulation
As artificial intelligence (AI) continues to advance in development and capability, industries of all kinds are looking for ways to leverage the evolving technology for their needs. This includes the automotive industry. While the presence of AI in automotive engineering processes is still small, it is growing, and its ability to learn rapidly from historical data makes it valuable for a multitude of applications.
One such application is simulation. As vehicles become more and more complex due to the integration of new technologies, the burdens placed on simulation software and processes increase. A recent article by Royston Jones, Global Head of Automotive and Transportation for Siemens Digital Industries Software, highlights how despite its small footprint within the current automotive industry, AI has great potential to manage this complexity in simulations and accelerate workflows.
Why automotive simulation?
Simulation has been an invaluable tool for the automotive industry. It enables engineers to test new component and vehicle designs in a digital environment, reducing reliance on physical prototypes and thereby decreasing the time and costs required to test them in the real world. Simulation also grants insights earlier in the design process, giving engineers and designers more time to optimize designs based on simulation results.
According to Royston, however, the ever-increasing complexity of today’s automotive products is placing new strains and simulation and related processes. For a long time, vehicles were traditionally built around purely mechanical systems. Today’s vehicles are very different. Thanks to electrification and the integration of software, vehicles are incorporating new batteries, electronics, thermal systems, sensors and more, imposing new multi-physics requirements that simulations must account for.
Simulations for scenarios such as external aerodynamics or crashworthiness tests were already complex enough. Now they have to contend with new vehicle systems that add even more considerations, as well as immense amounts of additional data engineers must sort through and interpret, increasing the risk of bottlenecks in their workflows.
Simulation enhanced with AI
These are precisely the kinds of problems Royston says AI can solve. Although the extents of its capabilities are still being explored, one thing AI has proven to be good at is recognizing data patterns. This can be especially helpful for automotive simulations that deal with complex geometry or generate immense amounts of data, such as crash tests.
AI can take all the data generated by these tests and identify the most relevant data for the needs of engineers and designers. Then it can cluster the data into distinct types of behavior, finding the key highlights from the data so nobody needs to spend days sifting through the data to make the same conclusions. Not only does this benefit engineers and speed up workflows, it also trains the AI to handle these tasks better, enabling it to deal with even more complex physics and simulations in the future.
AI and the future of automotive
Automating tasks like data collection and analysis is just the beginning. Royston goes on to describe how it can be used as copilots and knowledge banks more deeply integrated in simulation software and augment engineers’ expertise. The AI can educate itself, gaining the knowledge required to become valuable assistants to users of the software, as well as help onboard new users who are unfamiliar with it. This can be especially useful as more experienced engineers continue to retire from the industry.
Additionally, the more an AI learns, the more complex kinds of tasks it can eventually accomplish. One day engineers might instruct the AI to perform changes to the simulation model on its own, then run the simulation immediately afterward to see how it performs. As AI takes on more tasks, it frees engineers and designers and grants them more time to build their creativity and apply their expertise to more critical tasks.
While its full potential is still emerging, AI is growing to be another valuable tool for the automotive industry that can help prepare simulation software for the growing multi-physics complexity of today’s vehicles. By applying it now to \tasks such as data analysis and clustering, it has a better chance of learning from that data and growing into something that can transform how automotive engineering is done.
Be sure to check out the article for more information on AI in automotive simulation.
Siemens Digital Industries Software helps organizations of all sizes digitally transform using software, hardware and services from the Siemens Xcelerator business platform. Siemens’ software and the comprehensive digital twin enable companies to optimize their design, engineering and manufacturing processes to turn today’s ideas into the sustainable products of the future. From chips to entire systems, from product to process, across all industries. Siemens Digital Industries Software – Accelerating transformation.
