London-based AI software company Monolith is using the AI ​​platform to significantly reduce the cost of developing and testing new vehicles.

Monolith software uses self-learning models to instantly predict the results of sophisticated vehicle dynamics systems, reducing the need for physical tests and simulations. The company claims that this approach drastically speeds up every stage of the car development process – from initial design through design iterations and validation to production, which currently requires repetitive, time-consuming and expensive tests and simulations. Monolith says its platform requires fewer physical prototypes and road tests, making product validation safer and more sustainable.

“Optimizing a system or finding a new solution based on a decade of historical data is like offering an engineer a decade of experience immediately. This is the power of AI – it charges the expertise of the individual by unlocking the expertise stored in the company’s data, “said Dr. Joel Henry, chief engineer at Monolith.

So far, car companies have used a combination of realistic virtual simulations and physical testing during vehicle development. For each iteration of design, the simulation decides the physics that underlies the modeling of the system – a certain difficult and intensive of the calculated process. Virtual simulations help reduce the number of physical tests required, but the accuracy and precision of the results may be limited. Therefore, a number of physical tests are still needed to calibrate and validate virtual results, as well as to understand performance in working conditions that cannot be simulated.

“Today, car companies spend billions developing electrical architectures and software capabilities as they strive to win the race for electric, shared and autonomous mobility. This is shrinking R&D budgets and product deadlines in other areas, putting enormous pressure on engineering teams working to develop better vehicle hardware systems in less time and with fewer resources, ”he said. Dr. Richard Alffield, CEO and Founder of Monolith.

Monolith has spent six years developing its platform, which combines virtual and physical test data to train high-precision AI self-learning models. The models then predict the performance of the systems by understanding their behavior instead of solving the complex physics of the system or performing a physical test.

“Monolith was founded to enable AI engineers to solve even their most difficult physical problems immediately. We know this resonates especially with automotive engineers struggling to optimize hundreds of often conflicting criteria with hundreds of complex simulations. Requiring hours or days to solve, engineers were disappointed with the significant amount of physical tests that are still needed to compensate for the limitations of virtual tests. At the same time, the data that is created in the process is a huge opportunity when used with AI, “said Alfield.

London company Monolith brings artificial intelligence to automotive development

Previous articleRays Power Infra sells solar projects for over Rs 700Cr
Next articleDiscussion of upgrades to the European battery value chain