Monolith Artificial Intelligence Software creates new possibilities in specifying complex crash, aerodynamic and environmental tests
Artificial Intelligence software provider, Monolith has expanded the use of its AI platform to the BMW Group for accelerating the development of its vehicle range. By training Monolith self-learning models with the company’s wide reaching engineering test data, engineers can now use AI to solve previously impossible physics challenges and instantly predict the performance of highly complex systems like crash and aerodynamics tests.
The BMW Group crash test engineering team began working with Monolith in 2019 via the BMW Startup Garage to explore the potential of using AI to predict the force on a passenger’s tibia during a crash. Current crash development uses thousands of simulations as well as physical tests to capture performance. Even with sophisticated modelling, owing to the complexity of the physics underpinning crash dynamics, results require substantial engineering know-how to calibrate for real world behaviour.
Moreover, physical crash tests can only be conducted in later stages of development when the design is mature enough to create physical prototypes. Exploring a more efficient method, the BMW Group collaborated with Monolith to see if AI could predict crash performance and importantly, substantially earlier in the vehicle development process.
Self-learning models
Using Monolith, BMW Group engineers built self-learning models using the wealth of their existing crash data and were able to accurately predict the force on the tibia for a range of different crash types without doing physical crashes. Additionally, the accuracy of the self-learning models will continue to improve as more data becomes available and the platform is further embedded into the engineering workflow. This approach now means engineers can optimise crash performance earlier in the design process and reduce dependence on time-intensive, costly testing whilst making historical data infinitely more valuable.
According to Dr Richard Ahlfeld, CEO and Founder of Monolith, when the intractable physics of a complex vehicle system means it can’t be truly solved via simulation, AI and self-learning models can fill the gap to instantly understand and predict vehicle performance. This offers engineers a tremendous new tool to do less testing and more learning from their data by reducing the number of required simulations and physical tests while critically making existing data more valuable.
“We are excited to see how BMW Group engineers are using pioneering technology like Monolith to reduce the cost and time of product development as they develop the next generation of vehicles.”
Wider test applications for AI
The Monolith platform has been developed with a focus on user experience by automotive experts and data scientists to ensure seamless integration with existing engineering processes. As a result, as soon as the software is implemented, domain experts quickly begin gaining valuable insights and time back, as well as the chance to explore even wider opportunities.
In this respect, BMW is expanding its use of Monolith into more engineering functions across R&D that generate vast amounts of data from different sources, such as aerodynamics and advanced driver-assist systems (ADAS). There is the opportunity to use Artificial Intelligence to predict outcomes in challenging applications such as Noise, Vibration & Harshness (NVH) testing and other environmental tests such as climatic testing. In all these cases, the physics is complex and the number of possible test scenarios is large.
“The combination of engineering expertise and machine learning can provide a significant competitive edge and provide our customers with the means to create world-class products more efficiently.” Ahlfeld concludes.
- UK manufacturing steps up to COVID-19 crisis - April 2, 2020
- Clustering Innovation - March 12, 2020
- A Global Monitor - March 6, 2020