South Korean tyre maker Nexen Tire has developed an Artificial Intelligence (AI)-based tyre performance prediction system.
By establishing a tyre performance prediction system using AI technology, the company explained that it will use a machine learning technology in the concept design stage to precisely and rapidly anticipate the primary performance indicators such as fuel efficiency, noise, handling process, etc. that are considered during the tyre development process.
Since securing high-quality data in big volumes is critical for machine learning, Nexen Tire has created a data pre-processing technology that can detect and replace irregularities in the protected data. By securing a substantial amount of learning data utilising data augmentation techniques, the company was able to secure a forecasting model with good predictive performance for insufficient data.
The ability to forecast tyre performance early in the tyre development process has a significant impact on the quantity of prototypes produced and the development time. Primarily, Finite Element Analysis (FEA) is used to forecast the performance of generic tyres.
With FEA, the shape and material properties of a tyre can be modelled as a virtual three-dimensional tyre on a computer, and the mechanical properties of a product can be confirmed through numerical calculation. The advantage of FEA is that it can evaluate high precision performance estimates, but it takes a long time to calculate the figures, therefore developers quickly analyse performance at the concept design stage, which is inefficient.
Nexen Tire has been consistently working on establishing a Virtual Product Development System. With the newly developed tyre performance prediction system using AI technology, this will allow faster and more accurate tyre design and performance improvement during the pre-production process, in addition to the existing FEA-based performance prediction technique and Genetic Algorithm that suggest optimal design plans.
“We aim to finalise the development of the “Virtual Brain Loop System,” a tyre development system based on our own virtual design technology, and apply it to OE and RE goods,” said Seong Rae Kim, Researcher of The Nexen univerCITY, Nexen Tire’s central R&D Institute. “Through combined industry-academic research, we intend to increase talent training and R&D skills.”
Professor Seoung Bum Kim of Korea University and Professor Ki Chun Lee of Hanyang University collaborated on the newly created tyre performance prediction system using AI technology.