Nexen Tire develops tire performance prediction system using AI technology
- Through the virtual design system, Nexen Tire’s cutting-edge technology ensures the capacity to develop tires with the optimum performance
(SEOUL, South Korea, February 15, 2022) Nexen Tire, a leading global tire manufacturer, stated today that it has developed an Artificial Intelligence (AI)-based tire performance prediction system.
By establishing a tire 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 tire 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 utilizing data augmentation techniques, the Company was able to secure a forecasting model with good predictive performance for insufficient data.
The ability to forecast tire performance early in the tire 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 tires. With FEA, the shape and material properties of a tire can be modeled as a virtual three-dimensional tire 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 analyze 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 tire performance prediction system using AI technology, this will allow faster and more accurate tire 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 finalize the development of the “Virtual Brain Loop System,” a tire 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 tire performance prediction system using AI technology.