Nexen taps AI for tire performance prediction system

Seoul – Nexen Tire has developed an artificial intelligence- (AI) based process to “precisely and rapidly” predict tire performance, using machine learning technology in the concept design stage. 

Developed in collaboration with Korean universities, the "virtual brain loop system," factors in performance indicators such as fuel efficiency, noise and handling process, said Nexen in a 15 Feb statement.

As part of developing the system, Nexen said it created a ‘data pre-processing technology’ that could detect and replace irregularities in the data.

This provided access to “high-quality data in big volumes”, which then enabled Nexen to secure a forecasting model with good predictive performance for insufficient data.

According to Nexen, 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.

Traditionally, finite element analysis (FEA) is used to forecast the performance of generic tires.

The technology enables the modelling of the shape and material properties of a tire virtually, while the mechanical properties of the product can be confirmed through numerical calculation.

While FEA can evaluate high precision performance estimates, it takes a long time to calculate the figures.

As a result, developers tend to analyse performance at the concept design stage, which according to Nexen is inefficient.

Nexen’s new AI-based prediction system allows “faster and more accurate” tire design and performance improvement during the pre-production process, in addition to the existing FEA-based performance prediction technique.

"We aim to finalise the development of the ‘virtual brain loop system’, a tire development system based on our own virtual design technology," said Seong Rae Kim researcher at Nexen univerCITY R&D Institute.

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.