SEOUL, South Korea — Nexen Tire Corp. has developed an artificial intelligence (AI)-based tire-performance prediction system that the company claims can predict certain tire-performance parameters more precisely and rapidly.
Nexen will use machine-learning technology in the design stage to predict tire-performance parameters — such as fuel efficiency, noise, stopping distance and handling, the company said.
Forecasting tire performance early in the development process reduces both development time and the number of prototypes produced.
Traditionally, finite element analysis (FEA) is used to build and analyze 3D tire models, Nexen said. That process creates precise predictions but can take a long time and uses much computer-processing power, which can slow the development process.
Nexen's AI-based tire-performance prediction system allows for faster and more accurate tire design and performance improvement during the design stage, adding a valuable tool to the existing FEA-based performance-prediction methods, the company said.
To ensure the integrity of the data used in the AI-based system, Nexen Tire created a data pre-processing technology that detects irregularities in the data and screens them out.
"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 tires," said Seong Rae Kim, researcher of the Nexen univerCITY, Nexen's central research and development institute in Seoul.
"Through combined industry-academic research, we intend to increase talent training and R&D skill," Kim said.
Seoung Bum Kim, a professor at Korea University and Ki Chun Lee, a professor at Hanyang University, collaborated on the newly created tire-performance prediction system using AI technology.
