SURFACE TECHNOLOGY “Even sitting on a shelf in the
right conditions for two years, a tyre can lose up to 10% of its wet grip performance.” Seeing and understanding the
complex effects on a tyre’s materials and structure in order to reduce such degradation was extremely difficult, until now. SRI has partnered with Professor
Kimi Haseyama from Hokkaido University in Sapporo, Japan, to develop its first technology that utilises AI for deep learning in the development of tyres. Named ‘Tyre Leap AI Analysis’ for its ability to ‘leap’ forward in time, it predicts present and future conditions based on past trends. It anticipates how the properties
and structure of the rubber will change throughout a tyre’s lifecycle due to load, wear and age, and allows engineers to get an insight into how performance will be affected.
FEEDING THE AI ALGORITHM As the fifth largest tyre maker in the world, SRI’s knowledge of rubber science, garnered over 110 years, has been critical to the accuracy of the technology’s predictions. SRI provided real-world data along with huge quantities of advanced tyre images to ‘feed’ the AI technology.
New tyre under an electron microscope
A vast number of images showing
the complex internal structures of both new and old tyres were collated. These images were captured using an electron microscope, which utilises a beam of accelerated electrons as a source of illumination rather than visible light. The advantage being that electron
microscopes have a higher resolution and magnification of up to two million times. In comparison, a light microscope offers magnification of between 1,000-2,000 times. The data and detailed images were
fed into an algorithm developed by Professor Haseyama and his team at Hokkaido University, which set about analysing the data and images in order to extrapolate estimated rubber properties.
PREDICTING THE FUTURE The AI technology detects and assesses the rubber properties of an old tyre, as well as the surface and internal structure, and compares it to that of a new tyre. From this information it develops patterns across a tyre’s lifecycle and provides this statistical feedback. As a result, Tyre Leap AI
Analysis can accurately predict how materials and structures will change over time, and with it, how these
www.engineerlive.com
19
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44
