Artificial intelligence detects tool problems early 02 December 2014

Researchers at Nottingham Trent University have developed an artificial intelligence system claimed to detect problems with cutting tools on production lines with 100% accuracy.

A study led by Professor Amin Al-Habaibeh, of the School of Architecture, Design and Built Environment, found that by combining infrared cameras and neural networks, broken or missing cutting tools were consistently detected.

The technology – which does not require any contact with the machinery – could provide live feedback to alert operators and help prevent catastrophic tool damage, he says.

"This could be a very efficient method for manufacturers to maintain the productivity of their manufacturing lines and the quality of their products in an automated way," states Al-Habaibeh, a professor of intelligent engineering systems.

"The real advantage is that the system can detect problems in real time, which is difficult to achieve by [other] methods," he continues.

"Because the artificial intelligence system can learn, it's possible for it to monitor various cutting tools, making it flexible to use."

"As the technology is based on using a simple infrared camera, it should be easy for manufacturers to put it in place without any upheaval in relation to their existing equipment," adds PhD researcher Milad Elgargni.

"We believe, also, that it would be possible to develop the technology further to help detect gradual tool wear, which would help provide operators with increased awareness of the condition of the tools."

For more information, use the link below.

Brian Tinham

Related Companies
Nottingham Trent University

This material is protected by MA Business copyright
See Terms and Conditions.
One-off usage is permitted but bulk copying is not.
For multiple copies contact the sales team.