Germany’s Fraunhofer Institute IPA in Stuttgart has developed a new type of software that uses artificial intelligence (AI) to help industrial companies manage their machinery better. The researchers are apparently confident, given that they immediately launched a start-up called Data Coffee.

The ‘Station Connector‘ software offers a solution for a multitude of different machines with varying ages and ways of controlling them. According to Marcus Defranceski, the software should be seen as a kind of translation program.

Unifying parameters

According to Fraunhofer IPA, Station Connector makes parameters, such as power consumption, rotational speed and temperature, uniformly available for any application, regardless of the speed required at which the data is read.

Subscribe to IO on Telegram!

Want to be inspired 365 days per year? Here’s the opportunity. We offer you one "origin of innovation" a day in a compact Telegram message. Seven days a week, delivered around 8 p.m. CET. Straight from our newsroom. Subscribe here, it's free!

Subscribe!
This image has an empty alt attribute; its file name is ipa-schneller-und-einfacher-zugriff-auf-maschinendaten-bld-2-678x452.jpg

“Machine learning needs a high data speed, whereas monitoring requires a low speed. With Station Connector, we are basically putting an independent software layer between the systems and the databases that will later use this data,” says Marcus Defranceski, a scientist at Fraunhofer IPA.

“The available data creates a new transparency that allows for better manufacturing control. And it uncovers opportunities for process optimization in future,” the computer scientist explains.

Easy to use

The great thing is that it does not require that much computer knowledge to operate the software. The configuration is pretty self-explanatory. The machines can continue to run during the installation as well, Fraunhofer says.

“There are no restrictions when it comes to selecting the information and variables that are needed. The customer decides which data to process. An automated readout can be set up to detect any drops in production in time and to respond quickly to any malfunctions.”

See our archive on machine learning as well.

Support us!

Innovation Origins is an independent news platform that has an unconventional revenue model. We are sponsored by companies that support our mission: to spread the story of innovation. Read more.

At Innovation Origins, you can always read our articles for free. We want to keep it that way. Have you enjoyed our articles so much that you want support our mission? Then use the button below:

Doneer

Personal Info

About the author

Author profile picture Maurits Kuypers graduated as a macroeconomist from the University of Amsterdam, specialising in international work. He has been active as a journalist since 1997, first for 10 years on the editorial staff of Het Financieele Dagblad in Amsterdam, then as a freelance correspondent in Berlin and Central Europe. When it comes to technological innovations, he always has an eye for the financial feasibility of a project.