In this talk we will show how AI can let machines learn from each other. Specifically, we will show how AI can be used to reduce the installation / tuning time for (industrial) machines, by using data from other already installed machines.
We will demonstrate our approach experimentally, by applying it to a fleet of three slider-crank setups: mechanisms widely used in industry, e.g. in weaving looms. We show that by using AI and by re-using data from similar agents, the tuning process can be sped up significantly.