How Intralogistics systems benefit from machine learning with ML4Pro²
Intelligently evaluate available data and derive forecasts
Drive and automation systems already offer extensive data – even without the installation of further, cost-driving sensors. Utilizing this data to get insights into a machines condition is a key factor of solving the challenges machine builders face today. Model- and data-driven processes that use AI and machine learning to monitor a machines condition, support a machine builder in mastering this task. In combination with end-to-end networking of machines and the increasing power of cloud- or edge-computing solutions, these new processes will allow the machine builder to detect anomalies and predict plant failures and wear.
The innovation project – ML4Pro²
Together with partners from the leading-edge cluster it’s OWL, Lenze is working on a such a new end-to-end solution in the ML4Pro² innovation project: Model-based and data-driven processes are used to monitor the wear of relevant components. While at the same time, a digital twin of the machine provides support in finding and setting up suitable monitoring functions for the respective machine modules. This ensures that the machine-learning procedures can be applied even without expert knowledge.
Machine learning – very vividly
Using a machine exhibit from horizontal conveyor technology, Lenze illustrates how results from the ML4Pro² research project will change service and maintenance processes in industrial practice.
Watch Dr. Heiko Stichweh, Head of Innovation at Lenze, explain how the advanced machine learning algorithms developed in the ML4Pro² project can benefit machine builders.
Curious about machine learning?
Our experts are always eager to help, if you want to know more about our advanced machine learning algorithms contact us!