Predictive Maintenance ohne Buzzwords!
Predictive Maintenance ohne KI lässt sich mit sogenannten Ursache-Folge-Modellen realisieren. Diese Modelle werden mit Prozess-, Maschinen- oder Sensordaten verknüpft und ermöglichen so eine Überwachung in Echtzeit.
Workshop – Data Exploration and Analytics
In this 2 hour workshop, we will do a hands-on exploration and analysis of the data from a steam turbine that produces energy for households and industry.
SMITZH ‘OI4 Demonstrator’ Project
The demonstrator show how device data, diagnostics and prognostics can be communicated effectively and efficiently through the information pyramid.
4 Secrets to Make Smart Devices Work Successfully in Industry
Learn how UReason’s APM Studio (embedded in the software heart of the device) provides the diagnostic, prognostic and advanced control functions to the FOCUS-1 customers allowing them to ‘cruise’ in the most optimal way.
The Myth of Predictive Maintenance?
Predictive Maintenance (PdM) with data, new sensors and artificial intelligence is revolutionizing maintenance … or is it? Why is everyone talking about it, but you can hardly find any operational use cases?
Wie schließt man die „Lücke“ zwischen den Sensordaten und der Instandhaltung?
In diesem Webinar zeigen wir anhand von Beispielen aus der Praxis, wie man Daten nutzen kann, um Arbeitsprozess in der Instandhaltung zu automatisieren.
FAQ Data Science for predictive maintenance
Find some of the most frequently asked questions that we get related to data science.
APM Studio Integrated With PTC ThingWorx
UReason’s APM Studio integration to Industrial Internet of Things (IIoT) technology platform PTC ThingWorx allows you to provide real-time asset condition monitoring, predictive and prescriptive maintenance capabilities on your asset base.
Workshop – Data Exploration and Analytics
We show you how to get from raw data to valuable insights with the help of commonly used data analytics tools, which include python and jupyter notebooks.