How to get from Sensor Data to an AI based Realtime Application - A technical Deep Dive

Date:

Which components does it need to create a predictive Maintenance application based on vibration data created by an industrial machine? That is a question that I get asked from many manufacturing companies that think about extending their traditional business by digital solutions. In this talk I try to answer that question leading through a showcase project and explaining each commponent of the project.

Therefore, I created a showcase project called coffAI that is based on our experience with real predictive maintenance solutions with our long-term customer KSB. In my talk I explain the details of the coffAI project from an architectural point of view, which means explaining the whole data chain from the sensor signal to the AI based realtime application. I will also highlight the protocols that we used to get our field data into the cloud, as well as the edge devices that we needed to have our algorithms running. Finally, I will give an overview of the cost of such a project.

Further information about the talk:

Further material

EmbeddedWorld_1

EmbeddedWorld_2

EmbeddedWorld_3