Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Institutsteil Industrielle Automation

Seminar: Big Data for Industrial Automation

How to make data an asset.

Motivation: How does data become a valuable asset?

Industrial companies are collecting huge amounts of data from sensors. Raw data is not very beneficial unless it is turned into knowledge. To achieve that, data needs to be acquired, transferred, and analyzed in efficient ways to improve products and processes and to reduce costs and materials. Big Data technologies are needed to do that in a fast, scalable, replicated and fault-tolerant manner.

Objective: A practical introduction to directly benefit in your own production.

Practical Introduction to Big Data technologies in industrial automation: Industrial data from devices to visualization with industrial use cases learning through application. The content is directly implemented and consolidated through practical exercises.



Benefit from both, state of the art technologies and resarch as well as from practical exercises and experience. The Big Data seminar will gather all the know-how that will be necessairy to get startet or improve the data management and -usage in your production. 

  Introduction to Big Data
  • Introduction to Big Data frameworks (transfer, storage, and computation)

  • Big Data for industrial automation

  Introduction to Apache Kafka as a Streaming Platform

  • Fundamental concepts of Kafka

  • Kafka Architecture

  • Kafka as a messaging system

  • Kafka as a stream processing framework

   Data Acquisition via OPC UA to Kafka

  • OPC UA background

  • OPC UA to Kafka Connectors (e.g. python code)

  • Data Serialization (e.g. string and json)

   Data Analytics (focus on ML)

  • Batch vs. Stream analysis

  • Machine Learning Process

  • Industrial use case: stream prediction

  • Practical part: Implement the use case using Kafka Stream

  Data Visualization

  • Introduction to Grafana

  • Practice Grafana based on real stream data

  Practical exercise:

  • Install a distributed Kafka cluster

  • Practice the basic Kafka API

  • Develop an industrial data pipeline (OPCUA-Kafka-InfluxDB-Grafana)

  • Develop a simple processing application using Kafka Streams library for a real prediction use case

  • Explore the results using Grafana


Interested? Just send a short e-mail to Florian Pethig.


 800,-- €


SmartFactoryOWL | Campusallee 3 | 32657 Lemgo



Learning goals:

  • Basic knowledge of Big Data in industrial automation
  • Quick start to transfer and process industrial stream data in scalable way using Apache Kafka
  • Quick start to data visualization
  • Bring your company to a competitive position

Target group:

Decision makers, product managers, product marketing, engineers and developers from manufacturing companies


Registrations are prioritized according to the desired dates and the member of trainees. Each group consists of 8-12 persons to ensure the quality of practice units.