Process analysis: modeling, data mining, machine learning

  • type: lecture
  • chair: Institut für Industrielle Informationstechnik (IIIT)
  • semester: summer semester
  • place:

    07.07 Room 203

  • time:

    Friday 14:00-17:15 fortnightly


  • start: 22.04.2022
  • lecturer:

    Dr.-Ing. Christian Borchert

  • sws: 2
  • lv-no.: 2302145
  • exam:

    oral examination

  • information:

    The exam will take place on 5th August 2022 from 10:30 to 16:00

    Registration in CAS is required (deadline 29/07/2022). For the appointment scheduling please contact Dr. Borchert: or 01522 9862771


Lecture content

Students get to know problems of process engineering from the point of view of industrial practice, which are treated with the help of methods of physico-chemical modelling and data science. Students learn important interrelationships of process engineering and are able to explain them using example processes. They are able to identify relevant process data and select and apply appropriate modelling approaches to interpret them. Students are able to carry out practical analyses with process data and apply methods of varying complexity. Students are familiar with the data analysis value chain and have the ability to select a suitable data analysis procedure. The learning focus is on conveying broad methodological knowledge and application using practical examples. Reference is made to specialized in-depth lectures and/or more in-depth literature.

Aims of process engineering

  • Material and energy conversion by means of chemical, mechanical, thermal or biological operations
  • Basic operations (selection)
  • System examples
  • Important variables of process technology (temperature, pressure, composition, ...)
  • Economic efficiency in the process industry

Acquisition of data

  • Measured variables and measuring principles (selection)
  • Measurement uncertainty

Models of process technology

  • Balance equations (selection)
  • Constitutive equations (selection)
  • Solving balance equations (example in Matlab)
  • Parameter uncertainty and estimation
  • Data driven models
  • Grey-box models / hybrid models

Data Analysis

  • Requirements for data analysis in the process industry
  • Cost-effectiveness and prioritization of process analysis
  • Data pre-treatment
  • Application of data mining and machine learning
  • Online process


  • Excursion to BASF Ludwigshafen

Materials for the lecture

Materials for the lecture will be provided in ILIAS during the semester:

Magazine -> Organizational Units -> Faculty of Electrical Engineering and Information Technology -> SS 2021 -> Process Analysis: Modeling, Data Mining, Machine Learning SS21.


  • Bequette (1998). Process Dynamics: Modeling, Analysis and Simulation. Prentice Hall.
  • Russel & Novig (2016). Artificial intelligence - A modern approach. Pearson.
  • Matlab Documentation (2019). Mathworks.

Further information.

For more information, please contact