Machine Learning in Chemical Engineering

Summer semester
Type Time Place Lecturer
V; 2 SWS
Ü; 1 SWS
LSF  LSF Edgar Sanchez
  • Advanced knowledge in process engineering and informatics


The lecture deals with the emerging topic of machine learning in chemical engineering. Students are encouraged to use Python and Jupyter Notebooks as a self-study tool. In the course we analyze data sets regarding missing values, duplicates or outliers and edit them accordingly for applying suitable machine learning algorithms. Consecutively, you are familiarized with typical problem types such as regression, classification and clustering of data and are enabled to apply different models/estimators such as regression, partial least squares, artificial neural networks, … With these methods in mind, different examples from chemical engineering are used as an illustration of the methods such as fault detection, process optimization and hybrid modeling where a combination of mechanistic and data-driven models are used.
  • Analyze and edit data sets relevant in chemical engineering
  • Typical problem types: regression, classification and clustering
  • Different machine learning estimators/models such as linear and logistic regression, support vector machines and artificial neural networks
  • Application to typical examples from chemical engineering such as cost estimation, property prediction and hybrid modeling
  • Interactive use of Python for both illustrative purposes and self-learning

In summary, you are ready to analyze large research data in a new way and assess the use of either a mechanistic or data-driven model or a combination of both for your study.


Letzte Änderung: 20.10.2022 - Ansprechpartner: Webmaster