Quality Intelligence



Felix Sohnius

Chief Engineer


+49 241 80 25828



Further information


Fields of Expertise

Group of people Copyright: © WZL from left to right: Felix Sohnius, Alexandra Schmitt, Sebastian Beckschulte, Hannes Elser, Max Ellerich, Jimmy Chhor, Leo Nuy, Peter Schlegel, Marie Lindemann, Lars Gussen, Robin Günther, Junjie Liang, Daniel Buschmann, Quoc Hao Ngo

The advancing digitalization influences and unsettles producing companies equally - the increasing focus on IoT, the increasing degree of automation invoked in many places and the digital mapping of processes and products in the digital shadow represent only a small part of the new technical possibilities. However, the multitude of possibilities for action offered by digitalization, in particular, increasingly raise questions regarding the effects on the business success of activities.

Together with manufacturing companies, we are pursuing the goal of increasing process and product quality through the use of proven quality methods in combination with new technologies. Here we focus above all on the analysis of production and product data.

In particular, the methods of classical quality management have always been designed for the continuous improvement of processes and products in a preventive sense. Thus we combine the most original motivation of quality management with new technical possibilities to show the potential of digitalization. Since the restriction of limited information availability is increasingly receding into the background, methods of artificial intelligence such as machine learning can already supplement and extend classical quality methods today. For example, component-specific tolerance fields are created for each customer, while IoT-enabled products from the field themselves initiate improvement suggestions for production and development.

Central Tasks

  • With Predictive Quality, we extend existing statistical approaches to process monitoring with approaches from machine learning.
  • With Predictive Maintenance we extend the classical approaches of Total Productive Maintenance by Artificial Intelligence to carry out maintenance before machines fail.
  • With the objectification of customer perceptions and the analysis in the course of Predictive Perceived Quality, we supplement classical test person studies with automated measurements and machine learning approaches.
  • With Usage Data Analytics we identify improvement potential for subsequent product generations based on usage and interaction data of products from the field.


We deal with the analysis of data along the product lifecycle that allow conclusions to be drawn about process or product quality. By merging classical QM approaches with new technologies, we are able to find new solutions for both familiar and new problems.


Cooperation partners