Digitization of Production Processes

The digitization of production processes is opening up new design options for the course of business at shorter and shorter intervals. For example, the increasing digitization is driving new business models (such as machine leasing by time of use), the automation of production processes through machine-to-machine communication, as well as the ability to respond to customer demand for customized products (lot size 1). This development is, amongst other things, favored by the availability of mass sensor data. In research and in the field, digitization in industrial companies is usually described with the keyterm "Industry 4.0".
The aim of the research focus at the Chair of Application Systems and E-Business is to demonstrate the potential of the digitization of production processes as well as to investigate new application systems and architectures. For this, we on the one hand examine the use of wearable computers (e.g. data glasses and smartwatches) in the industrial sector and on the other hand, we analyze the use of machine learning for industrial production scheduling.

Wearable Computers
A current example of the research focus is the examination of the use of wearable computers in industrial plants. The focus herein lies in the employee support in manufacture and production processes. Wearable computers offer the potential to enrich the real environment of employees with additional virtual elements (so-called augmented reality). Although wearable computers and augmented reality have been the subject of research for a long time, their diffusion into industrial enterprises is going slowly. The aim of current research at the Chair is therefore the identification of application scenarios for the use of data glasses, smartwatches and smart clothes (e.g. data gloves) as well as the conception, implementation and evaluation of application systems for wearable computers.

Machine Learning for Production Scheduling
In addition, this research area investigates the use of machine learning for industrial production scheduling. The research focuses on application systems that are required to support production scheduling by machine learning. The characteristics of production environments that have an influence on sequence planning are investigated and scheduling algorithms are developed, and simulated and evaluated in production environments.

Currently Worked-On Questions

  • Possibilities of using wearables in the industrial sector
  • Use of Machine Learning for Production Scheduling


Cooperation Partners