Process-driven product development

Research field

AG prozessgetriebene Produktentwicklung

In process-driven product development, information technology, analytical and empirical approaches are developed in the operational and production environment. The focus is on using product life cycle and environmental data to build adapted products and processes.

The fields of work are data mining, data-driven modelling and simulation to improve customer-oriented product features. The necessary data-based depictions of products and processes are developed for various fields of application and implemented. For example, existing AI and digitalization approaches for industrial issues are adapted and prepared so that they can be integrated into products and processes in the industrial environment with little effort. This optimizes the energy efficiency and sustainability of products and processes in particular.

The following topics are being researched:

  • Modelling of production processes concerning product characteristics and energy consumption
  • Optimization of product and process parameters based on data-driven models to increase energy efficiency
  • User-friendly provision of digitalization and AI methods for SMEs



  • Eis-Auge - Ice detection on wind turbines using AI-supported image processing
  • BreGoS - Bremen goes Sustainable - A university region on the way to sustainability - Subproject: Transformative research in campus labs and comparative analysis of sustainability governance, networks and practices
  • EnSort - Increasing energy efficiency in the waste and recycling material sorting process by applying artificial intelligence methods - Sub-project: Modelling and characterization of material flows

Selected publications:

  • Nabati, E. G., Nieto, M. T. A., Bode, D., Schindler, T. F., Decker, A., & Thoben, K.-D. (2022). Challenges of manufacturing for energy efficiency: towards a systematic approach through applications of machine learning. Production, 32, e20210147. DOI:
  • Schindler, T.F., Bode, D., Thoben, K.-D. (2023). Towards Challenges and Proposals for Integrating and Using Machine Learning Methods in Production Environments. Advances in System-Integrated Intelligence (SYSINT 2022). DOI:
  • Schindler, T., Greulich, C., Bode, D., Schuldt, A., Decker, A., Thoben, KD. (2020). Towards Intelligent Waterway Lock Control for Port Facility Optimisation. Dynamics in Logistics (LDIC 2020). DOI: