Gentelligent processes in biologically inspired manufacturing

Gentelligent processes in biologically inspired manufacturing

Kategorien Zeitschriften/Aufsätze (reviewed)
Jahr 2021
Autoren Denkena, B., Dittrich, M.-A., Stamm, S., Wichmann, M., Wilmsmeier, S.:
Veröffentlicht in CIRP Journal of Manufacturing Science and Technology, Vol. 32 (2021), S. 1-15.

Production systems have to meet quality requirements despite increasing product individuality, varying batch sizes and a scarcity of resources. The transfer of experience-based knowledge in a flexible and selfoptimizing production and process planning offers the potential to meet these challenges. Biological systems solve conceptually similar challenges pertaining to the transfer of knowledge, flexibility of individual reactions and adaptation over time. Thus, in the context of digital transformation, mechanisms derived from biology are interpreted and applied to the knowledge domain of production technology. To be able to exploit the potential of bio-inspired production systems, genetic and intelligent properties of technical components and machines were identified and brought together under the concept of “Gentelligence”. Expanding upon this concept with the new idea of process-DNA and biologically inspired optimization algorithms facilitates a more flexible, learning and self-optimizing production, which is shown in three different applications. By using the new concept of gentelligent process planning it is possible to determine machine-specific process parameters in turning processes in order to ensure appropriate roughness within the requirements. Furthermore, the combination of the concept with a material removal simulation allows the determination of the resulting process force in tool grinding for subsequent unknown workpiece geometries. As a result of using the process-DNA, a workpiece- independent knowledge transfer and thus process adaptation for shape error compensation becomes possible. Gentelligent production scheduling enables a process-parallel, holistically optimized machine allocation, and as a result, a significantly reduced lead time.

DOI 10.1016/j.cirpj.2020.09.015