Refine
Document Type
Language
- English (2)
Has Fulltext
- no (2)
Publication reviewed
- begutachtet (2)
Institute
Is it possible for pharmaceutical companies to apply the concepts of industry 4.0, such as the smart factory, completely in their GMP relevant production processes? Are the GMP guidelines generally open to modern production methods enabled by I4.0? Are those responsible in the pharmaceutical industry familiar with the possibilities of I4.0?
The hypotheses could not be supported completely. The survey shows that the potential of industry 4.0 concepts has not yet arrived in large parts of the workforce and the management level. The GMP regulations allow innovations in many areas, but with considerable effort during the implementation phase. The complete introduction of a smart factory means a reinterpretation of the existing regulations. This leads to very cautious first steps which are in the area of employee support, not the introduction of new processes in the workflow itself.
In this article, the optimization of the control circuit and path planning of a delta kinematic with the help of machine learning is presented. The described delta kinematic is primarily used for pick-and-place applications in the field of packaging machines. The optimization of the path planning procedure aims to make the workflow more efficent and flexible for commissioning the delta kinematic. By optimizing the control circuit using machine learning, mechanical oscillations and the deviation of the specified path are to be minimized. The possible use of a simulator for training, the prediction quality and the implementation on the robot controller are discussed. Furthermore, the path planning procedure was optimized. For this purpose, an environment was implemented in which a reinforcement learning agent plans the path of the robot between a starting point and a target point in a time-optimized manner, considering interference contours e.g. from the machine. The obtained results show the optimization of the robot by machine learning with a root mean squared error of the predicted torques of 0.06025 Nm in a prediction time of around 0.125 ms and the possibility of path planning with different criteria.