Autor: Matthias Mühlbauer

In factory operations, measuring equipment is often used without automatic storage or further processing possibilities of the measured value. In this case, employees must capture and process the measured values manually. In this article, an approach for the optical detection and digitization of measured values with the help of machine learning methods is presented. This aims to reduce the workload of the employees, avoid reading errors and enable automated documentation.

Due to competitive pressure pharmaceutical companies are also driven to increase the efficiency of their processes. In this paper an approach for the predictive detection of malfunctions of filling systems for powdery pharmaceutical products using machine learning is presented. The focus is on the prediction of filling deviations with recurrent neural networks, with the objective to detect a drift in the process stability to intervene accordingly.