Autor: Mirko Kück

Optical systems are a popular choice for quality inspection because they are not only contactless and precise but also comparably fast. Particularly in cases where a 100% quality inspection is required low measurement and evaluation time is of essential importance. With high production rates of several parts per second, manual inspection is not feasible anymore and the evaluation needs to be automatically carried out by algorithms. In this article we propose a fast method for anomaly detection in image data based on principal component analysis and filtering. The method shows competitive performance on a data set of challenging surface inspection.

The increasing customization of products, which leads to higher numbers of product variants with smaller lot sizes, requires a high flexibility of manufacturing systems. These systems are subject to dynamic influences and need increasing effort for the generation of the production schedules and for the control of the processes. This paper presents an approach that addresses these challenges. First, scheduling is done by coupling an optimization heuristic with a simulation model to handle complex and stochastic manufacturing systems. Second, the simulation model is continuously adapted by real-time data from the shop floor. If, e.g., a machine goes down or a rush order appears, the simulation model and consequently the scheduling model is updated and the optimization heuristic adjusts an existing schedule or generates a new one. This approach uses real-time data provided by future cyber-physical systems to integrate scheduling and control and to manage the dynamics of highly flexible ...

The importance of data science for production and logistics continues to grow because more data are available due to Industry 4.0-Applications used for process and system optimization. In addition, the improved methods and tools for data analysis enable an easier processing of application-specific issues. This article is the second part relating to data science in production and logistics. While the first article dealt with the definition of terms and the potential of data analysis, the article at hand is dedicated to the application of data science in production and logistics by means of various application examples.

The implementation of industry 4.0 concepts requires a new understanding of data processing and analysis. Data Science integrates approaches of mathematical modelling and performant implementation to analyse data of specific application areas. Within this first article, the basics of Data Science are presented and perspectives for a data-driven production and logistics are discussed. Within a second article in a following edition, the process steps for structured data analysis will be explained and illustrated by means of application examples.

Current developments of Industry 4.0 offer new possibilities for coordination and coope-ration in production networks. Information technology allows for an ad-hoc documentation and analysis of system states. Hence, manufacturing resources can be offered to other companies in the short term, and coordination, scheduling, and billing can be done quickly. Industry and science now need to find appropriate procedures and practices how to implement and run networks of shared resources.

Due to dynamics and complexity within production and delivery networks, customer demands are often highly volatile. In order to achieve a well-founded production planning and control, future customer demands have to be predicted precisely. Classical statistical forecasting methods are often easy to apply but are not able to react on dynamic effects within the data. Methods of nonlinear dynamics consider qualitative in addition to quantitative information within past order data to find possible deterministic structures and, as a result, to achieve better forecasts of the future. This article deals with the development of a data base containing recommendations to choose suitable prediction methods in different situations.