Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

7
7
Reset filters

Settings
Now showing 1 - 7 of 7
No Thumbnail Available
Publication

Model-based routing in flexible manufacturing systems

2019 , Windmann, Stefan , Balzereit, Kaja , Niggemann, Oliver

In this paper, a model-based routing approach for flexible manufacturing systems (FMS) with alternative routes for the work pieces is proposed. For each work piece, an individual task has to be accomplished, which consists of several processing steps. Each processing step can be executed on alternative working stations of the FMS. The proposed routing method employs a model of the conveying system to find energy efficient and fast routes for the respective work pieces. The conveying system model is based on a directed graph, where the individual conveyors are modeled as weighted edges. It can be straightforwardly applied to several types of FMS by adjusting the application-dependent parameters. Efficient computation of the fastest route through the conveying system is accomplished by means of dynamic programming, i. e., by integration of Dijkstra's algorithm in a dynamic programming framework, which is based on the proposed conveying system model. Additional consideration of energy efficiency aspects leads to a Mixed Integer Quadratically Constraint Program (MIQCP), which is solved by substitution of Dijkstra's algorithm by a branch and bound method. Experimental results for an application scenario, where the energy efficient routing method is applied to route work pieces between the working stations of an FMS, lead to 20 % reduction of energy consumption on average.

View
No Thumbnail Available
Publication

Machine learning in automation

2018 , Beyerer, Jürgen , Niggemann, Oliver

In the 21st century, we no longer try to turn lead into gold, but data into money. Machine Learning therefore becomes our modern Philosopher's Stone. While the search for the Philosopher's Stone occupied researchers for 2500 years-leading to porcelain and not to gold-we are optimistic to achieve better results in a shorter period of time. Machine Learning has been an established field of research for decades, yielding a large set of tested algorithms and many successful applications. Nevertheless, the application of these algorithms to Cyber-Physical Systems (CPS) is a rather new field which still poses several challenges. First of all, CPS require solutions which fulfil nonfunctional requirements such as safety, security, maintainability and real-time capabilities. They also show a complex timing behavior which is often due to complex causalities and due to state-based system behavior. Furthermore, the number of useful data points is rather small compared to other domains, mainly because the observed data is highly redundant and covers only a few typical normal situations and not much more informative marginal situations. Several solutions to these challenges are currently in the focus of research, e. g., the integration of a priori knowledge into Machine Learning algorithms (i. e., Greybox-Approaches), the automatic configuration and choice of suitable algorithms (i. e., AutoML), or the development of specific algorithms. However, questions such as data quality, big data platforms and time synchronization also play an important role. This special issue will highlight some of these research trends. The question of interpretability is in the focus of the first paper, ""Interpretable machine learning with reject option"". The next paper, ""Combining expert knowledge and unsupervised learning techniques for anomaly detection in aircraft flight data"", deals with the integration of a priori knowledge on the learning methods. The papers ""Computation of energy efficient driving speeds in conveyor systems"" and ""Online parameter estimation for cyber-physical production systems"" outline methods to learn models for the purpose of prediction and optimization. Finally, the papers ""Simulation and optimization of industrial production lines"" and ""Assessment of variance & distribution in data for effective use of statistical methods for product quality prediction"" apply learned models to prediction tasks.

View
No Thumbnail Available
Publication

Data-driven anomaly detection in cyber-physical production systems

2015 , Niggemann, Oliver , Frey, Christian

Im Zuge von Trends wie Industrie 4.0 ändert sich die Wertschöpfung in der produzierenden Industrie: Daten-basierte Services ergänzen klassische Geschäftsmodelle und schaffen neue Märkte. In diesem Artikel werden anhand des Anwendungsfalls Anomalieerkennung solche daten-basierten Services vorgestellt und diskutiert. Der Beitrag betrachtet dazu Beispiele aus der Fertigungstechnik, aus der Prozesstechnik und aus dem Gebiet der Energieanalyse.

View
No Thumbnail Available
Publication

Online parameter estimation for cyber-physical production systems based on mixed integer nonlinear programming, process mining and black-box optimization techniques

2018 , Otto, Jens , Vogel-Heuser, Birgit , Niggemann, Oliver

Cyber-Physical Production Systems (CPPS) should adapt to new products or product variants efficiently and without extensive manual engineering effort. In comparison to rewriting the automation software for each adaption, manual engineering effort can be reduced by reusable software components with free parameters, which must be adjusted to individual production scenarios. This paper introduces CyberOpt Online, a novel online parameter estimation approach for reusable automation software components. In contrast to classic mathematical modeling approaches, such as Mixed Integer Nonlinear Programming (MINLP), our approach requires no predefined models that represent the system. Models, e. g., of the energy consumption of CPPS, are learned automatically from data observed during the operation of the production system. Therefore, the manual engineering effort is minimized as postulated by the paradigm of CPPS. The presented approach combines MINLP, process mining and black-box optimization techniques for calculating optimal timing parameter configurations for automation software components with free parameters in the domain of discrete manufacturing.

View
No Thumbnail Available
Publication

Interaktionsmodell für Industrie 4.0 Komponenten

2017 , Diedrich, Christian , Bieliaiev, Alexander , Bock, Jürgen , Gössling, Andreas , Hänisch, Rolf , Kraft, Andreas , Pethig, Florian , Niggemann, Oliver , Reich, Johannes , Vollmar, Friedrich , Wende, Jörg

Verwaltungsschalen bilden zusammen mit den Assets der digitalen Fabrik I4.0-Komponenten. Interaktionen zwischen den Verwaltungsschalen sind wichtige Bestandteile der Wertschöpfungsketten in den I4.0-Systemen. Dafür benötigen die Verwaltungsschalen eine gemeinsame Sprache. Auf der Basis der Festlegungen der DIN SPEC 91345, d. h. des RAMIs und der Struktur der Verwaltungsschale, wird hier das Interaktionskonzept beschrieben.

View
No Thumbnail Available
Publication

Computation of energy efficient driving speeds in conveying systems

2018 , Windmann, Stefan , Niggemann, Oliver , Stichweh, Heiko

This article addresses the automatic optimization of driving speeds in conveying systems. Electric drives in existing conveying systems are usually accelerated and decelerated according to predetermined movement profiles. Such an approach is inflexible for conveying applications with changing constraints and, in many cases, not optimal with respect to energy efficiency. In the present work, a method for automatic computation of energy efficient movement profiles is proposed. The proposed method is based on accurate models for electric drives and several types of conveying applications such as roll conveyors, belt conveyors and vertical conveyors. Furthermore, joint energy efficiency optimization for two drives, which are attached to an intermediate circuit, is investigated. Thereby, additional constraints on the energy flow between the drives are imposed in order to reduce load peaks and energy feedback into the grid. The resulting optimization problem is a mixed integer quadratic program (MIQP), which can be solved in a few milliseconds. Experimental results show that energy losses of electric drives are cut down by using the obtained non-trivial movement profiles instead of standard trapezoid movement profiles. The additional constraints on the energy flow between two drives lead to further significant improvements with respect to the overall energy losses.

View
No Thumbnail Available
Publication

A self-configurable fault detection system for Industrial Ethernet networks

2017 , Windmann, Stefan , Niggemann, Oliver

In this paper, a self-configurable fault detection system for automated production systems with Industrial Ethernet is proposed. The scope of the proposed fault detection system are process variables, i.e., the observed actuator and sensor signals. Self-configuration of the fault detection system is enabled by recording and analyzing the link connection of the Ethernet network during system start. In a subsequent training phase, a knowledge base is automatically built from the observed process variables. Knowledge-based fault detection is accomplished once the knowledge base is established. Fault detection has been evaluated for a glue production process. In this application case, the knowledge-based fault detection method yielded a balanced accuracy of 99.81%, while a model-based method, which has been used as reference, produced a balanced accuracy of 93.11%.

View