Peter Göhner

Coupling heterogeneous production systems by a multi-agent based cyber-physical production system

Todays increasing volatility of market demands and customer requirements are forcing industrial enterprises to realize and ensure an increased flexibility of production systems. Since current automation concepts and architectures for production systems do not provide the required flexibility sufficiently, new approaches have to be developed. This paper proposes an approach that implements the quickly evolving concept of Cyber-Physical Systems for the special case of production systems by means of software agents. A joined demonstrator of such Cyber-Physical Production System is described and used for the evaluation of the proposed multi-agent approach.

Reusable Models in Industrial Automation: Experiences in Defining Appropriate Levels of Granularity

Abstract Domain engineering approaches are widely used in the software engineering. They focus on building reusable models in a domain. At the Institute of Industrial Automation and Software Engineering (IAS) of the University of Stuttgart, a new domain engineering approach has been developed. The approach considers entire industrial automation systems, including hardware and software. Models that capture structure and behavior of entire systems have to be carefully tailored, in order to be reusable. The level of granularity deserves particular attention, since too coarse or too fine grained reusable models discourage reuse. This paper addresses the issue of finding appropriate levels of granularity and proposes a set of recommendations for determining appropriate levels of granularity for reusable models created during domain engineering.

Requirements on engineering tools for increasing reuse in industrial automation

Motivated by increasing demands for efficiency, reuse approaches have been increasingly gaining significance during the last years. System engineering shifted from single systems to product lines. Although the engineering paradigm changed, industrial automation systems within a product line are created with the same engineering tools as single systems. Hence, it becomes relevant to analyze which requirements engineering tools shall fulfill in order to increase reuse within a product line of industrial automation systems. The identified requirements are interesting for the following reasons: first, they are relevant for developers of engineering tools, since they aim to provide competitive products. Second, they are relevant for developers of industrial automation systems, since they reuse existing artifacts in designing new industrial automation systems with the help of engineering tools. Third, the topic is interesting for researchers and practitioners in the field of product line engineering for industrial automation systems who want to know which aspects are already supported by current engineering tools.

Prioritization of Test Cases Using Software Agents and Fuzzy Logic

Limited test time and restricted number of test resources confront test managers with big challenges, especially in the system test. Consequently, the test manager has to prioritize test cases before each test cycle. There is much information available for determining a reasonable prioritization order in software projects. However, due to the complexity of current software systems and the high number of existing test cases, the abundance of information relevant for prioritization is not manageable for the test manager, even with high effort. In this paper we present a concept for an automated prioritization of test cases using software agents and fuzzy logic. Our prioritization system determines the prioritization order which increases the test effectiveness and the fault detection rate.

Conceptual Design of an Engineering Model for Product and Plant Automation

Common engineering approaches and modelling approaches from software engineering are brought together. For the domain of process automation, i.e. product and plant automation, an implementation oriented approach for an object oriented software development for heterogeneous distributed systems is introduced. Model elements for control are added to UML as well as small-scale patterns for plant automation. Besides large-scale patterns are introduced as well as implementational models. The adoption of UML regarding applied diagrams and stereotypes for process automation will be introduced and structured components, an idiom for product automation software development, will be compared to other software engineering notations.

Mining software code repositories and bug databases using survival analysis models

Code repositories and bug databases contain valuable information about the process of software development. Typical studies correlate code properties with the number of faults in a software module to find error-prone modules. However, many studies do not regard the occurrence of faults over time, although the time information can be retrieved from bug databases. In order to overcome this problem, we suggest the application of survival analysis models, which are used in biostatistics and can handle time-dependent data. Because a large amount of raw data has to be evaluated statistically, we further discuss the automated retrieval and pre-processing of raw data from code repositories and bug databases.

Model-driven development of real-time systems with UML 2.0 and C

In this era of intense liking to automation in almost all time-critical fields, real-time systems have got widespread utilization in industrial, commercial, medical, space and military applications. Model-driven development of real-time systems has been a task requiring great effort because of the system complexities arising from dealing with quite a huge number of input and output streams within an acute time frame. Complexity exists both in the modeling task as well as in transforming the models into programming language code. Most real-time systems are embedded systems and because of the memory and execution time constraints, they use procedural programming language like C for their platform environment. On the other hand the MDA, an OMG standard model driven development approach, uses an MOF compliant language like UML for the modeling task and the transformation between UML and C is not straight-forward. In this paper we present how the MDA approach can be applied to the development of real-time systems. UML 2.0 is used for modeling and C is used as the target programming language

Agentenbasierte dynamische Rekonfiguration von vernetzten intelligenten Produktionsanlagen – Evolution statt Revolution

Viele Unternehmen und Institute beschaftigen sich aktuell mit dem Begriff Industrie 4.0 und seiner genauen Auslegung. Daraus resultierend existieren viele verschiedene Vorstellungen daruber, was unter dem Begriff genau zu verstehen ist. Ein Kernthema ist die Auflosung der starren Strukturen und Hierarchien der Ebenen der Automatisierungspyramide in den Unternehmen und uber Unternehmensgrenzen hinweg. Realisiert wird dieses durch eine gesteigerte vertikale (uber die Ebenen der Automatisierung hinweg) und horizontale (unterschiedliche ITSysteme) Vernetzung (vgl. Beitrag Vogel-Heuser „Herausforderungen und Anforderungen aus Sicht der IT und der Automatisierungstechnik“).

An agent-oriented approach for self-management of industrial automation systems

The increasing complexity of modern industrial automation systems (IAS) makes support of technical system management tasks necessary. Towards this goal, a generic agent-based concept for self-management systems is introduced, that supports efficient integration of self-management functions during operation time of IAS. Starting with the specific requirements on self-management systems in the domain of IAS a basic architecture is derived and completed with 6 different agent types that work on 3 levels. The functional principle is explained by means of a real-world example of a passenger lift system that is extended with self-healing functionality.

An agent-based approach for automating the disturbance handling for flexible manufacturing systems

In this paper, an agent-based approach for automating the disturbance handling in flexible manufacturing systems is proposed. This approach builds on a model that captures the environmental context of disturbances to derive their expected impact. Distributed hierarchical optimization is employed to update the generated schedule under consideration of efficiency and stability. The proposed approach has been realized and tested on a model of a real flexible manufacturing system. Test results have shown a very good potential for the proposed approach in automating disturbance handling by keeping small deviations from the original schedule and achieving high efficiency measures with good reactivity.