Werner Herfs

Cognitive Control Technology for a Self-Optimizing Robot Based Assembly Cell

In the face of global competition there is a great danger for countries with high labor costs (e.g. Germany) to lose more and more production plants to low-wage countries. Almost inevitably there will be a relocation of after-sales services as well as of research and development. Eventually this will cause a significant decline of wealth. For this reason especially high-wage countries are always striving for higher productivity of production processes. On the other hand the products have to be of high-end quality to ensure an advantage in the market. Thus there is an obvious dilemma between planning-orientation and value-orientation which has to be resolved. This could possibly be obtained by shifting planning efforts to the runtime system and at the same time enabling the system to adapt to changing requests and circumstances. In order to get there, automation technology is definitely playing a key role in present-day highly automated production processes. Unfortunately classical automation technology has not been supporting this kind of self-organizing, self-controlling and self-optimizing behavior. This paper introduces an approach to make production systems more “intelligent” based on the idea of a cognitive control architecture. At first the motivation and the research vision are introduced followed by an outline of the research approach. As a concrete example of an application a robot based assembly cell is described. The methods used and insights gained so far are presented in the second part, followed by an outlook towards future activities.Copyright

Self-optimising Production Systems

One of the central success factors for production in high-wage countries is the solution of the conflict that can be described with the term “planning efficiency”. Planning efficiency describes the relationship between the expenditure of planning and the profit generated by these expenditures. From the viewpoint of a successful business management, the challenge is to dynamically find the optimum between detailed planning and the immediate arrangement of the value stream. Planning-oriented approaches try to model the production system with as many of its characteristics and parameters as possible in order to avoid uncertainties and to allow rational decisions based on these models. The success of a planning-oriented approach depends on the transparency of business and production processes and on the quality of the applied models. Even though planning-oriented approaches are supported by a multitude of systems in industrial practice, an effective realisation is very intricate, so these models with their inherent structures tend to be matched to a current stationary condition of an enterprise. Every change within this enterprise, whether inherently structural or driven by altered input parameters, thus requires continuous updating and adjustment. This process is very cost-intensive and time-consuming; a direct transfer onto other enterprises or even other processes within the same enterprise is often impossible. This is also a result of the fact that planning usually occurs a priori and not in real-time. Therefore it is hard for completely planning-oriented systems to react to spontaneous deviations because the knowledge about those naturally only comes a posteriori.

SOAR-based sequence control for a flexible assembly cell

For a long time self-optimizing production systems have been proposed as a contribution to make production processes more adaptive while keeping them synchronized towards a global goal. As todays industrial automation is identified as a bottle-neck, a control framework which is built around the cognitive platform SOAR is introduced in this paper. The main idea is the provision of a model-based approach to explicitly describe the application task and a control architecture which is able to generate adequate (or even optimal) action-flows to achieve the task. As an illustrative scenario a robot based handling cell is presented.

Cognition-Enhanced, Self-optimizing Production Networks

This research area focuses on the management systems and principles of a production system. It aims at controlling the complex interplay of heterogeneous processes in a highly dynamic environment, with special focus on individualized products in high-wage countries. The project addresses the comprehensive application of self-optimizing principles on all levels of the value chain. This implies the integration of self-optimizing control loops on cell level, with those addressing the production planning and control as well as supply chain and quality management aspects. A specific focus is on the consideration of human decisions during the production process. To establish socio-technical control loops, it is necessary to understand how human decisions are made in diffuse working processes as well as how cognitive and affective abilities form the human factor within production processes.

Radio channel characterization at 5.85 GHz for wireless M2M communication of industrial robots

The fourth industrial revolution, also referred to as Industrie 4.0, has triggered a number of research projects to improve communication systems for industrial environments. Wireless technologies for mission-critical machine-to-machine communication are expected to enable very efficient and highly flexible production processes. It is especially challenging for wireless interfaces to fulfill the required end-to-end latency and the reliability constraints of the automation industry. In order to design novel PHY and MAC schemes for ultra low delay, ultra reliable and deterministic transmission of data, e.g., through optimized pulse shaping, we study the indoor radio propagation in a representative factory automation cell where industrial robots are to be controlled. We performed channel measurements using a broadband channel sounder at 5.85 GHz carrier frequency. During the measurements, the robots were in motion and executed a typical pick-and-place process. From the recorded data we evaluate the channel characteristics and calculate relevant delay statistics. We distinguish two measurement series that differ in the scattering environment and present the derived parameters. Finally, we discuss the impact of our results on the design of new 5G waveforms for industrial radio systems.

Hybrid Production Systems

While virtual product development allows great freedom in terms of design, actual development processes are rather restricted. Those boundary conditions are at best hardly possible to exert influence on. Therefore, future research has to focus both on the realisation of the concept of one-piece-flow while simultaneously increasing flexibility and productivity and on the technological advancement. Hence, hybridisation of manufacturing processes is a promising approach, which often allows tapping potentials in all the aforementioned dimensions.

3D Assembly Group Analysis for Cognitive Automation

A concept that allows the cognitive automation of robotic assembly processes is introduced. An assembly cell comprised of two robots was designed to verify the concept. For the purpose of validation a customer-defined part group consisting of Hubelino bricks is assembled. One of the key aspects for this process is the verification of the assembly group. Hence a software component was designed that utilizes the Microsoft Kinect to perceive both depth and color data in the assembly area. This information is used to determine the current state of the assembly group and is compared to a CAD model for validation purposes. In order to efficiently resolve erroneous situations, the results are interactively accessible to a human expert. The implications for an industrial application are demonstrated by transferring the developed concepts to an assembly scenario for switch-cabinet systems.

Integration und Durchgängigkeit von Information im Produktionsmittellebenszyklus

Kurzfassung Die effiziente Lösung von Engineering- und Serviceaufgaben während des gesamten Lebenszyklus heutiger Produktionsanlagen setzt einen intensiven Informationstransfer zwischen Mitarbeitern der einzelnen Fachbereiche in Entwicklung, Konstruktion, Inbetriebnahme und Service voraus. Idealerweise dient hierbei das digitale Anlagenabbild als übergreifendes Informationsmodell und begleitet das Produktionssystem entlang seines Lebenszyklus und darüber hinaus für spätere Neukonstruktionen. Die Vernetzung von Lebenszyklusdaten ist jedoch in der Regel lückenhaft. So werden zum Beispiel externe Engineering- und Produktdaten sowie Daten aus der Elektro- und Automatisierungstechnik einschließlich des resultierenden Anlagenverhaltens nur unzureichend in das Informationsmodell der Digitalen Fabrik integriert. Zudem fehlen Werkzeuge, die nach der Inbetriebnahme einen systematischen Abgleich der realen Anlage mit dem digitalen Abbild ermöglichen. Damit entfernt sich aber die reale Anlage von ihrer digitalen Version, und es fehlen aktuelle und konsistente Informationen für Serviceaufgaben sowie für Erweiterungs- und Änderungsprojekte. Die in diesem Artikel vorgestellten Konzepte zielen auf eine verbesserte Durchgängigkeit der Information im Lebenszyklus von Produktionsmitteln unter Berücksichtigung der Notwendigkeit eines stetigen Abgleichs zwischen digitaler und realer Welt ab. Die entwickelten Konzepte werden anhand der Siemens-Modellanlage SmartAutomation veranschaulicht.

Integration of Software Tools with Heterogeneous Data Structures in Production Plant Lifecycles

Abstract Today, most technical disciplines involved in the lifecycle of production plants process their tasks with software tools that establish their own data stocks. Thus, the corresponding information networks are characterized by heterogeneous data structures leading to drawbacks considering information retrieval, identification of interdisciplinary dependencies and creation of generalized design solutions. Information integration aims to solve these problems by providing unified access to distributed heterogeneous sources. This article first describes the information network in production plant lifecycles and discusses the required elements for the process of information integration. This is followed by an outline of current research and technology in the fields of neutral formats and engineering ontologies. The developed concepts for information integration in production plant lifecycles are presented based on this, and demonstrated with a model plant for bottling, commissioning, and recycling.

Virtual Production Systems

The use of simulation systems is of significant importance for companies in high-wage countries as the requirements of product- and process quality are generally higher than in low-wage countries due to conditions of the market. Since the implementation of simulation tools is not value-adding in the first place, the performance of virtual product development chain must therefore be continuously increased in terms of greater planning efficiency. Research in the field of virtual production systems therefore addresses the following issue.