Markus Obdenbusch

Towards Optimized Machine Operations by Cloud Integrated Condition Estimation

The requirements concerning the Overall Equipment Effectiveness (OEE) – especially machine availability – increase constantly in production nowadays. Unplanned down-times have to be prevented by efficient methods. Predictive, condition based maintenance represents a valuable approach for fulfilling these demands. Existing concepts lack of information, training data or interconnectedness. The objective of this paper is to present a novel approach in the context of Industrie 4.0 by using machine models with integrated uncertainties in the beginning, resolving these by methods of machine learning during operation and integrating both into a cloud-based service architecture.

The Need of Dynamic and Adaptive Data Models for Cyber-Physical Production Systems

Abstract Cyber-physical production systems (CPPSs) are the fundamental basis for the realization of the German initiative “Industrie 4.0,” which covers not only the usage of intelligent embedded devices and their interconnectedness, but also models for describing different processes according to the product’s life cycle. This article focuses on challenges regarding the integration of different views on urgent aspects, technologies, and paradigms to formulate one consistent modeling approach. Different use cases then describe the application of modeling and implementation concepts as well as benefits of new possibilities for process control. These are: model-based human-robot interaction for flexible assembly automation, a cloud-based approach for advanced condition monitoring, and product-centered control in the Laboratory for Machine Tools and Production Engineering (WZL)’s Smart Automation Lab.

Optimized state estimation by application of machine learning

The requirements concerning the technical availability as part of the overall equipment effectiveness increase constantly in production nowadays. Unplanned downtimes have to be prevented via efficient methods. Predictive, condition-based maintenance represents a valuable approach for fulfilling these demands, but precise models for state estimation are missing. From the manufacturers’ point of view the challenge consists in wear models with the capability of specifying the correct component’s state as well as providing reliable failure forecasts. Unfortunately, nowadays creation of wear models is based on specific stress tests or design of experiments from the manufacturer. The integration of the production phase or even data feedback and user knowledge does not take place. New potential is promised by cross-cutting technologies from ICT like cloud technologies—in general virtual platform concepts—or approaches of machine learning as enabling technologies. The objective of this paper is to adopt existing algorithms to the new application of condition monitoring in order to evaluate the applicability for automated training of robust wear models. In that context the most commonly used algorithms are described and the reader gets an impression what challenges have to be met when dealing with machine learning. A selection of about ten algorithms with 45 variants is evaluated for four different features within a packaging machine. In the outlook the embedding of the trained model in a cloud architecture is presented.

Demo: a realistic use-case for wireless industrial automation and control

This demo showcases a typical industrial automation scenario of a robot picking and placing work pieces from a moving conveyor belt. It involves sensory data inputs to a Programmable Logic Controller (PLC), and instructions from the PLC to a robot for the pick and place operation. The scenario requires communication from sensors to the PLC and from the PLC to a robot with ultra-low latency and extremely high reliability. While none of today’s wireless standards is capable of satisfying these stringent communication demands, our early prototype implementation of some of the design features of the future 5G standard enables industrial control using wireless communication. Our demo will show the live performance characteristics of the 5G design features for low latency and high reliability.

Hochproduktive Roboterkooperation zur spanenden Vorbearbeitung von Großbauteilen (HORuS)

Kurzfassung Der Beitrag beschreibt das aktuelle Forschungsprojekt HORuS, welches am Werkzeugmaschinenlabor WZL der RWTH Aachen und durch die Forschungsvereinigung für Programmiersprachen (FVP) bearbeitet wird. Ziel des Projektansatzes ist die Entwicklung einer durchgängigen CAD/CAM-Planungskette für die Programmierung eines Industrieroboters zur spanenden Bearbeitung von Großbauteilen. Durch Integration vorab identifizierter Prozessfähigkeitsbereiche wird eine Steigerung der Leistungsfähigkeit von CAM-Systemen und dem Produktionsprozess erzielt.

Identifikation und Lokalisierung von Werkzeugen und Objekten

Kurzfassung Der Beitrag beschreibt anhand eines Beispiels innerhalb einer Roboterzelle, wie Bluetooth 4.0 zur Identifikation und Lokalisierung von Werkzeugen im industriellen Umfeld eingesetzt werden kann. Ziel der vorgestellten Ansätze ist es zum einen, mittels Signalstärkemessungen und einer geeigneten Infrastruktur Kommunikationssignale entsprechend so auszuwerten, dass eine diskrete Positionsbestimmung innerhalb eines (Arbeits-)Raums möglich ist. Zum anderen sollen mittels eines speziellen Broadcast-Protokolls Informationen von Werkzeugen und anderen Komponenten an eine Zellensteuerung übermittelt werden. Die sich daraus ergebenden Möglichkeiten für neue industrielle Anwendungen werden dabei verdeutlicht.