DIAMOND: distributed multi-agent architecture for monitoring and diagnosis

Abstract

This paper presents a concept for building up a distributed monitoring and diagnosis system for complex industrial applications. For this purpose, a hierarchical organized model with distributed, cooperating agents was developed. The hierarchical aspect guarantees a predictable behaviour of the system with a high performance and the flexibility of the system is ensured by the federal distribution (Bongaerts 1998). By using this approach, a modular component diagnosis and monitoring (CDM) system is realized that enables the integration of legacy monitoring and diagnostic tools, specific to the application area. Universal applicable mechanisms were found to perform diagnostic processes and to improve the quality of a diagnosis by handling different diagnostic mechanisms in parallel and by applying conflict resolution algorithms. This software architecture for monitoring and diagnosis was developed by the University of Karlsruhe in cooperation with three industrial partners and one research institute within the framework of the EU Esprit Program: ‘DIAMOND: DIstributed Architecture for MONitoring and Diagnosis’ (DIAMOND 2002).

Keywords:

• Multi agent-system
• Distributed architecture
• monitoring
• diagnosis
• conflict resolution
• CORBA
• FIPA-ACL, XML

Acknowledgements

This research work has been performed at the Institute for Process Control and Robotics, Prof. Dr.-Ing. H. Wörn and Prof. Dr.-Ing. R. Dillmann, Department of Computer Science, University of Karlsruhe, Germany, in collaboration with Union Fenosa Generación, SA, Spain, KUKA Roboter GmbH, Germany, GenRad Ltd, UK, Instituto de Investigación Tecnológica – Universidad Pontificia Comillas, Spain and SATE srl, Italy. The research is partly funded by the European Commission in the DIAMOND project under contract no. EP 28735.

Professor H. Wörn studied electrical engineering at the University of Stuttgart. He obtained his PhD at the Institute for Control of Machine Tools and Manufacturing Equipment of the same university for his work ‘Mehrprozessorsteuerungssystem für Werkzeugmaschinen mit standardisierten Schnittstellen’. He then worked in industry for KUKA Schweißanlagen und Roboter GmbH where he advanced to a leading position in research and development. Professor Wörn is an internationally acknowledged expert in robotics and automation. His expertise includes robot applications, robot controls sensors for robots and programming and simulation of robotic installations. Since 1997 he has headed the Institute for Process Control and Robotics at the University of Karlsruhe as professor for complex systems in automation and robotics. His research directions are: planning, programming, control, diagnosis and sensor systems for industrial robots; autonomous mobile robots, microrobots, service robots, telerobots and autonomous vehicles; planning and simulation of manufacturing systems and enterprises; robot and sensor-assisted surgery; microassembly; modelling of complex systems in production and medicine.

Dr Thomas Längle studied Computer Science at the University of Karlsruhe in Germany, where he received his master of science in 1993 with work on localization of robot systems. Then, he moved to the Institute for Real-time Computer Systems and Robotics at the University of Karlsruhe in Germany, where he worked as a researcher in the robotics group. Since 1995, he has been leader of the research group ‘Intelligent Robots’; he received his PhD in December 1996. In January 1997, he moved to the Institute for Process Control and Robotics at the University of Karlsruhe, where he works in the position of an assistant professor as leader of the research group ‘Industrial Robots’. The group consists of 10 full-time researchers PhD students and several master's students. His research interests include different aspects of robotics and manufacturing, intelligent control, multi-agent systems, diagnosis and teleservice.

Martin Albert studied physics at the University of Karlsruhe in Germany, where he received his master's in solid-state physics. He currently works as researcher in the areas of distributed diagnostic software at the Institute for Process Control and Robotics at the University of Karlsruhe (TH). He is involved in the European-funded project MAGIC (Multi-agent-based Diagnostic Data Acquisition and Management in Complex Systems) and develops a communication infrastructure, based on a multi-agent approach. Martin is a specialist in distributed software systems and has over four years’ experience with multi-agent systems. His research interests include different aspects of manufacturing and diagnosis, distributed software, ontologies and multi-agent architectures.

Dr Arif Kazi studied Mechanical Engineering and Mechatronics at the Universities of Darmstadt and Braunschweig in Germany and at the University of Waterloo in Canada. After completing his degree, he did his PhD thesis on medical robotics at the Research Centre, Karlsruhe. Dr Kazi started working for KUKA Robotics in Augsburg, Germany, in 1998. After coordinating research projects for more than four years, he now acts as KUKA's technology manager for programming and simulation.

Attilio Brighenti graduated cum laude in Mechanical Engineering from Bologna University in 1976. He worked in applied R&D and technology development at E. WEBER Carburettors and at Tecnomare where he specialized in marine systems engineering and processes for the offshore industry and was appointed R&D Manager for Systems Development. In 1991 he setup an independent technology consulting activity, and in 1998 he founded SATE srl. His professional experience also includes teaching at the University of Naples and the publication of nearly 50 papers on international journals.

Santiago Revuelta Seijo was born at Ferrol, Spain, in 1968. He is mining engineer fromt the Polytechnic University of Madrid in 1993 and he has worked at Union Fenosa since 1995. Previously he worked at lberdrola as a junior engineer in projects related to photovoltaics. Inside Union Fenosa he stayed for two and a half years at Anllares Thermal Power Plant supervising the fuel purchases needed for the plant. Afterwards he moved to the R&D department of Union Fenosa Generación and was in charge of implementing innovative solutions and technologies at different business units to increase the profitability of them. Since august 2003 he has developed his activity in the R&D department of Union Fenosa Corporate.

Chris Senior is a Senior Technologist and research engineer with the Diagnostic Solutions division of Teradyne Inc., based in Manchester, UK. Chris currently works in the areas of Telematics and Diagnostics Software Research. He is a specialist in distributed software systems and has over Five years’ experience with internet, wireless and Java technologies, and is currently in his third year of reading for an Engineering Doctorate as a researcher with the Applied Mathematics and Computing (AMAC) group, in the School of Engineering at Cranfield University. After joining Teradyne in 1996, Chris worked in the field of distributed diagnostic systems, undertaking published research as part of the EC ESPRIT-funded project DIAMOND (Distributed Architecture for Monitoring and Diagnosis). Prior to this, Chris read for a bachelor's degree in Electronic and Electrical Engineering at the University of Salford in Manchester.

Dr Miguel A. Sanz Bobi is a Professor at the Engineering School of the Universidad Pontifica Comillas, Madrid, Spain, dividing his time between teaching and research in the field of artificial intelligence. He has been the main researcher in more than 30 industrial projects over the last 19 years related to the diagnosis in real-time of industrial processes, incipient detection of anomalies based on models, knowledge acquisition and representation, reliability and predictive maintenance. All these projects have been based on a combination of artificial intelligence, new information technologies and data mining techniques.

Jose Villar Collado obtained his Electronic Engineer degree from the School of Industrial Engineering (ICAI) of the Universidad Pontificia Comillas in 1961. He is currently a member of the research staff at the Instituto de lnvestigación Tecnológica IIT (Institute of Applied Research) belonging to the Universidad Pontificia Comillas, where he also teaches electronics, instrumentation and control. He obtained his PhD in fuzzy logic applied to diagnosis of industrial processes in 1997. His research interests include knowledge-based systems, fuzzy logic, fuzzy control, electricity markets, multi-agent systems, electronics and online monitoring and diagnosis.