Distributed Cyper Physical Production Systems (DCPPS), have many promising advantages such as flexibility and scalability. A distributed approach facilitates adaptation of a production facility setup to changing market demands, such as the need for product variants, single lot production or new products. Moreover, it allows to better react to disturbances and changes during operation, like dynamic routing and short-term production re-scheduling.
In distributed systems, however, coordination and collaboration between individual components are a challenge. The interplay of distributed components increases complexity of the system, definition of control strategies, and verification in particular concerning, fault propagation and fault handling which arises in the absence of a central control unit.
Fault propagation can cripple decision making processes and can be the bottleneck in the overall system. Therefore, it is of paramount importance to create an architecture facilitating autonomous detection and countermeasures by using intelligent semantic abstractions, data fusion and integration techniques to enhance available data, advanced reasoning techniques for fault detection and tolerance, and functional testing for systems diagnostics and prognostics. As a result, such a self-aware system can proactively detect and mitigate problems related to its operation.
The goal of the SAMBA project is to explore various methodologies and architectures which can enhance distributed automation systems with scalable learning capabilities, self-discovery and self-aware monitoring and cognitive decision makings that will ease and reduce engineering and maintenance of the system. The advantage of such a solution is that engineering efforts can be focused on the normal operation and all the flexibility of distributed systems can be used to autonomously adjust the system and mitigate faults in order to avoid stoppage of the production process. Efficiency, advantages and disadvantages of each explored method will be evaluated in simulations based on IEC 61499 function blocks and data provided by the industrial partner.
The outcome should provide the foundation of implementation of aforementioned self-discovery, self-aware data integration and semantic interpretation, and cognitive decision making methodologies in a real-world adaptive DCPPS.
** This exploratory project (FFG 855426) was funding by BMVIT and the Austrian Research Promotion Agency (FFG) within the programme ICT of the Future (4. call 2015)
|Duration||01/09/2016 - 31/10/2017|
|Program||FFG IKT der Zukunft 4. Call|
|Principle investigator for the project (Danube University Krems)||Priv.-Doz.Dipl.-Ing.Dr. Thilo Sauter|
|Project members||Dipl.-Ing. Dr. Aleksey Bratukhin Dipl.-Ing. Albert Treytl|
Grau, A.; Indri, M.; Bello, L.; Sauter, T. (2017). Industrial robotics in factory automation: From the early stage to the Internet of Things. IEEE, IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society: 6159-6164
Siafara, L.; Kholerdi, H.; Bratukhin, A.; Taherinejad, N.; Wendt, A.; Jantsch, A.; Treytl, A.; Sauter, T. (2017). SAMBA: A self-aware health monitoring architecture for distributed industrial systems. IEEE, IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society: 3512-3517
Industrial robotics in factory automation: From the early stage to the Internet of Things
IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, Beijing, China, 02/11/2017
SAMBA: A self-aware health monitoring architecture for distributed industrial systems
IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, Peking, China, 02/11/2017