Agent-based cyber-physical production systems for Industry 4.0


   Faculty of Engineering and Informatics


About the Project

This project aims to develop novel methods and software tools for the implementation of highly adaptive multi-agent systems for manufacturing control, applying plug-and-produce technology to cyber-physical systems. These multi-agent systems will use effectively the available resources (e.g. robots, assembly stations, inspection devices) to adapt to changing production scenarios and will offer a dramatic reduction in deployment cost and time, as well as improved operational efficiency and equipment utilisation. This research is related to the Industry 4.0 strategic initiative. The ultimate objective is the creation of "meta-automation" software that will enable reconfiguring cyber-physical production systems and eliminating disturbances with minimum human intervention.

The competitiveness of manufacturing companies in modern markets increasingly depends on cost-effective flexible automation technologies. The reconfiguration of a cyber-physical production system, for increasing its capacity or introducing a new product variant, requires extensive human intervention and, therefore, it is time-consuming and expensive. Plug-and-produce systems introduced some levels of autonomy. However, there are currently no known plug-and-produce platforms that can address the full cycle of deployment, control and adaptation of heterogeneous mechatronic components, in particular components from different vendors. Despite achievements to date in the fields of multi-agent systems, plug-and-produce technology and reconfigurable manufacturing systems, fundamental challenges remain. The full potential of the agent-based plug-and-produce approach is still being uncovered, including the ability to handle complex real-time tasks.

This project will support a paradigm shift from a conventional, resource-intensive and largely human-driven configuration and system integration process to plug-and-produce cyber-physical systems with self-awareness and adaptation capabilities. Machine learning and, in particular, deep learning techniques will be used. The key objectives are:

  1. To define a vision and software architecture of a multi-agent system framework for plug-and-produce cyber-physical systems.
  2. To define a plug-and-produce multi-agent approach for the integration of modules from different equipment suppliers and heterogeneous control systems inside one production line.
  3. To develop methods for real-time system awareness using integrated sensor networks, and self-learning capabilities for a robust process optimisation of the entire manufacturing system, as well as individual production units.
  4. To design advanced distributed control infrastructures and scalable cloud architectures enabling resource virtualisation.
  5. To design smart human-machine interfaces that can support proactively the user throughout system evolution.

How to apply

Formal applications can be made via the University of Bradford web site.


References

1. Daniele Scrimieri, Omar Adalat, Shukri Afazov, and Svetan Ratchev. An integrated data- and capability-driven approach to the reconfiguration of agent-based production systems. The International Journal of Advanced Manufacturing Technology, 2022, https://doi.org/10.1007/s00170-022-10553-0.
2. Daniele Scrimieri, Shukri M Afazov, and Svetan M Ratchev. Design of a self-learning multiagent framework for the adaptation of modular production systems. The International Journal of Advanced Manufacturing Technology, 115(5):1745–1761, 2021.
3. Daniele Scrimieri, Nikolas Antzoulatos, Elkin Castro, and Svetan M. Ratchev. Automated experience-based learning for plug and produce assembly systems. International Journal of Production Research, 55(13):3674–3685, 2017.
4. Daniele Scrimieri, Robert F Oates, and Svetan M Ratchev. Learning and reuse of engineering ramp-up strategies for modular assembly systems. Journal of Intelligent Manufacturing, 26(6):1063–1076, 2015.

Email Now


PhD saved successfully
View saved PhDs