aGent Oriented Zero Defect Multi-stage mANufacturing

Funder

Organizational Unit

Publications

Smart inspection tools combining multi-agent systems and advanced quality control

Publication . Barbosa, José; Leitão, Paulo; Ferreira, Adriano; Queiroz, Jonas; Angione, Giacomo; Lo Duca, Giulia

Although the everlasting goal of achieving a zerodefect production system is not new, the current state of the art has not yet allowed to reach this objective. This paper describes the architectural system foundations of the European R&D GO0DMAN project where a multi-agent system is developed as the mean to provide a real-time, multi-level and multi-stage approach to reach a zero-defect production system in multi-stage environments. Particularly, the paper focuses the integration of software agents and quality control stations forming smart inspection tools, aligned with the cyber-physical systems principles. The proposed approach is validated using an electrical motor testbed, where the agent-based system allows the digitization of the running testing system in a multi-stage schema.

2018Conference object

Restricted access

Multi-agent system architecture for zero defect multi-stage manufacturing

Publication . Leitão, Paulo; Barbosa, José; Geraldes, Carla A.S.; Coelho, João Paulo

Multi-stage manufacturing, typical in important industrial sectors, is inherently a complex process. The application of the zero defect manufacturing (ZDM) philosophy, together with recent technological advances in cyber-physical systems (CPS), presents significant challenges and opportunities for the implementation of new methodologies towards the continuous system improvement. This paper introduces the main principles of a multi-agent CPS aiming the application of ZDM in multi-stage production systems, which is being developed under the EU H2020 GO0D MAN project. In particular, this paper describes the MAS architecture that allows the distributed data collection and the balancing of the data analysis for monitoring and adaptation among cloud and edge layers, to enable the earlier detection of process and product variability, and the generation of new optimized knowledge by correlating the aggregated data.

2018Conference object

Open access

Implementation of a multi-agent system to support ZDM strategies in multi-stage environments

Publication . Barbosa, José; Leitao, Paulo; Ferreira, Adriano; Queiroz, Jonas; Geraldes, Carla A.S.; Coelho, João Paulo

This paper describes the development of a multiagent system (MAS) to support the implementation of zero-defect manufacturing strategies in multi-stage production systems. The MAS infrastructure, combined with on-line inspection tools, data analytics and knowledge generation, constitutes a suitable approach to integrate process and quality control in multi-stage environments. This will allow the early detection of product defects, the adaptation to operating condition changes and the optimisation of manufacturing processes. This type of integrated management structure is aligned with a zero-defect manufacturing production model which is of paramount importance in the actual state-of-the-art manufacturing paradigms. As a proof of concept, the devised manufacturing supervision model was deployed into an experimental multi-stage system that run a set of several tests on electrical motors. The agent-based solution was implemented using the JADE framework and the exchange of information structured by proper data models and industrial based Internet-of-Things and Machine-to-Machine technologies, such as OPC-UA, REST and JSON. The obtained results demonstrate the suitability of the devised integrated management model as a vehicle to achieve dynamic and continuous system improvement in multi-stage manufacturing environments.

2018Conference object

Restricted access