Publicação
Multi-agent system architecture for zero defect multi-stage manufacturing
| Resumo: | 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. |
|---|---|
| Autores principais: | Leitão, Paulo |
| Outros Autores: | Barbosa, José; Geraldes, Carla A.S.; Coelho, João Paulo |
| Assunto: | Cyber-physical systems Multi-agent systems Multi-stage manufacturing Zero defect manufacturing |
| Ano: | 2018 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Instituto Politécnico de Bragança |
| Idioma: | inglês |
| Origem: | Biblioteca Digital do IPB |
| Resumo: | 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. |
|---|