<p>Mass personalisation is becoming a reality goal. It requires manufacturing industry to gain smart manufacturing capabilities to responsively and flexibly produce personalised products with dynamic batch sizes in a cost-effective way. However, current manufacturing automation technologies have been rigid and inflexible, which are designed for mass production and mass customisation manufacturing paradigms. To address these challenges, a manufacturing system is required to adopt self-organisation cognitive capabilities to achieve flexible, autonomous, and error-tolerant production in manufacturing system, in a supply network, in customer needs. Within the context, the concept of Self-Organising Manufacturing Network has been proposed to meet the requirements of mass personalisation. In this paper, a four-layer self-organising manufacturing network architecture is proposed. In this architecture, manufacturing resources are encapsulated as Semantic Twins to make peer-to-peer interoperable communications in the manufacturing network. During the interaction of semantic twins, autonomous configuration and optimisation of manufacturing schedules are achieved. This architecture is modelled by agents, and the autonomy of agents is supported by multi-agent technologies. The future research directions to achieve a self-organising manufacturing network also discusses in this paper. The proposed architecture promises adaptive operations towards mass personalisation.</p><p>Keywords: Mass personalisation; Smart manufacturing; Manufacturing system control; Self-organising manufacturing network; Multi-agent manufacturing system; Semantic-aware cyber-physical system; Semantic Twin</p>

Multi-Agent-Based Self-Organising Manufacturing Network Towards Mass Personalisation

Paper Proceedings: https://asmedigitalcollection.asme.org/MSEC/MSEC2021/volume/85062

2021 International Manufacturing Science and Engineering Conference (MSEC2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.