Skip to main content

Global supply chains, market fragmentation, mass customization and shorter product life cycles have scaled up competition among companies which give rise to the need for introducing cognitive abilities through flexible and easily reconfigurable production systems. In this sense, there is unmined potential for the European manufacturing industry to be more innovative, productive and competitive whilst using fewer resources and reducing environmental impact. The emerging cyber-physical system (CPS) presents a significant opportunity to implement smart manufacturing in the Industry.
This project, called Social Network of Machines (SOON), proposes to investigate the impact of the use of autonomous social agents to optimise manufacturing process in the framework of Industry 4.0. In this context, “agents” are process, data, things, and people. "Social" means that cyber-physical entities will act autonomously in order to optimize an industrial process following behaviours models inspired by human social networks. Currently, in Industry 4.0, smart entities do exist. However, intelligence is localised and intelligent heterogeneous entities cannot communicate together even inside the same shop-floor. Our motivation comes from the observation that, if we want to create a real Internet of Everything that brings together processes, data, things, and people, all these entities have to be connected and follow a shared, easy to understand paradigm.
To address this point, SOON proposes a holistic multi-agent framework that encompasses machines and humans. The presence of human operators is therefore crucial both to teach to and to learn from software agents, via deep learning and data mining algorithms. Agents will take decisions merging and analysing big and heterogeneous data produced by sensors, automation and information systems (such as enterprise resource planning and manufacturing execution system), and human actions.
The design and evaluation of the SOON system will be performed through predictive maintenance scenarios in collaboration with three different industrial companies (in Slovakia, Spain and Switzerland). Such collaboration will enable the project consortium at assessing the application of the developed solution on concrete industrial scenarios. The three selected scenarios cope different problems within the industrial manufacturing. The first scenario pays attention to the reliability of the data provided by sensors that are key inputs in other process models and calculations (width, thickness, temperature, etc.) and whose measurement is very difficult because it is influenced by noise, distortions, etc. Errors and deviations entails quality problems that will result in nonconformities. The second scenario is thought for manufacturing environments requiring extreme accuracy (tool machines with precision requirements in the order of 1 µm) and with intrinsic and extrinsic tolerances. Finally, the third scenario is more focused on equipment reliability. These different scenarios will assure that the results will be exploitable beyond the project (e.g., portability to different industrial environments). In the three cases, the project is focused on the specific task of predictive maintenance.
In agreement with the industrial partners, the valuable data acquired during the project that are not confidential will be published in open repositories and made available to the scientific community.
We believe that the arrival of Industry 4.0 revolution combined with recent improvements in machine learning, and the application of autonomous multi-agent architecture can finally bring disruptive innovation in industrial process optimization and modelling.

Call Topic: Big data and process modelling for smart industry (BDSI), Call 2017
Start date: (36 months)
Funding support: 739 503 €

Project partners

  • University of Applied Sciences and Arts Western Switzerland - Switzerland
  • TORNOS SA - Switzerland
  • Universidad de Oviedo - Spain
  • ArcelorMittal Innovación Investigación e Inversiones S.L. - Spain
  • Petru Maior University - Romania
  • Slovak Academy of Sciences - Slovakia
  • Mat-obaly s.r.o. - Slovakia

Main results

The SOON project investigates the impact of the use of autonomous social agents to optimise manufacturing processes in the framework of Industry 4.0. "Social" means that cyber-physical entities will act autonomously in order to optimize an industrial process following behaviour models inspired by human social networks. Currently, in Industry 4.0, smart entities do exist. However, intelligence is localised and intelligent heterogeneous entities cannot communicate together even inside the same shop-floor. Our motivation comes from the observation that, if we want to create a real Internet of Everything that brings together processes, data, things, and people, all these entities have to be connected and follow a shared, easy to understand paradigm.
In this project, we propose a holistic multi-agent paradigm that encompasses machines and humans. The presence of human operators is therefore crucial both to teach to and to learn from software agents, via deep learning and data mining algorithms. Agents will make decisions merging and analysing big and heterogeneous data produced by sensors (vibration, temperature, etc.), automation and information systems (such as enterprise resource planning and manufacturing execution system), and humans in real-time.

The first year of the SOON project has been dedicated to the definition of the project scenarios and the data handling approach. Together with the companies that are partners in the project, we have identified the most relevant scenarios and use cases. In particular, we have identified 6 scenarios (for a total of 11 use cases) that can be addressed with the proposed solution. The most relevant scenarios focus on Predictive and Smart maintenance needs. A general multi-agents architecture is being defined and an ontology describing the different entities has been realized. In addition, a multi-agent infrastructure (in which every machine is an agent) based on Reinforcement Learning (RL) has been realized and its optimization and evaluation is ongoing. The solution allows the design of various layouts of machine workshops (see for instance the figure below) with different kinds of industrial machines. The RL algorithm aims at optimizing the overall production process taking into account possible failures and the limitation of resources.

Key exploitable results

The overall objective of this project is to demonstrate the added value of using a social human-machine network to model and optimize smart industries processes. The project is at a first stage, nevertheless we expect that the final results could have a large impact for the scientific community and, in a more applied perspective, European industry. The main goal of the project is to propose smart solutions to reduce maintenance costs and optimize performances in different industrial sectors where big data and high complexity is involved.

Scientific: The scientific results can be summarized as follow:

  • Novel predictive maintenance algorithms based on social multi-agents approach.
  • An open datasets with manufacturing data to share with the scientific community.
  • An evaluation framework to ensure repeatability and validate the resilience of the proposed approach.

Industry: We expect that at the end of the project, the industrial partners directly involved in the project will be the first to develop and deploy the project outcomes toward industrial solutions. The outcomes from industrial demonstrations will be communicated through public reports, industrial fairs and workshops. Technological innovations can bring undeniable advantages such as safer workplaces and more efficient, pleasant and sustainable industrial processes.

Socio-economics: The most significant impact of the SOON project from a societal perspective will consist in industrial innovation through IoT integration in Industry 4.0. The conflictual relation of humans and (industrial) AI is a hot topic in the Industry 4.0 community. We hope that the social network paradigm that we propose will facilitate the integration of AI solutions without neglecting the role and the wellbeing of humans involved in industry 4.0.

Publications in Open Access

Search