ONE4ALL Project aims to reinforce the resilience and flexibility of the manufacturing lines through innovative modular and reconfigurable technologies centred on humans and sustainability. This objective will be reached through a series of interconnected innovations into 5 pillars.
The Data-driven Digital Twins are one of the pillars of I4.0 and an essential resource towards I5.0.
However, an adaptation is needed to surpass challenges such as frequently changing
demands and complex manufacturing systems.
In combination with data-driven simulation, DTs modelling reflects the real system more
accurately and enables AI, which boosts the computational potential and deeper understanding.
In line with Innovation 1, the accurate simulation of complex systems through the data-driven DTs enhances the performances and potential of the control and Decision Support System. Further on, thanks to the advancements in self-learning algorithms, it is possible to tackle the optimisation of a wide variety of problems and support a novel workforce speeding up their adaptation period. In addition, the simulation of “what-if” scenarios with the DTs will generate additional training data for the self-learning DSS.
Periodic questionnaires will be performed to spotlight workforce gap knowledge and their needs, plus a study of the customers’ needs to predict possible changes and anticipate disruptions. The technologies’ development process will holistically integrate this information to ensure workforce safety and necessities.
Continuous sustainability assessment and environment impact: sustainable aspects will be closely analysed to evaluate, along the project life cycle, the evolution of the technical, economic and environmental impact associated with ONE4ALL innovations.
The IOP aims to interconnect all ONE4ALL modules (digital and physical) and present the information gathered in real-time through user-friendly interfaces to improve the understanding among end-users (manager and operators) concerning what is happening in the production line and how to organise and control it to improve the performance. The information and assessment provided
covers sustainability aspects, products’ quality, resource consumption, production modules activities, orders and business analysis.
Covering the physical infrastructure, plug-and-produce self-reconfigurable cobots will be developed embedded with IIOT devices. Firstly, the modularity of the process chain thanks to the mobile cobots as production modules, enabling the auto-scale of the production according to the demand. Secondly, the modularity of the production module itself. Lastly, the cobots will integrate IIOT devices and high-quality sensors to monitor key parameters in real-time. The cyber-interconnectivity of all devices and data gathering will ease the efficient organisation, reconfiguration and integration with the IOP.
