Self-aware Twin for Zero Defect

Current manufacturing platforms rely heavily on quality inspection at the end of the production line, where up to 100% of the parts will be fully checked, especially for high-end products. This normally leads to high costs, requires skilled workers, and sometimes reduces the speed of the line. Most importantly, product quality inspection does not prevent the generation of faulty products, it just prevents their delivery to the client. If the defects are detected only at the end of production line, the fault prognosis is quite difficult and trial-and-error-based, since it is not very clear which production step or process has produced it. Investigation of fault causes can be time- demanding, interrupts line operation, and causes huge amount of scrap and waste or time and money lost on rework operations. In this context, SelfTwin proposes a novel quality control and monitoring system based on smart Digital Twins (DTs) that are able to predict the evolution of the product along the manufacturing line in the most efficient and effective way to ensure product quality and reduce the appearance and propagation of defects23. The smart DT will predict the values of the critical product KPIs and will be continuously updated with the actual values of the critical parameters of influence, measured in-line, at the same pace as the line. The updated prediction of the DT is then used to monitor the process and act upon subsequent phases of the production, in order to adjust some process parameters, so that the final product meets its exact design specifications, avoiding defect propagation and reaching zero-defect production. Upon the detection of defects, the system will inform the workers at the shopfloor or, in more automated setups, perform automatic calculations and modify the process parameter values though adaptive control systems. In this way, not only the generation of defects will be prevented but also at system level, it will prevent the propagation of the defects to downstream processes and products.

Main innovation is the concept of the smart Digital twins (DT) with advanced sensors (various types) that will allow a real-time feedback loop between the digital twin and the production line, so that the DT is updated continuously in real time data from in-situ measurements of the critical process/product parameters (to both update the parameter values and the accuracy of the DT) and the DT provides information to monitor and adjust the process. This will lead to zero-defect strategy with a real-time feed-forward loop in which the generation of defects will be predicted by the DT and the corrective measures will avoid generation of the defects in real manufacturing lines.

The vision of this proposal is to enable zero defect manufacturing by providing a novel control and monitoring system based on smart Digital Twins that leads to higher product quality and can be used by manufacturing companies in their transformation in zero defect data-driven economy. This vision will be realized through the following list of objectives:

• Define a new concept of Self-aware Digital Twins for realizing ZDM
• Develop and test a set of advances services for realizing SelfTwin
• Integrate services with selected component in Data4AI Platform
• Validate the SelfTwin solution
• Enabling a wide exploitation