Daytime Project

Project Profile


A novel combination of digital twinning and predictive maintenance

Despite the benefits that predictive maintenance and digital twinning can bring to smart manufacturing, there are currently few functioning examples. By integrating findings from industrial use-cases in a generic value chain model, the ITEA project DayTiMe intends to plug this gap in the market.


Based on the Industry 4.0-related concept Condition-Based Maintenance (CBM), predictive maintenance (PdM) determines the condition of in-service equipment to decide when maintenance is warranted. This creates enormous time and cost savings compared to traditional maintenance. However, algorithms for Internet of Things (IoT) PdM platforms are only as good as the quality of the data labelling. While sensors and Cyber-Physical Systems (CPS) that measure production parameters can be used to obtain masses of raw data, digital twinning holds the key to real-time, easy- to-understand monitoring of processes and systems.


The DayTiMe (Digital Lifecycle Twins for Predictive Maintenance) project revolves around 14 industrial use-cases in fields like healthcare, energy and telecoms. For each of these, a novel PdM solution (concept, technology, methods and prototype implementation) will be created alongside a digital twin-based demonstrator comprising CPS visualisation, an underlying behaviour model, bi-directional data connectivity, learning intelligence and interfaces. Algorithms and machine learning models will be developed to analyse data, leading to a comprehensive report on how sensor data can identify predictive maintenance actions. The findings will also be converted into tools and combined in a method toolbox which will support everything from CPS creation to new business models. Organisations can thus choose the method that fits their needs. Finally, the question of where data should be saved and maintained will be answered through functional IT-backbones for the digital twins and use-cases.


DayTiMe is beneficial to both businesses and individuals. As part of the use- cases, data-driven business models will be developed to generate revenue and the method toolbox will generalise and disseminate findings to industry at large. The market expectations are high: maintenance costs should be reduced by 20-25%, breakdowns by 70-75% and downtime by 35-45%, leading to an increased output of 20-25%. PdM also allows problems to be fixed before they occur, creating safer employee conditions – an increase in wellbeing that will result in improved efficiency and therefore a better quality of product. In areas such as automotive, this has a knock-on effect for customer safety, helping to decrease healthcare costs across Europe.

Project Website