One of the key challenges of industrial enterprises is often reducing the unplanned machine downtime to increase overall equipment effectiveness (OEE) and hence to output productive supply and service. This is due to the reason of insufficient historical and real-time AI-driven data analysis to predict assets health status and hence enterprises are limited to provide prompt remedy before the expected failure. Therefore, intelligent maintenance is about using data to make automated decisions, predictions, and real-time optimisation across the end to-end value chain.

Solution Requirement:
- Develop an AI model with Machine Learning (ML) or Machine Vision (MV) that can further improve the availability and service levels of end-to-end digital services.
- Look at the components of the end-to-end digital services and identify the critical problematic components that will impact the operational of digital services.

- Provide the predictive steps that can be taken to avoid that any of the problems can happen and / or can have an impact.
- Make it clear as well in which order these AI-ML (or maybe AI-MV steps) should be implemented and for each step the positive impact on the availability of the digital services and why.
- Indeed, we do not expect that you do develop the relevant AI-ML models, but make it clear what these models should predict and, to get to that and what data types (in detail) need to be used for that?
- Validate whether these data types are or can be made available. And, how to apply 5G into the solution.