Use case description
- Predictive maintenance monitors data from sensors on equipment to ensure it is in good condition and flag pre-emptively if there is a need to repair it, eliminating the need for scheduled maintenance, adding AI to “condition-based monitoring”
- For this to work effectively, dozens of sensors need to be employed combined with machine learning/AI at the edge to accurately predict the equipment’s condition
- The benefit of predictive maintenance is that it reduces downtime and increase the return on assets (up to 24%)
- Gartner predicts that spending on IoT-enabled predictive maintenance will increase to $12.9 billion in 2022 from $3.4 billion in 2018
Customer benefits – why edge?
- Advanced predictive maintenance requires data from 1000s of sensors to be collected and analysed – a huge amount of data, too expensive to send to a central server
- Edge computing can also simplify integration with other management systems, e.g. CRM
- Enterprises in some industries, e.g. manufacturing, are hesitant to use the cloud (data security)
Potential ecosystem partners
- Device manufacturers – companies are moving towards servitisation and providing maintenance services with the product/device
- Systems integrators to integrate outcomes of analytics into wider enterprise systems
- Cloud providers – solutions will move to IoT, therefore connecting to the cloud will becoming increasingly important, as insights need to be shared across multiple parties
- Maintenance companies who would leverage the analytics output
Industry mapping
*AEC: Architecture, engineering and construction
Case study: Atos
For more information, check our STL Partners’ Edge Use Case Service