What's new in Dynamics 365 for service industries? Part 2
- Posted on April 6, 2018
- Estimated reading time 4 minutes
This article was originally written by Avanade alumn Ismael Quteifan.
In my previous blog post, I highlighted three new functionalities added to Dynamics 365 that are core to the operation of the Service, Maintenance and Asset Management industries. In this post, we will see how new and existing features of Dynamics 365 can be deployed to the industries’ solution to take it to a new level.
We manage assets and fleets in ERP systems for a reason: the sheer amount of data and transactions involved. Data hoarding is not the ultimate goal here. The goal is data summaries, KPIs and intelligence into how well your asset, service or fleet management system is performing.
There are a few "out of the box" Power BI dashboards embedded in Dynamics 365 workspaces, but that's only a sample of what can be achieved with this powerful tool. It is common knowledge now that pre-configured reports will always be customised. This is Microsoft's philosophy in expanding the reporting tool with the capabilities of Power BI, which can also join static and dynamic data from other sources like your offline Excel, Access or legacy system databases. That is, of course, if you don't decide to migrate them into Dynamics 365 as extended data entities.
There are three levels of maintenance: corrective after the event, preventative based on some schedule and then there is predictive maintenance based on clever algorithms and continuous condition monitoring. Microsoft has empowered its Dynamics 365 with Azure Machine Learning services as an extension to its Field Service module. Oil sample analysis results, various counters, temperature, pressure and load sensors can now be solved simultaneously to predict when the next maintenance should be performed. This way we can reduce maintenance downtime to when it is actually required and optimise maintenance stock holding cost. Safety is also improved since there are more dimensions measured and failures between preventative maintenance periods can be predicted.
A good example is the Rolls Royce and Microsoft collaboration on machine learning and Cortana Intelligence – see video below.