Skip to content
Okko Oulasvirta
Energy & Utilities

Asset Health & Field Operations Twin

Interactive demonstration

One live view of an asset — its telemetry, its condition, the weather it faces and the crew that can reach it — that turns an anomaly into a dispatched job.

The decision it supports

This asset is behaving abnormally. How serious is it, and what is the right field response right now?

What changes

Fewer failures that could have been caught, crews sent to the right asset with the right part, and a shorter path from first anomaly to work on site.

Data domains

  • Assets
  • Grid and network
  • Field service
  • Weather
  • Finance and cost
Loading the application…

The workflow

  1. 01An anomaly is detected on an asset from live telemetry
  2. 02Its recent readings are shown against normal behaviour and past faults
  3. 03Condition, age and service history are assembled into a risk score
  4. 04Local weather and forecast exposure are laid over the asset
  5. 05The operational impact of a failure here is estimated
  6. 06Nearby field teams, their skills and their distance are shown
  7. 07The operator weighs the options and dispatches a job or schedules an inspection
  8. 08A work order is raised in the field system and the outcome is recorded

Platform capabilities most relevant here

  • Eventstreams

    Let operational applications react to what is happening now, not what happened yesterday.

  • Eventhouse / KQL

    Ask questions of high-volume machine and event data fast enough to act on the answer.

  • OneLake

    One governed copy of enterprise data that analytics, AI and applications can all build on.

  • Ontology

    Encode the vocabulary, relationships and rules your business already works with.

  • AI functions

    Apply language models to business data as a normal part of a data pipeline.

  • Fabric Apps

    Build the application where the governed data already lives, instead of copying it out.

  • Enterprise APIs

    Turn a decision into a change in the system that actually runs the process.

  • Event-driven triggers

    Notice the condition that matters and start the response automatically.

Not every application needs every capability. This is the subset that this decision actually depends on.

Talk about building this