System for Preparing Digital Twin Scenarios for Decision Review

The problem

In day-to-day operations, sensor history, the asset model and operating limits are held in separate records and files, preventing the team from reviewing the same case in a single view.

As a result, the link to source evidence can be lost while preparing a scenario comparison, leading to repeated checks and uncertainty about the basis for the decision.

Incomplete automation may overlook a disconnected sensor or conditions outside the model, while poorly controlled automation risks a simulation being mistaken for an instruction.

What we set out to improve

• Time required to prepare a scenario comparison for review
• Correct routing of cases involving a disconnected sensor or conditions outside the model to the appropriate specialist queue
• Recording of recommendations corrected or rejected by the process engineer

How the system works

1. 01 Retrieve sensor history, asset model and operating limit data from an authorised source
2. 02 Verify the source system, record identifier and recency information
3. 03 Transform the fields into the target process schema
4. 04 Prepare a scenario comparison draft
5. 05 Compare the draft with business rules and source records
6. 06 Check for exceptions involving a disconnected sensor or conditions outside the model
7. 07 Obtain the process engineer's approval, correction or rejection
8. 08 Write the input, recommendation, changes and final decision to the audit log

Methods we used

• Source-traceable data extraction from sensor history, the asset model and operating limits
• Structured output that restricts scenario comparison fields through business rules
• An exception gate that separates cases involving a disconnected sensor or conditions outside the model
• A queue that shows the source and recommendation together for the process engineer
• Duplicate-processing controls and rollback records to mitigate the risk of a simulation being mistaken for an instruction

Where people stay involved

Data and security

Only the fields required for the task are processed from sensor history, the asset model and operating limits. Source-system permissions remain in force, and personal or commercially sensitive data is minimised before being provided to the model. Every read, recommendation, human amendment and write to the target system is logged.

Who this suits

Frequently asked questions