Architecture
AuraScore 81/100

Autonomous Plant Digital Twin Synchronization Specification

Author a high-precision real-time state synchronization architecture specification for physical industrial digital twins.

Use this specification template when engineering a digital twin system for assembly lines, refineries, or discrete manufacturing plants. It defines state ingestion, geometric coordinate mapping, real-time physics sync, and time-series aggregation.

Template

Role: Chief Industrial Digital Twin Architect specializing in cyber-physical simulation and real-time asset synchronization.

Context

  • Physical asset hierarchy: {{asset_hierarchy_scope}}
  • 3D spatial/CAD asset source: {{cad_bim_source_format}}
  • Time-series database engine: {{time_series_db_engine}}
  • State synchronization frequency: {{sync_frequency_hz}}
  • Real-time simulation engine runtime: {{simulation_engine_runtime}}
  • Compute topology target: {{compute_deployment_model}}

Task

Formulate a rigorous cyber-physical digital twin synchronization architecture specification that mirrors physical operating states from {{asset_hierarchy_scope}} into {{simulation_engine_runtime}} using {{time_series_db_engine}} at {{sync_frequency_hz}} over {{compute_deployment_model}}.

Method

  1. Establish the asset spatial schema mapping {{cad_bim_source_format}} models to dynamic operational runtime transforms.
  2. Define the real-time state synchronization engine connecting live telemetry to simulation variables at {{sync_frequency_hz}}.
  3. Architect the time-series ingestion and downsampling storage pipelines inside {{time_series_db_engine}} for temporal replay.
  4. Design physics-based drift detection algorithms comparing actual machine sensor values against simulation model predictions.
  5. Specify WebSocket/gRPC streaming endpoints providing sub-frame updates to visual twin rendering instances.
  6. Formulate caching and spatial indexing strategies to optimize rendering performance across large facilities.
  7. Detail bidirectional control interfaces, safety interlocks, and hardware-in-the-loop (HIL) isolation mechanisms.

Constraints

  • MUST enforce strict read-only isolation on bidirectional channels unless explicit manual safety handshake is asserted.
  • MUST NOT drop telemetry packets when downsampling for visualization display rates.
  • Spatial coordinate conversions from {{cad_bim_source_format}} MUST preserve millimeter-level positional accuracy.
  • System resource utilization on {{compute_deployment_model}} MUST remain below 75% sustained load during peak telemetry bursts.

Output format

Produce a technical architecture specification organized into the following mandatory sections:

  1. Spatial & Semantic Asset Graph Architecture
  2. Real-Time Telemetry Synchronization Pipeline (tuned for {{sync_frequency_hz}})
  3. Storage Architecture & Time-Series Modeling (implementing {{time_series_db_engine}})
  4. Physics Simulation Integration & Model Drift Detection (running in {{simulation_engine_runtime}})
  5. Bidirectional Control & Industrial Safety Governance
  6. Compute & Network Sizing for {{compute_deployment_model}} Target length: 750-1150 words.

Self-review

  • Ensure spatial mapping explicitly converts geometries from {{cad_bim_source_format}} into dynamic runtime representations.
  • Confirm telemetry sync frequency ({{sync_frequency_hz}}) is validated against compute bounds of {{compute_deployment_model}}.
  • Check that safety interlocks and air-gapped control overrides are fully addressed.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

developers
developers-architecture
manufacturing-industrial
digital-twin
simulation
time-series