Platform overview
One asset model. Three ways to use it.
Every PHL AI product works from the same record of each machine: its identity, its signals, how it relates to its neighbours and what has happened to it. TwinCore builds that record; Maintain and Simulate reuse it.
Shared platform
Asset identity · Ingestion · Twin state · Access · Audit · Reports
- PHL TwinCoreFlagship · first release
- PHL MaintainReview queue in first release
- PHL SimulateTwo scenario models in first release
01What the products share
Shared by design, not by integration.
Seven layers every product reads from and writes to.
Asset identity
One global asset ID, tag and type per machine, in a Facility › Area › Cell › Asset › Component hierarchy. Criticality and ratings live here.
Industrial data
Readings arrive through one ingestion path: validated against a schema, normalised to canonical units, de-duplicated and tagged with their workspace. Missing intervals are kept as gaps, never filled.
Digital-twin configuration
A versioned signal map, typed relationships and a plan-view layout. Published versions are immutable, so every alert, scenario and report can name the twin version it used.
Monitoring
Twin state is the latest good value per signal with its freshness. Stale or offline data changes the asset’s state instead of disappearing from view.
Analytics
Deterministic rules, statistical deviation checks and the rules-based Review Priority. Each output carries a class tag (RULE, STAT, SCEN) so it can never pass for a measurement. Trained models are a future capability.
Integrations
CSV and Parquet imports are part of the first release. MQTT and OPC UA sources connect through a gateway on your network. See the integration catalogue for the status of each.
Reporting
Report templates share one engine: scope, period, twin version, data coverage and limitations appear in every report.
02Architecture
Readings flow in. Nothing flows back to the machine.
The proposed platform pipeline. AWS services are named as the planned hosting design, not as a running deployment.
A
Physical equipment
- Machines & sensors
- PLCs
- SCADA / historian
- CMMS records
B
Edge connectivity
- OPC UA read-only clientRequires adapter
- MQTT bridgeRequires adapter
- Store-and-forward bufferRequires adapter
C
Data ingestion
- CSV / Parquet importAvailable in MVP
- Validate · normalise units · dedupeAvailable in MVP
- AWS IoT Core + queuePlanned
D
Industrial data platform
- Asset metadata (PostgreSQL)Planned
- Time-partitioned telemetryPlanned
- Files & history (Amazon S3)Planned
E
Digital twins
- Signal map & relationshipsAvailable in MVP
- Versions & freshnessAvailable in MVP
- 3D view (glTF)Planned
F
Analytics & simulation
- Rules & statistical flagsAvailable in MVP
- Scenario models S1 · S2Available in MVP
- Trained predictive modelsFuture capability
G
Application
- Twin explorer & telemetryAvailable in MVP
- Alerts & review queueAvailable in MVP
- ReportsAvailable in MVP
Control boundary. Readings flow from the plant to PHL AI over outbound TLS. There is no write path back: PHL AI does not send commands to PLCs, setpoints or production controls. People act through the systems they already operate.
- Available in MVP
- Designed for the first release and shown in the demo with sample data.
- Requires adapter
- Works through a gateway, adapter or customer configuration on your network.
- Planned
- On the roadmap, designed but not in the first release.
- Future capability
- Requires models, infrastructure or validation that does not exist yet.
03Capabilities and status
What is in the first release, and what is not.
| Capability | What it does | Status |
|---|---|---|
| Asset registry & facility hierarchy | Facility › Area › Cell › Asset › Component, CSV import, criticality. | Available in MVP |
| Digital-twin configuration | Signal map, relationships, plan-view layout, published versions. | Available in MVP |
| Telemetry import & visualization | CSV/Parquet, sample data, thresholds, gaps and freshness. | Available in MVP |
| Live telemetry through a gateway | MQTT and OPC UA via a gateway on your network. | Requires adapter |
| Rules & statistical flags | Static, sustained, rate-of-change and stale-data rules; z-score deviation flags. | Available in MVP |
| Maintenance review queue | Review Priority, assignment, notes, resolution record. | Available in MVP |
| Scenario models S1 & S2 | Threshold policy replay; deterministic cell capacity model. | Available in MVP |
| Engineering reports | Six templates with data coverage and limitations. | Available in MVP |
| 3D twin view (glTF) | Optional view of the same twin. | Planned |
| Public API & webhooks | Read API first, then webhooks. | Planned |
| Single sign-on | SAML / OIDC. | Planned |
| Trained predictive models | Only with labelled failure history and published evaluation. | Future capability |
| Physics-based simulation | Through external, validated engines. | Future capability |
Bring your industrial systems into clearer view.
Start with a focused equipment workflow and expand toward connected digital twins and industrial simulation as your requirements evolve.
Illustrative demo · no signup · not connected to equipment