Application note · Specialised industrial engineering

Application Note: TwinCAT Virtual Commissioning and a Private Engineering Assistant

Automate TwinCAT project builds, simulate machine sequences and use locally hosted AI without crossing the real-time or safety boundary.

This application note combines an engineering pipeline with a virtual plant and a permission-aware private assistant. It improves review and test coverage while the real PLC, motion and safety runtimes remain authoritative.

Engineering baseline

Store TwinCAT project source, library versions, target configuration, I/O map and test definitions in version control. Use Automation Interface from a controlled runner to create/open projects, update approved parameters and invoke builds. Archive compiler output and generated artefact hashes.

Simulation boundary

Connect the PLC runtime to a virtual plant over a controlled ADS interface. The model represents sensors, actuators, motion constraints and fault injection at the fidelity needed for the test. Never bridge virtual actuation to live equipment by default; separate networks and allowlists enforce the boundary.

Test campaign

Execute normal sequences, start/stop transitions, interlocks, sensor faults, communication loss, limit conditions and restart. Compare traces against expected state transitions and timing bands. AxiGovernor hosts the core estate; AxiKeystone or AxiVector can run more or higher-fidelity simulation instances.

Private assistant

Index only approved manuals, standards, code libraries and project knowledge. Enforce repository and project ACLs during retrieval. Require citations for explanations and tests. Generated Structured Text is a proposal: compile, simulate, peer-review and commission it through normal authority.

Evidence and handover

Deliver the source commit, TwinCAT/library versions, runner environment, simulation version, test report, known limitations, approved deployment package and rollback. Keep safety validation distinct and performed by competent authorised personnel.

Primary technical references

References are provided for software architecture and implementation planning. Validate the versions, licences, support matrix and regulated-use requirements applicable to the final deployment.

From technical concept to production system

Apply this technology through an Axiotech engineering work package

Axiotech can connect the compute, AI or analytics platform to the machine controls, data contracts, validation evidence and lifecycle-support model required for industrial use.

Relevant Hyperion platforms

Hyperion X1140-C

AxiKeystone

A CPU- and memory-led HPC platform for simulation, genomics, analytics, compilation and workloads with large in-memory working sets.

One 4U node; 128 AMD EPYC cores; 1.15TB ECC DDR5; one NVIDIA RTX PRO 4000 24GB; enterprise U.2 NVMe.

Hyperion X1150-C

AxiGovernor

A controls-engineering and virtual-commissioning platform for TwinCAT, PLC, motion, simulation and private engineering AI.

One 4U node; 96 AMD EPYC cores; 768GB ECC DDR5; one NVIDIA RTX PRO 5000 48GB; engineering storage and remote management.

Hyperion X2160

AxiVector

A tightly coupled two-node simulation and mathematical-computing platform for MPI, CFD, FEA and optimisation.

Two 4U nodes; 256 AMD EPYC cores; 2.3TB aggregate ECC DDR5; two 96GB GPUs; direct 100GbE RoCEv2 RDMA between nodes.

Configuration and quotation

Validate this workload on Hyperion

Final architecture and price depend on representative code and data, concurrency, storage, networking, site infrastructure, component availability and export compliance.

Request Formal Quotation