A controls-engineering and virtual-commissioning platform for TwinCAT, PLC, motion, simulation and private engineering AI.
This brief explains where the baseline fits, the software and operating model it supports, and the evidence Axiotech should use to validate a final configuration. Indicative specifications remain subject to component availability, export compliance and formal quotation.
Baseline architecture
One 4U node; 96 AMD EPYC cores; 768GB ECC DDR5; one NVIDIA RTX PRO 5000 48GB; engineering storage and remote management.
The current compute node is based on the Supermicro AS-4125GS-TNRT / CSE-418G2TS 4U rack platform, integrated with matched rails, power, management, networking and rack infrastructure as required.
Best-fit workloads
TwinCAT builds, ADS-connected simulation, virtual commissioning, engineering CI, private PLC/code assistance and robot-cell integration while real-time control remains on certified controllers.
It consolidates build, test, simulation, documentation and private assistance while keeping plant intellectual property on site.
Recommended software stack
Windows Server or validated Windows/Linux virtualisation, Beckhoff TwinCAT 3, ADS, Automation Interface, Git, CI runners, simulation tools, local code models and PrometheusAI engineering services.
Pin host drivers and infrastructure separately from versioned application containers. Record source, image, dataset/model and hardware allocation with each benchmark or production release.
Deployment pattern
Segment engineering, simulation and plant interfaces. Use version control, clean build runners, allowlisted ADS/OPC UA paths and a private knowledge index that follows project permissions.
Define monitoring, identity, backup, change control and workload ownership at the same time as compute. Multi-user platforms require resource allocation and quotas; production services require health, overload and rollback behaviour.
Sizing boundary
Hard real-time control remains on the industrial controller. The server supports engineering, simulation, orchestration and analytics rather than replacing safety- or motion-certified runtime hardware.
Final sizing should use representative code, data, concurrency and service objectives. Aggregate core, RAM or VRAM figures do not by themselves predict application performance.
Commissioning and acceptance
Build a known TwinCAT project, run normal and fault simulation sequences, verify interface isolation, restore a baseline and demonstrate that generated changes cannot bypass review or safety authority.
Axiotech should retain the resulting configuration, firmware/driver baseline, environment manifest, benchmark data and recovery procedure as the system acceptance pack.
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.