NVIDIA Real Estate and Construction Germany

EDAG Production Solutions

Real-time Analytics

EDAG needed to help manufacturers launch and optimize factories faster, but fragmented planning tools, disconnected supplier data, and manual status tracking slowed collaboration, increased errors, and delayed readiness for new production lines.

Factory launches up to three months ahead of schedule
More than 100 workers trained virtually before installation
Reduce manual data integration by up to 50%

Reported impact

Business outcome

EDAG customers accelerated factory launches by up to three months, cut manual data integration by up to 50 percent, trained more than 100 workers virtually before installation, and improved quality and first-time-fix rates by detecting issues and corrective actions inside the digital twin before they became production delays.

  • Cost Reduction
  • Productivity Improvement
  • Speed to Market

Solution

EDAG built an industrial digital twin platform on OpenUSD and NVIDIA Omniverse to unify planning, simulation, and operations data for factory programs. The platform ingests 3D CAD models, metadata, simulation outputs, and live production information through a scalable OpenUSD connector pipeline, reducing manual data integration and giving teams a continuously updated model of production lines and factories. Live dashboards expose KPIs such as cost and schedule, while a built-in AI assistant helps users track status, identify risks, and keep stakeholders aligned. The same environment supports virtual layout validation, AI-enabled quality analysis on live production data, and VR-based worker training before equipment is installed. This gives manufacturers a shared collaboration layer where engineering, supplier, and operations teams can simulate decisions, resolve defects, and prepare the workforce before physical changes are made.

Data flow

CAD models, supplier metadata, simulation results, and live production data are ingested into EDAG's OpenUSD pipeline, surfaced through the Omniverse-based digital twin, and then used for KPI dashboards, layout simulation, defect analysis, and VR training across factory teams.

Solution architecture

3 components · 2 layers
  1. Serving
    • NVIDIA Omniverse Supplies the digital twin technology stack for simulation, collaboration, and AI-enabled factory workflows.
    • EDAG digital twin platform Acts as the shared factory-planning environment where customers monitor KPIs, validate layouts, and train workers virtually.
  2. Orchestration
    • OpenUSD Provides the interoperable data model and connector pipeline that unifies planning and production information.

Architecture clues

  • A built-in AI assistant is used for status tracking and risk management directly in the digital twin.
  • The platform combines simulation-first planning with live production data rather than treating design and operations as separate systems.
  • VR training is created from the same engineering and planning data used for factory design.

Evidence from the source

A connector enables users to transfer key metadata via a simple, efficient, and scalable OpenUSD data pipeline that can reduce manual data integration by up to 50%.
EDAG’s digital twin platform—built on NVIDIA Omniverse technologies and OpenUSD—helps teams unify project and supplier data for real-time collaboration.
Live dashboards allow project managers, engineers, and suppliers to monitor crucial KPIs, including project cost and schedule.
Operators interact with an intuitive interface to pinpoint defects, trace root causes, and follow step-by-step corrective actions—all in real time without stopping the production line.
The company leveraged OpenUSD and NVIDIA Omniverse™ technologies to build an industrial digital twin platform.
Transparency Evidence & methodology 90/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. NVIDIA

    EDAG Production Solutions customer story

    First-party
    https://www.nvidia.com/en-us/case-studies/edag/
    Source type
    Vendor-published customer story
    Published
    Feb 5, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Feb 5, 2026 · NVIDIA · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.