vyzn's Reference Model - the technical bridge from BIM to Simulation & Analysis

The Challenge‍

Although Building Information Modeling (BIM) is increasingly established in construction planning, many underlying 3D building models, especially in IFC format, suffer from significant structural and semantic deficiencies. Common issues include:

• Missing or inconsistent information about rooms, surfaces, materials, or component types
• Heterogeneous data quality
• Overlapping, duplicated, or ambiguously assignable elements
• Limited semantic depth: models often lack explicit information about the functional role or logical relationships of building components. For example, it is unclear whether a component is part of the thermal envelope or how rooms are topologically connected. In most cases, room definitions are entirely missing.

These structural and semantic gaps make the creation of automated workflows - for deriving energy or comfort simulations, CO₂ balances, or circularity assessments - extremely complex and error-prone. In practice, a direct transition from the 3D building model to simulation and analysis is rarely possible without preliminary manual data cleaning, supplementation, and structuring.

‍

Our Approach

To close this gap, we developed the vyzn Reference Model. Through geometric processing, topological analysis, and AI-supported algorithms, we extract and structure those data from BIM models that are truly relevant for simulation-based planning processes. This results in an abstracted, consistent, and high-quality building model: the vyzn Reference Model.

It forms the basis for all subsequent analyses, from thermal simulations and energy efficiency to cost calculations, structural analysis, and CO₂ accounting.By automating the derivation of relevant building structures, manual data cleaning effort is drastically reduced, and the quality of planning is significantly improved.

Technical core principles:

• Geometric & Topological Analysis:
  We extract precise geometric structures such as surfaces, room boundaries, building envelopes, and openings from the building model. Through topological evaluation, we reconstruct relations such as adjacencies, zone and storey assignments, or membership in functional areas (e.g., access zones, elevator shafts, thermal envelope). This allows automatic derivation of logical units such as buildings, zones, or access cores.
• AI-supported Completion:
  Missing or inconsistent information - such as component classifications, opening assignments, or functional roles—is detected and plausibly supplemented or corrected by trained models. This creates a complete, structured building dataset with high semantic depth.
• Semantic Model Enrichment:
  The reference model is uniformly typed, logically named, and enriched with derived attributes, for example, thermal relevance, eBKP-H classifications, room functions, or zonal assignments. It thus provides an ideal foundation for automated analyses, simulation-based optimization, and AI-driven predictive models.

The vyzn Reference Model - the key to the next level of Digital Building Planning

The vyzn Reference Model paves the way for a new quality in digital building planning: structured, complete, and simulation-ready models - created automatically. Instead of costly manual data cleaning, we enable a robust and transparent basis for analyses, evaluations, and optimizations.

From 3D model to solid decision basis: in minutes, not weeks.

Through targeted geometric, topological, and semantic processing, an error-prone, often incomplete BIM model is transformed into an intelligent digital twin - machine-readable, simulation-ready, and ideal as a starting point for further digital workflows.

With the vyzn Reference Model, we create the technological bridge between construction planning and data-driven decision-making: efficient, automated, and scalable.