Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Building Performance Predictor: Integrating AI Performance Analysis into Architectural Design

Reference number
Coordinator BIMTech Innovations AB
Funding from Vinnova SEK 500 000
Project duration November 2025 - August 2026
Status Ongoing
Venture Innovative Startups
Call Innovative Startups 2025

Purpose and goal

The project aims to develop and validate LUX – an ML-based tool enabling real-time evaluation of building daylight performance in Revit, following Swedish standards. The tool targets large architectural and engineering firms. The project complements an open web platform for smaller companies, developed with support from Belysningsstiftelsen. Future modules will address energy, climate impact, and other Nordic standards. Developed in collaboration with LINK Arkitektur, White, Ramboll and others.

Expected effects and result

The project is expected to result in a validated prototype of LUX, a Revit plugin that adds advanced functionality to the open web platform’s core module. New features include support for custom material parameters (reflectance, transmittance), integration within Revit, and daylight metrics aligned with Norwegian and Danish standards. The project also evaluates simultaneous analysis of entire floors or building models, along with automated reporting to streamline the design process.

Planned approach and implementation

The project will be carried out in three phases: (1) development of the core module for LUX and its integration into Revit, (2) implementation of advanced functions such as material management and simultaneous analysis, and (3) testing and validation together with pilot users. The work will follow an agile process with continuous feedback from architectural firms, focusing on usability and performance.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 30 October 2025

Reference number 2025-02020