Research Framework and Institutions
FireModel-AI is developed within the BESKID research framework in collaboration with the University of Wuppertal and Forschungszentrum Jülich.
AI-driven reduced-order fire prediction framework for near real-time Heat Release Rate (HRR) prediction in transient fire scenarios.
The framework predicts HRR time-curves within fractions of a second using POD-based reduced-order modeling and ANN surrogate models trained on high-fidelity CFD simulations generated with FDS.
The current models are trained for:
Developed by Mehrdad Nouroozyan within the KIB contribution of the BESKID research project, in collaboration with Prof. Dr.-Ing. Fabian Brännström (Chair of Fire Dynamics, University of Wuppertal).
High-dimensional CFD snapshots generated using the Fire Dynamics Simulator (FDS) are assembled into a snapshot tensor and compressed into a low-dimensional reduced basis using Proper Orthogonal Decomposition (POD).
Only the dominant POD modes are retained. Instead of solving the governing Navier–Stokes equations during prediction, an Artificial Neural Network (ANN) learns the nonlinear mapping between the material parameter vector μ and the reduced coefficients a.
The transient fire response is reconstructed as:
This enables near-instantaneous prediction of HRR time-curves while retaining the dominant physical behavior extracted from the original CFD simulations.
FireModel-AI is developed within the BESKID research framework in collaboration with the University of Wuppertal and Forschungszentrum Jülich.