Granular flows (ex. fluidization), are composed of dozens of particles. In order to avoid the necessity of building real scale installations required to improve processes where particulate transport is involved there is an urgent need of building a mathematical models capable to accurately simulate such a processes. One of the most time consuming process that need to be taken into account while granular flows are modelled is mutual particle interaction. Due to complexity and great number of interactions, modeling such flows is not a trivial task. Nowadays two main models are available hybrid Euler-Lagrange (HEL) and Discrete Element method (DEM). In HEL interactions between solid phase are calculated basing of Kinetic Theory of Granular Flow (KTGF) where probability of collision is based on solid volume fraction in computational cell but time needed to obtain results is relatively short. In DEM particle interactions are calculated directly but it results in long computational time and high cost required to obtain reasonable results. In order to overcome the problem of long lasting calculations and predicting particle interactions, while keeping required accuracy a fast and robust Reduced Order Model (ROM) can be developed. The ROM technique allows building a low order, approximation of the system based on the calculated data. The principle of this approach is the expression of the model response parameters in a form of a linear combination of space dependent modes calculated for wide range of input parameters (obtained from simulation of particle collision using DEM). Generated Surrogate Model (SM) can be than used as a part of HEL approach to substitute forces between particle interactions basing on solid volume fraction with forces obtained using DEM. In such a way the precision of DEM model will be preserved but results will be obtained much faster. In parallel with creating the ROM model and simulations experimental tests will be carried out to collect data for developed collision model validation.