Calibration and verification of DEM parameters for dynamic particle flow conditions using a backpropagation neural network

Abstract

The Discrete Element Method (DEM) requires input parameters to be calibrated and validated in order to accurately model the physical process being simulated. This is typically achieved through experiments that examine the macroscopic behavior of particles, however, it is often difficult to efficiently and accurately obtain a representative parameter set. In this study, a method is presented to identify and select a set of DEM input parameters by applying a backpropagation (BP) neural network to establish the non-linear relationship between dynamic macroscopic particle properties and DEM parameters. Once developed and trained, the BP neural network provides an efficient and accurate method to select the DEM parameter set. The BP neural network can be developed and trained for one or more laboratory calibration experiments, and be applied to a wide range of bulk materials under dynamic flow conditions.