Calibration of DEM models for fertilizer particles based on numerical simulations and granular experiments

The discrete element method (DEM) can accurately predict and describe the motion behavior of granular ma-terials; it has been widely used in related research in all walks of life. However, the material microscopic pa-rameters involved in a simulation are difficult to measure using experimental methods, and the accuracy of the microscopic parameters has a direct impact on the predicted material motion behavior. In this study, a new calibration method was used to calibrate contact parameters commonly used in DEM simulations for fertilizer particles. The angle of repose (AoR) and the bulk height were selected as macroscopic response indicators, and the coefficient of restitution, coefficient of static friction, and coefficient of rolling friction of fertilizer particles were used as the parameters to be calibrated in the study. The input parameters required for the training of the radial basis function neural network (RBFNN) were obtained by combining Latin hypercube sampling with funnel stacking simulations. Finally, a multi-island genetic algorithm (MIGA) was used to optimally solve the approximate model, and comparative experiments and discharge experiments were conducted to validate the model. The results show that the sphericity of the fertilizer particles in the study is 90%, and spherical particles can be used instead in the simulation. Additionally, the approximate model obtained from the RBFNN training has a high model fit to the input and output parameters and a good prediction capability for the macroscopic behavior generated by the input parameters of the fertilizer particles. The result generated from the calibration was a set of data solutions, and the errors were less than 5% after validation of the data. Further experimental validation was done using the discharge experiment, which was consistent with the simulation results, indicating that the calibration results can accurately reflect the macroscopic motion behavior of the fertilizer particles, further illustrating the reliability of the method.

Automated summary

In this study, a new calibration method was developed to calibrate contact parameters commonly used in DEM simulations for fertilizer particles. The input parameters required for the training of the RBFNN were obtained using Latin hypercube sampling and funnel stacking simulations. The results showed that the calibration method accurately reflected the macroscopic motion behavior of the fertilizer particles.