Kinetic model of vibration screening for granular materials based on biological neural network

Abstract

The kinetic model is the theoretical basis for optimizing the structure and operation performance of vibration screening devices. In this paper, a biological neurodynamic equation and neural connections were established according to the motion and interaction properties of the material under vibration excitation. The material feeding to the screen and the material passing through apertures were considered as excitatory and inhibitory inputs, respectively, and the generated stable neural activity landscape was used to describe the material distribution on the 2D screen surface. The dynamic process of material vibration screening was simulated using discrete element method (DEM). By comparing the similarity between the material distribution established using biological neural network (BNN) and that obtained using DEM simulation, the optimum coefficients of BNN model under a certain screening parameter were determined, that is, one relationship between the BNN model coefficients and the screening operation parameters was established. Different screening parameters were randomly selected, and the corresponding relationships were established as a database. Then, with straw/grain ratio, aperture diameter, inclination angle, vibration strength in normal and tangential directions as inputs, five independent adaptive neuro-fuzzy inference systems (ANFIS) were established to predict the optimum BNN model coefficients, respectively. The training results indicated that ANFIS models had good stability and accuracy. The flexibility and adaptability of the proposed BNN method was demonstrated by modeling material distribution under complex feeding conditions such as multiple regions and non-uniform rate.