Porosity Prediction of Granular Materials through Discrete Element Method and Back Propagation Neural Network Algorithm

Granular materials are used directly or as the primary ingredients of the mixtures in industrial manufacturing, agricultural production and civil engineering. It has been a challenging task to compute the porosity of a granular material which contains a wide range of particle sizes or shapes. Against this background, this paper presents a newly developed method for the porosity prediction of granular materials through Discrete Element Modeling (DEM) and the Back Propagation Neural Network algorithm (BPNN). In DEM, ball elements were used to simulate particles in granular materials. According to the Chinese specifications, a total of 400 specimens in different gradations were built and compacted under the static pressure of 600 kPa. The porosity values of those specimens were recorded and applied to train the BPNN model. The primary parameters of the BPNN model were recommended for predicting the porosity of a granular material. Verification was performed by a self-designed experimental test and it was found that the prediction accuracy could reach 98%. Meanwhile, considering the influence of particle shape, a shape reduction factor was proposed to achieve the porosity reduction from sphere to real particle shape.

[1]  Mohammad Reisi,et al.  A new DEM-based method to predict packing density of coarse aggregates considering their grading and shapes , 2012 .

[2]  Zhanping You,et al.  Using discrete element models to track movement of coarse aggregates during compaction of asphalt mixture , 2018, Construction and Building Materials.

[3]  C. C. Furnas.  Grading Aggregates - I. - Mathematical Relations for Beds of Broken Solids of Maximum Density , 1931 .

[4]  H. Lee,et al.  Consistent distribution of air voids and asphalt and random orientation of aggregates by flipping specimens during gyratory compaction process , 2017 .

[5]  Fan Kai.  Design on Asphalt Mixture Ratio Based on Neural Networks , 2012 .

[6]  Sudhir Varma,et al.  Optimizing asphalt mix design process using artificial neural network and genetic algorithm , 2018 .

[7]  Shihui Shen,et al.  Analysis of Aggregate Gradation and Packing for Easy Estimation of Hot-Mix-Asphalt Voids in Mineral Aggregate , 2011 .

[8]  Tao Wang,et al.  Compaction Characteristics and Minimum Void Ratio Prediction Model for Gap-Graded Soil-Rock Mixture , 2018, Applied Sciences.

[9]  Zhanping You,et al.  Lab assessment and discrete element modeling of asphalt mixture during compaction with elongated and flat coarse aggregates , 2018, Construction and Building Materials.

[10]  A. Calabi-Floody,et al.  Mechanical behavior of asphalt mixtures with different aggregate type , 2015 .

[11]  Jianlong Zheng,et al.  Three-Dimensional Simulation of Aggregate and Asphalt Mixture Using Parameterized Shape and Size Gradation , 2019, Journal of Materials in Civil Engineering.

[12]  Yu Liu,et al.  Discrete element modeling of realistic particle shapes in stone-based mixtures through MATLAB-based imaging process , 2017 .

[13]  Changhong Zhou,et al.  Influence of particle shape on aggregate mixture’s performance: DEM results , 2019 .

[14]  G. Roquier.  A Theoretical Packing Density Model (TPDM) for ordered and disordered packings , 2019, Powder Technology.

[15]  Zhanping You,et al.  Determining Aggregate Grain Size Using Discrete-Element Models of Sieve Analysis , 2019, International Journal of Geomechanics.

[16]  G. Roquier.  The 4-parameter Compressible Packing Model (CPM) for crushed aggregate particles , 2017 .

[17]  Guangjie Han,et al.  A BP Neural Network Prediction Model Based on Dynamic Cuckoo Search Optimization Algorithm for Industrial Equipment Fault Prediction , 2019, IEEE Access.

[18]  F. de Larrard,et al.  Linear packing density model of grain mixtures , 1986 .