A granular material is a conglomeration of discrete solid, macroscopic particles characterized by a loss of energy whenever the particles interact. Some examples of granular materials are nuts, coal, sand, rice, corn flakes, and ball bearings. Granular materials are commercially important in applications as diverse as pharmaceutical industry, agriculture, and energy production (Lithium-ion batteries, Solid-oxide fuel cells, and solar thermal energy storage systems). In my research, the main focus on dry granular systems experiencing thermal and mechanical loads.

DEM (Discrete Element Method)

The DEM is used to simulate the assembly of particles allowing a finite displacement and rotation of discrete bodies. It is developed based on the idea that discrete particles could be displaced independently from one another and interact with each other only at the contact points. Inter-particle forces are calculated using contact laws. Modeling through DEM has been recently receiving greater attention due to its uniqueness in capturing inter-particle interactions in granular assemblies.

Artificial neural networks (ANN) is one of the widely used machine learning techniques to recognize complex patterns and relationships between inputs and outputs in a system. It learns from processing the data sets to establish a relationship between the inputs and outputs.

ANN is a computing model whose layered structure resembles the neurological structure in the human brain. It can learn from the data and can be trained to recognize complex patterns, relations and predict. ANN is a collection of connected neurons having a function similar to biological neurons.

Application of the machine learning techniques to mechanical design as well as in-process predictions for complex systems [1,3,10].