An Example of Artificial Neural Network (ANN) Application for Indirect Estimation of Rock Parameters

A study was conducted to develop an artificial neural network model to determine the modulus of elasticity and unconfined compressive strength of a rock. Multiple regression analysis was used for the study to correlate modulus of elasticity and unconfined compressive strength with the index properties. A feed forward back propagation neural network model was also used for the study to determine the modulus of elasticity and unconfined compressive strength of gypsum. Porosity, slake durability, Schmidt hardness, point load, and strength were also examined during the study. It was also observed that there exist a statistical relationship between elasticity modulus and unconfined compressive strength with slake durability index, point load index, effective porosity, and Schmidt hammer rebound number.