ABSTRACT
Though statistical relations are good enough to predict the properties fairly well, they are limited by the degree of nonlinearity they can model. Moreover, statistical relations constrain the data along a particular geometry which may not always be favorable to capture the nonlinear relations existing between various parameters. Further, in engineering domains, algebraic and differential equations are used to describe the behavior and functional properties of real systems and to create mathematical models to represent them. Such approaches require accurate knowledge of system dynamics and use of estimation techniques and numerical calculations to emulate the system operation. The complexity of the problem itself may introduce uncertainties that make the modeling nonrealistic or inaccurate. The sound produced during rock drilling is so complicated that accurate modeling will be difficult and may be only approximate it well sometimes, because of the complexity of the nature of the rock drilling process. Artificial neural networks (ANN) have been found to be very efficient in handling nonlinear relationships and intelligent prediction of the required parameters. ANNs implement algorithms that attempt to achieve a neurological-related performance such as learning from experience, making generalization from similar situations, and judging states where poor results are achieved in the past.
