Metalurgija (Apr 2012)
Usage of neural network for the prediction of surface roughness after the roller burnishing
Abstract
In order to increase productivity, machining times and market competitiveness of machining production systems, it is important to continuously develop existing technological solutions. This article describes the usage of the neural network for the prediction of surface roughness after the roller burnishing. Since the observed problem is multidimensional with several input parameters and one output parameter and since nonlinearity and complexity of parameter correlation, there was used the backpropagation neural network algorithm. Empirical and experimental values of input and output parameters were used as initial values for the learning of the neural network. Developed neural network model with its results can be used for easier implementation of further roller burnishing process plans.
