Constrained Optimization of Surface Roughness in Longitudinal Turning via Novel Modified Harmony Search

The present research deals with a modified optimization algorithm of harmony search coupled with artificial neural networks (ANNs) to predict the optimal cutting condition. To this end, several experiments were carried out on AISI 1045 steel to attain required data for training of ANNs. Feed forward artificial neural network was utilized to create predictive models of surface roughness and cutting forces exploiting experimental data, and Modified Harmony Search algorithm (MHS) was used to find the constrained optimum of the surface roughness. Furthermore, Simple Harmony Search algorithm (SHS) and Genetic Algorithm (GA) were used for solving the same optimization problem to illustrate the capabilities of MHS algorithm. The obtained results demonstrate that MHS algorithm is more effective and authoritative in approaching the global solution than the SHS algorithm and GA.