Volume 11 Issue 2 ( June )

Surface quality plays a pivotal role in the performance and durability of metal components across diverse industries. Burnishing, a commonly employed finishing method, has gained significant popularity for its efficacy in enhancing surface quality, especially in aluminium alloy applications. This research paper introduces a novel approach to elevate surface quality during the burnishing process of aluminium alloys, leveraging the capabilities of Artificial Neural Networks (ANNs). In this paper, machining parameters and their effects on the aluminium alloy material 6351 using a lathe were considered. A mathematical model has been developed to forecast variable surface roughness. The surface quality achieved after the procedure on the work piece is then utilized for ball burnishing. Subsequently, the surface quality pattern is employed to replicate the burnishing process using optimization, sensitivity analysis, and ANN. The quality of the surface parameters determined on the aluminium alloy after burnishing is estimated using a ball, and it is experimentally confirmed at 1.73164 m. The results of this research provide valuable insights into the intricate interplay of burnishing parameters on aluminium alloy surface quality, aiding in the development of more efficient and cost-effective finishing processes.

Keywords: Artificial Neural Network; Al Alloy; Surface Quality; Burnishing