Prediction of Material Removal in Extrusion Honing of Hastelloy C22 Using Artificial Neural Network

Abstract

The traditional finishing processes are incapable of producing required surface finish and other characteristics in difficult-to machine materials like Nickel based superalloys and also complex geometrical shapes of engineering components. Hence to achieve these goals non-traditional micro-machining processes have been developed. Extrusion honing (EH) is one of the non-traditional micro-machining process to debur, radius, polish, and remove recast layer of components in a wide range of applications. In this process material is removed from the work-piece by flowing abrasive laden medium under pressure through or past the work surface to be finished. Components made up of complex passages having surface/areas inaccessible to traditional methods can be finished to high quality and precision by this process. Hastelloy C22 offers resistance to both aqueous corrosion and attack at elevated temperatures and it is a difficult metal to machine using traditional techniques. In this study, micro finishing of internal surface of Hastelloy C22 material having predrilled passage diameters 7, 8, 9 and 10 mm have been performed in an indigenously built hydraulic operated one way extrusion honing setup. For the present EH process, patented polymer mixed with SiC abrasive at 35% volume concentration was used as carrier medium. The study was performed for 46, 54, and 60 grit sizes of SiC abrasive. The material removal in EH process varies with passage diameter and grit size of abrasives at each trial. A feed forward back propagation neural network model has been developed for the prediction of material removal and it has successfully predicted material removed in each trial of EH process.