Experimental investigation on thermally enhanced machining of high-chrome white cast iron and to study its machinability characteristics using Taguchi method and artificial neural network

Machining of hard-to-wear materials such as high-chrome white cast iron (HCWCI) and high-manganese steels is an uphill task when conventional route followed. Alternatively, thermally enhanced machining (TEM) can be used to minimize the tooling cost very effectively. This paper presents the detailed study of TEM of HCWCI in which the effect of cutting parameters and surface temperature of the stock material on machinability characteristics (cutting forces and surface roughness) are analyzed using ANOVA and artificial neural network (ANN). The experimental work was conducted to follow Taguchi techniques. HCWCI is finding newer applications in mining; mineral processing industries were the workpiece in the machining studies using cobalt-based cubic boron nitride insert tool. Localized heat was added at the tool-work interface which softens the metal and eases the machining operation. The influences of the control factors on the process responses have been analyzed using analysis of variance (ANOVA), and the results are correlated using ANN. Linear regression was used to establish the relation between the control parameters and the process responses. The results show that TEM causes easy shearing of the material, leading to the reduction in cutting forces with expected improvement in tool life and surprisingly good surface finish. The confirmation tests suggest both second-order regression and ANN which are better predictive models for quantitative prediction of TEM of HCWCI, and ANN is more accurate of the two. Also, it was proved that oxy-LPG flame heating is an economical option compared to laser-heated machining in hard turning process.