Abstract
Inconel718 superalloy is one of the difficult-to-cut materials used widely in the aerospace industries. Inducing high tensile residual stress is a critical problem during the machining of Inconel718. This problem becomes more detrimental in presence of rough machined surface because fatigue life of the manufactured components might be decreased significantly. The aim of the present study is to access desired machining parameters including cutting speed, depth of cut, and feed rate for simultaneous optimizing surface roughness and tensile residual stress in the finish turning of Inconel718. After conducting experimental measurements, the results were introduced to the artificial neural networks. Then, the functions implemented by neural networks were defined as objective functions of nondominated sorting genetic algorithm. Finally, it was shown that implemented hybrid technique provides a robust framework for machining of Inconel718 superalloy.
Notes
Color versions of one or more of the figures in the article can be found online at www.tandfonline.com/lmmp.