The machining of the nickel-based superalloy Monel 400 has excellent mechanical qualities and may be used in a wide variety of commercial applications. The current study explores the effect of the Surface roughness, primary cutting force, and cutting temperature at the tool work mating point on machining parameters such as cutting speed, feed rate, and depth of cut, and Laser power, which has four levels that are regularly spaced levels. In order to evaluate cutting conditions, a DOE L30 orthogonal array and ANOVA were used. A feed forward back propagation artificial neural network (ANN) model with a 4-10-3 architecture trained using a Levenberg-Marquardt (LM) algorithm resulted in a well-organized modelling of the intricate connection between surface roughness, main cutting force, and cutting temperature on machining parameters. This was accomplished through the use of the LM algorithm (R-value of 0.98). In order to predict the optimal turning parameters, the trained network was improved with the use of a genetic algorithm (GA). The ANN-GA technique is the name that has been given to this strategy. Because of the optimization that was done utilizing the ANN-GA approach, there was a discernible decrease in the surface roughness is 11.2% as well as the primary cutting force is about 16%. According to the findings of the analysis of variance, the most significant factor is cutting speed, followed by depth of cut and feed rate.

PDF (Download Full text)

| Download Citation (XML)