Genetic Algorithm-Based Prediction of SR in Turning Monel K500 Super Alloy

By integrating simulated annealing and a Genetic Algorithm (GA), this study aimed to anticipate the surface roughness that would be produced during the turning process of the super alloy Monel K-500. The results of this research would then be compared to experimental analysis. Experiments in turning were carried out using the L9 orthogonal array, and values of surface roughness were determined for each possible combination of cutting settings. After that, the values of surface roughness that were predicted by simulated annealing and the Genetic Algorithm were compared to the values that were obtained by experimentation. According to the findings, both simulated annealing and the Genetic Algorithm were capable of making correct predictions regarding surface variation. Both approaches' capacity to optimise cutting settings for improved surface quality is demonstrated by the strong correlation that exists between the anticipated values generated by each method and the experimental results. The capacity of simulated annealing to optimise the turning process was validated by the efficient exploration of the parameter space that it supplied as well as by the predictions that it produced, which were correct to a reasonable degree. In a similar fashion, the Genetic Algorithm proved reliable performance and converged on near-optimal solutions for the purpose of minimising surface roughness variation.