Abrasive waterjet drilling process enhancement using machine learning and evolutionary algorithms

To improve the abrasive waterjet drilling procedure for yttrium-stabilized zirconia-coated Inconel 718 superalloy, this study suggests an integrated approach using machine learning and an evolutionary algorithm. The objective is to simultaneously minimize the erosion diameter and taper angle of the drilled holes by identifying the best combination of drilling parameters such as stand-off distance, abrasive flow rate, waterjet pressure, and angle of impact. The machine learning models are developed using the random forest algorithm after tuning its hyperparameters to predict the erosion diameter and taper angle. The multi-verse optimization (MVO) algorithm is used to identify the best combination of drilling parameters. The comparison of results proved the efficacy of MVO over other algorithms. Confirmation experiment results are also in line with the results of MVO, since the percentage of deviation is meager. This integrative approach has the capability of significantly improving aerospace and industrial abrasive waterjet drilling operations.