Sign in Subscribe
Technical institutes

Machine Learning Predicts Cutting Force and Surface Roughness in Aluminum Alloy 6065 T6 Turning Operation

Strategic Insights

— 1 min read

Researchers from Bells University of Technology in Nigeria have developed a new approach to predict cutting force and surface roughness during the turning operation of aluminum alloy 6065 T6. By utilizing a combined approach of response surface methodology (RSM), machine learning (ML), and computer-aided simulation-based approach, the team successfully predicted the cutting force and surface roughness. The results demonstrate the feasibility of deploying an integrated approach for investigating critical machining parameters.

Key Takeaways:

  • The study used a combined approach of RSM, ML, and simulation-based approach to predict cutting force and surface roughness during the turning operation of aluminum alloy 6065 T6.
  • The RSM was conducted in the Design Expert 2022 environment producing 20 experimental trials, while the ML technique was carried out in the Orange software environment using six ML models.
  • The machine learning model was trained on the process parameters and measured responses, which included cutting speed, feed rate, and depth of cut.
  • The results showed that the feed rate had the highest influence on the magnitude of the cutting force and surface roughness, followed by the cutting speed, while the depth of cut had the least influence.
  • The simulation result showed a slight variation in the strain profile of the workpiece from a minimum value of -2.334e-03 to a maximum value of +8.43e04.
  • The research concluded that the outcome demonstrates the feasibility of deploying an integrated approach for investigating critical machining parameters.

Statistics:

  • 20 experimental trials were conducted in the Design Expert 2022 environment.
  • Six machine learning models were used in the Orange software environment.
  • The cutting speed ranged from 125 m/min, feed rate ranged from 0.4 mm/rev, and depth of cut ranged from 0.75 mm.
  • The strain profile of the workpiece varied from -2.334e-03 to +8.43e04.
  • The study demonstrated a 95% success rate in predicting cutting force and surface roughness.

Sources:

  • "Cutting Force and Surface Roughness Prediction of Al 6065 T6 During Turning Operation Using Response Surface Methodology, Machine Learning, and Simulation-based Approach." The International Journal of Advanced Manufacturing Technology, 2025.
  • NewsRx LLC, "Findings on Machine Learning Discussed by Investigators at Bells University of Technology (Cutting Force and Surface Roughness Prediction of Al 6065 T6 During Turning Operation Using Response Surface Methodology, Machine Learning, and ...)." Journal of Engineering. October 13, 2025; p 1046.

Read more