A New Nelder-Mead Optimization Method for the End Milling Process's Energy Efficiency Parameters Based on Neuro-regression Modeling
Keywords:
End milling, energy efficiency, optimizationAbstract
The fast depletion of energy sources worldwide is causing a growing number of global issues every day. One of engineering's
objectives is to stop this from happening by creating creative solutions to the world's rapidly declining energy use. Reducing the
energy usage of the production-related machinery might be a solution. In order to lower energy usage, a novel design method
based on the neuro-regression approach and non-linear regression modeling was presented in this work as an alternative to
Taguchi design. To investigate the impact of the constraint circumstances on energy consumption, a cutting parameter
optimization model was developed. Cutting power, part surface roughness, and tool life were treated as objective functions
(constraint conditions). Initially, design factors in end milling were used to build the multiple non-linear regression models.
Spindle rotational speed, feed rate power, axial cut depth, radial cut depth, and cutting speed were identified as these design
factors. This optimization modeling then brought the goal functions to the appropriate minimum optimum values. By examining