Multi-objective feedrate optimization method of end milling using the internal data of the CNC system

This paper proposed a feedrate optimization method of end milling using the internal data of the CNC system, i.e., the spindle power, the block number, and the combined speed of feed axes, based on the controlled elitist non-dominated sorting genetic algorithm (i.e., the controlled NSGA-II) to address the multi-objective non-linear optimization problem for simultaneously increasing the machining efficiency and decreasing the fluctuation of the spindle power. To establish the objective functions and their constraint conditions in the optimization process, a spindle power–predicting model considering different milling operations, i.e., the up-milling operation and the down-milling operation, is proposed, from which the spindle power can be accurately predicted. Compared to the traditional method of optimizing the feedrate via the cutting force, the spindle power used in the proposed method is better because it is more convenient to acquire and is cost effective. To validate the proposed methods, a set of experiments are conducted to prove the feasibility of our spindle power prediction model as well as the advantage of the controlled NSGA-II-based method in improving the machining efficiency and balancing the tool load.