The concave and convex nature of helical surfaces determines variable feed rate and variable load machining, resulting long machining times and huge consumption power. During machining process, spindle vibration will reduce machining quality and increase machining energy consumption. To attain high-quality and low-consumption machining, this paper introduces an optimization method aim at reducing energy consumption associated with the process parameters used for machining helical surfaces, with particular consideration given to spindle vibration. Firstly, the mechanism underlying the synergistic effect of spindle vibration and process parameters on machining energy consumption and surface roughness is analyzed, and a corresponding mechanistic model is developed. Secondly, to solve the problem of multiple covariance in the regression fitting to improve prediction accuracy of energy consumption model, an improved stochastic configuration network is used to compensate for the error. Finally, the optimal process parameters for multi-objective optimization are determined through the application of an enhanced non-dominated sorting genetic algorithm. In comparison to the empirical process parameters, the optimized machining energy consumption has been reduced by 9.82%, and surface roughness has decreased by 7.02%. This demonstrates that the method proposed in this paper can provide strong support for the green and sustainable development of the manufacturing industry.
Zhang et al. (Mon,) studied this question.