Data-Driven Cutting Parameters Optimization Method in Multiple Configurations Machining Process for Energy Consumption and Production Time Saving

Abstract

Cutting parameters and machining configurations affect the energy consumption and production time in the machining process significantly. Previous cutting parameters optimization methods are proposed for a specific machining configuration that limits its generalization ability. However, the machining configuration varies constantly with actual machining tasks, which results in the predetermined optimization method is impractical. We propose a data-driven optimization method for the multiple machining configurations, aimed at reducing energy consumption and production time. Firstly, the analysis of the relationship between energy consumption and meta-actions under different machining states is carried out, and the Gaussian process regression (GPR)-based energy consumption model is proposed. Then, a multi-objective optimization model is proposed for energy consumption and production time reduction, which is solved via a multi-objective grey wolf optimization. Finally, the experiments are conducted to verify the validity of the proposed method and the influence of meta-actions on energy consumption and production time are explicitly analyzed. The case study indicates the proposed energy consumption model has better prediction accuracy for multiple machining configurations. Optimizing cutting parameters achieves a trade-off between energy consumption and production time. Moreover, the parametric influence indicates cutting speed is the most influential cutting parameter for energy consumption and production time.