Optimized Parameter Prediction for Aluminum Alloy 7075 Machining Using a Hybrid Experimental Design Strategy

In this paper, a high-performance machining accuracy and parameter prediction algorithm was proposed that better meets specific surface roughness requirements of the boring machining of aluminum alloy 7075. First, a hybrid experiment design strategy that incorporates factor range segmentation and exchange methods was used to improve data collection and ensure that the model accurately reflects the processing characteristics of the machine used. Then, a 1D CNN deep learning algorithm was used to model the relationship between boring parameters and the machining results, integrated with a particle swarm optimization algorithm to solve the parameter optimization problem for different processing objectives. The results proved that the proposed method was useful for the solution of the parameter prediction problem in specific machining objectives.