期刊
MEASUREMENT
卷 163, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.measurement.2020.108001
关键词
Residual stress minimization; Process parameter optimization; Turning; Support vector regression; Particle swarm optimization
资金
- SCP [TZ2016006-0102]
- NSFC [51525501]
Surface residual stress, induced by process parameters, has a significant effect on the performance of workpiece. Focusing on the minimization of surface residual stress in turning DT4E pure iron, the influence of cutting speed (v(c), 80-240 m/min), feed rate (f, 0.04-0.20 mm/rev) and depth of cut (a(p), 0.05-0.25 mm) on surface tensile residual stress (sigma(tau) in cutting direction, sigma(r) in feeding direction) is analyzed, and the optimal combination of process parameters is found. Central composite design (CCD) method is first used to design the turning experiments of pure iron material. By means of range analysis and the main effect plot, the relations between the process parameters and responses are discussed in detail. Subsequently, the non-linear mapping models of sigma(tau) and sigma(r) with regard to turning parameters are established respectively using support vector regression (SVR) method. The experimental database is utilized to validate the effectiveness of SVR models. Taking the total stress sigma as the optimization objective of process parameters, the optimal combination of turning parameters within given parameter ranges is finally obtained by combining SVR models with improved particle swarm optimization (PSO) algorithm. Further, the comparisons between genetic algorithm (GA), traditional and improved PSO algorithms are conducted, which indicate that the improved PSO algorithm has an advantage in convergence efficiency. Finally, verification experiments are performed to confirm the minimization of surface residual stress. The results show that the proposed optimization strategy of process parameters is effective and reliable, while at the same time providing a good prediction accuracy. (C) 2020 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据