SVR-PSO算法在慢走丝线切割参数优化中的应用

针对慢走丝线切割加工中难以同时获得较快加工速度和较优表面质量的问题,从其加工参数与加工指标之间的高非线性关系入手,选取水压、脉冲时间、脉冲宽度、峰值电流和进给速率作为优化参数,以表面粗糙度(Ra)、材料去除率(MRR)作为优化指标,设计正交实验;创新运用支持向量机(SVR)结合粒子群算法(PSO)建立其多目标预测优化模型,得到最优加工参数。结果表明:所建立的多目标预测优化模型优化效果十分显著,相同Ra下MRR平均提高32%;相同MRR下Ra同比下降25%。

Application of SVR-PSO Algorithm in LSWEDM Parameters Optimization

In order to solve the problem of difficulty in achiving a higher material removal rate and a better surface integrity simul-taneously, the highly nonlinear relationship between process parameters and machining performance was studied.A Taguchi experiment was designed with water pressure, pulse-on time, pulse-off time, peak current and feed rate as the main optimization parameters, sur-face roughness ( Ra) and material removal rate ( MRR) as the optimization targets.It was innovative to apply the support vector ma-chines ( SVR) and particle swarm algorithm ( PSO) to acquire the optimized parameters combination by establishing a multi-objective model.The results show that the multi-objective optimization model is very efficient in increasing MRR and reducing Ra, by 32%and 25%respectively under same conditions of Ra and MRR.