基于CSO-LSSVM模型的选择性激光烧结成型工艺参数优化

Optimization of selective laser sintering molding processing parameters based on CSO-LSSVM model

成型收缩是影响选择性激光烧结技术(selective laser sintering,SLS)制件精度的关键因素,而工艺参数对材料烧结情况和收缩变形程度有着明显影响,因此选择合理的参数组合对减小精度误差和改善成型性能质量有着重要意义。为降低SLS成型件工艺参数优化试验成本,文章开发了一种名为CSO-LSSVM成型精度预测模型用于工艺参数的预测。该模型的设计思路是:首先,通过Sine映射、非线性切换因子和针孔成像反向学习等3种改进策略全方面协调增强了蛇优化器(snake optimizer,SO)的收敛精度和寻优速度,接着,将改进后的蛇优化器(chaotic multi-strategy enhanced snake optimizer,CSO)与最小二乘支持向量机(least square support vector machine,LSSVM)结合,整定关键核函数参数,提高模型预测精度和泛化能力。为验证CSO-LSSVM模型的有效性和优越性,利用Matlab软件在真实数据集基础上将其与LSSVM、BP(back propagation)神经网络以及极限学习机(extreme learning machine,ELM)模型进行对比。结果表明:文中所提方法具有更高的预测精度,其误差评价指标均方根误差、平均绝对百分比误差和平均绝对误差分别为0.5462、9.4877、0.4017。该模型可为SLS成型加工提供最优工艺参数,有效指导加工。

Molding shrinkage significantly impacts the precision of selective laser sintering(SLS)components,with process parameters playing a critical role in material sintering and shrinkage deformation.Enhancing molding performance quality holds paramount importance.To curtail testing costs in the optimization of process parameters for SLS-molded parts,we introduce the CSO-LSSVM molding accuracy prediction model.The model’s design rationale is multifaceted:first,we comprehensively enhance the convergence accuracy and optimization speed of the snake optimizer(SO)through a trio of improvement strategies—Sine mapping,nonlinear switching factors,and pinhole imaging reverse learning.Subsequently,we seamlessly integrate the termed chaotic multi-strategy enhanced snake optimizer(CSO)with the least square support vector machine(LSSVM)to fine-tune pivotal kernel function parameters,thereby augmenting predictive accuracy and generalization capabilities.To affirm the validity and superiority of the CSO-LSSVM model,we leverage Matlab software for comparative analysis against LSSVM,BP(back propagation)neural network,and extreme learning machine(ELM)models using authentic datasets.Results unequivocally establish the method's heightened predictive accuracy,substantiated by error evaluation metrics:root mean square error of 0.5462,mean absolute percentage error of 9.4877,and mean absolute error of 0.4017,respectively.This model facilitates the provisioning of optimal process parameters for SLS molding,thereby offering effective processing guidance.