基于激光熔化技术加工工艺参数优化研究  

Optimization study of processing parameters based on laser melting technology

作　　者：赵渭平 任伟 张雷伟 张华[1] ZHAO Weiping;REN Wei;ZHANG Leiwei;ZHANG Hua(Mechanical and Electrical Engineering College of Tongchuan Vocational and Technical College,Tongchuan 727031,Shaanxi China)

机构地区：[1]铜川职业技术学院机电工程学院,陕西铜川727031

出　　处：《粘接》2024年第1期129-132,共4页Adhesion

基　　金：铜川职业技术学院院级科研课题(项目编号:TZY202008)。

摘　　要：为进一步提升选区激光熔化技术加工材料的质量,提出一种基于PSO-BP神经网络的工艺参数优化模型,通过提升致密度进一步提升材料质量。其中,使用粒子群优化算法PSO对BP神经网络进行参数优化,进一步提升参数优化预测精度。实验结果表明,与基于传统的BP神经网络优化预测模型相比,基于PSO-BP神经网络的工艺参数优化模型具有更高的预测精度,优化后的预测致密度值更加接近于真实值,且优化预测过程的稳定性更好,更加适用于选区激光熔化技术的工艺参数优化,实现效果更佳的质量提升。To further improve the quality of materials processed by selective laser melting technology,a process parameter optimization model based on PSO-BP neural network was proposed,which improves the material quality by increasing the density.In this model,the particle swarm optimization algorithm PSO was used to optimize the parameters of BP neural network,and the prediction accuracy of parameter optimization was further improved.The experimental results showed that compared with the traditional BP neural network optimization prediction model,the PSO-BP neural network based process parameter optimization model had higher prediction accuracy,the predicted density value after optimization was closer to the true value,and the stability of the optimized prediction process was better.It is more suitable for optimizing process parameters of selective laser melting technology,achieving better quality improvement.

关 键 词：材料制备 选区激光熔化技术 BP神经网络 PSO 

分 类 号：TP392[自动化与计算机技术—计算机应用技术] TQ171.62[自动化与计算机技术—计算机科学与技术]