摘要
针对薄壁件在侧铣加工过程中容易产生让刀变形的问题,为实现薄壁件侧铣加工方式下变形量的预测,提出了一种基于SAPSO-BP神经网络技术预测薄壁件侧铣加工变形的方法。通过建立T型薄壁件侧铣加工仿真模型,并用实验验证其有效性,为后续神经网络提供训练样本;再引入模拟退火粒子群算法(SAPSO),优化BP神经网络的初始权值与阈值,建立基于SAPSO-BP的薄壁件侧铣加工变形预测模型,并验证分析了其可行性。
In order to predict the deformation of thin-walled parts during side milling,a new method based on SAP-SO-BP neural network is proposed to predict the deformation of thin-walled parts in side milling.Through the establishment of T-shaped thin-walled workpiece side milling simulation model,and experimental verification of its feasibility,provide training samples for the follow-up neural network;then introduce simulated annealing particle swarm optimization(SAPSO)to optimize the initial weights and thresholds of BP neural network,establish the deformation prediction model of thin-walled workpiece side milling based on SAPSO-BP,and verify and analyze its reliability.
作者
郑华林
冯博
张世贵
张晟玮
李湉
ZHENG Hualin;FENG Bo;ZHANG Shigui;ZHANG Shengwei;LI Tian(College of Mechanical and Electrical Engineering,Southwest Petroleum University,Chengdu 610500,CHN;Aecc Aero Science and Technology Co.,Ltd.,Chengdu 610500,CHN)
出处
《制造技术与机床》
北大核心
2021年第4期65-69,共5页
Manufacturing Technology & Machine Tool
基金
四川省科技厅重点研发项目(19ZDZX0055)。