灰色神经网络模型在自由曲面加工误差预测中的应用  

Application of Gray Neural Network Models in Prediction ofFree-form Machining Errors

作　　者：马大洋 陈岳坪[1] 曾林安 Ma Dayang;Chen Yueping;Zeng Linan(School of Mechanical and Automotive Engineering,Guangxi University of Science and Technology,Liuzhou,Guangxi 545616,China)

机构地区：[1]广西科技大学机械与汽车工程学院

出　　处：《工具技术》2023年第11期151-155,共5页Tool Engineering

基　　金：国家自然科学基金(51565006,52165054);广西自然科学基金(2020GXNSFAA1591,2018GXNSFAA050085);2016年广西高校高水平创新团队及卓越学者计划(桂教人[2016]42号);广西科技大学创新团队支持计划(科大科研发[2017]64号)。

摘　　要：为了有效预测自由曲面的加工误差,结合灰色模型和BP神经网络模型提出了一种改进型麻雀搜索算法优化的灰色神经网络模型。通过引入鸟群算法更新麻雀算法中个体的位置,提升麻雀搜索算法的搜索能力;采用改进的麻雀搜索算法优化BP神经网络,避免BP神经网络在权值和阈值选择时的随机性太强,从而提高预测结果的稳定性。实验结果表明,改进麻雀搜索灰色神经网络对自由曲面加工误差预测的最大残差绝对值为8.52μm,比粒子群灰色神经网络和混沌海豚群灰色神经网络的预测结果分别减少了63.74%和61.76%,说明改进麻雀搜索灰色神经网络能有效提高预测精度。In order to effectively predict the machining error of free-form surfaces,this paper combine the gray model with the BP neural network model and propose a gray neural network model optimized by an improved sparrow search algorithm.The search capability of the sparrow search algorithm is improved by introducing a bird swarm algorithm to update the position of individuals in the sparrow algorithm,and the improved sparrow search algorithm is used to optimize the BP neural network to avoid the BP neural network being too random in the selection of weights and thresholds,thereby improving the stability of the prediction results.The experimental results show that the maximum absolute value of residuals predicte by the improved sparrow search gray neural network for free-form surface machining error is 8.52μm,which are reduced by 63.74%and 61.76%compared with the prediction results of particle swarm gray neural network and chaotic dolphin swarm gray neural network respectively,indicating that the improved sparrow search gray neural network can effectively improve the prediction accuracy.

关 键 词：加工误差预测 灰色神经网络 麻雀搜索算法 自由曲面 

分 类 号：TG702[金属学及工艺—刀具与模具] TH124[机械工程—机械设计及理论]