摘要
针对传统预测深孔加工中钻削力精度不高的问题以及BP神经网络本身存在的缺陷,提出了BAS-BP神经网络预测模型。文章基于天牛须算法与BP神经网络相互结合,利用天牛须算法计算优化BP神经网络中的初始权值与阀值,从而建立BAS-BP神经网络的预测模型。并与传统BP神经网络预测模型进行对比。结果表明BAS-BP神经网络克服了训练时间长、收敛速度慢的缺点,预测精度明显提高。
Aiming at the problem of low accuracy of traditional prediction of drilling force in deep hole processing and the defect of BP neural network itself, a prediction model of BAS-BP neural network is proposed.Based on the combination of Beetle Antennae Search Algorithm and BP neural network, this paper uses Beetle Antennae Search Algorithm to calculate and optimize the initial weights and thresholds in BP neural network, and then establishes the prediction model of BAS-BP neural network. And compared with the traditional BP neural network prediction model. The results show that the BAS-BP neural network overcomes the shortcomings of long training time and slow convergence speed, and the prediction accuracy is obviously improved.
作者
刘晓峰
苗鸿宾
温静媛
LIU Xiao-feng;MIAO Hong-bin;WEN Jing-yuan(School of Mechanical Engineering, North University of China, Taiyuan 030051,China;Shanxi Province Deep Hole Machining Center, Taiyuan 030051,China)
出处
《组合机床与自动化加工技术》
北大核心
2019年第8期49-52,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
山西省回国留学人员项目基金(2015-077)
