基于模糊神经网络的深孔加工刀具磨损率预测  

Tool Wear Rate Prediction in BTA Drilling Base on Fuzzy Neural Network

作　　者：李孟虔 苗鸿宾[1,2] 王婷 王涛 LI Mengqian;MIAO Hongbin;WANG Ting(School of Mechanical Engineering,North University of China,Taiyuan 030051,China;Shanxi Province Deep Hole Machining Center,Taiyuan 030051,China)

机构地区：[1]中北大学机械工程学院,太原030051 [2]山西省深孔加工工程技术研究中心,太原030051

出　　处：《机械设计与研究》2020年第1期134-137,148,共5页Machine Design And Research

基　　金：中北大学科技立项项目(20181512)。

摘　　要：刀具的过快磨损不仅增大加工成本,也影响工件的最终加工质量,因此预测和减少刀具磨损率具有重要意义。由于BP神经网络本身容易陷入局部极小值、收敛速度慢等缺陷,且深孔加工过程及其复杂,无法建立加工中刀具磨损率与加工参数之间的准确数学模型,故采用模糊神经网络建立BTA刀具磨损率在线钻削模型。仿真和实验结果表明,该模型能有效预测BTA刀具磨损率,对提高刀具寿命和加工深孔的质量具有一定的意义。The excessive wear of the tool not only increases the machining cost,but also effect the final machining quality of the parts,so it is important to predict and reduce the wear rate.Focusing on BP neural network itself is easy to fall into local minimum point,low rate of convergence etc.And the intricate deep hole machining process cannot establish an precise mathematical model between the wear rate and the machining parameters during working.Therefore,the on-line drilling model of wear rate of BTA tool was built by using fuzzy neural network.The simulation and experimental results show that this model can effectively predict the wear rate of BTA tools,which is effective for improving tool life and deep hole drilling quality.

关 键 词：BTA钻削 刀具磨损率 模糊神经网络 预测 

分 类 号：TG713[金属学及工艺—刀具与模具] TP18[自动化与计算机技术—控制理论与控制工程]