基于BP神经网络双对数算法的刀具磨损分析及寿命预测研究  

Tool Wear Analysis and Life Prediction Based on BP Neural Network Double Logarithm Algorithm

作　　者：燕洋妞 何世文[1] 林孝良 伍小波[1] 林益斌 YAN Yangniu;HE Shiwen;LIN Xiaoliang;WU Xiaobo;LIN Yibing(College of Materials and Advanced Manufacturing,Hunan University of Technologyy,Zhuzhou 421007,China;Zhuzhou Huarui Precision Cutting Tools Corporation Limited,Zhuzhou 421000,China)

机构地区：[1]湖南工业大学材料与先进制造学院,湖南株洲412007 [2]株洲华锐精密工具股份有限公司,湖南株洲412000

出　　处：《湖南有色金属》2023年第6期67-72,共6页Hunan Nonferrous Metals

基　　金：湖南省自然科学基金项目(2020JJ6069);湖南工业大学研究生科研创新项目资助(CX2305)。

摘　　要：针对刀具磨损状态和寿命预测受刀具材质、切削参数及加工材料等影响使得测试复杂且难以准确预测的问题,建立基于BP神经网络结合双对数算法的刀具磨损分析与寿命预测模型。用交叉验证法改变切削参数,对前后刀面的失效分析可知主要以后刀面磨损为主。将切削过程中的刀片后刀面磨损值VB与时间T双对数化发现:在一定范围内,改变单个切削参数,只有后刀面的初始磨损量发生变化;改变多个切削参数,后刀面的初始磨损量和磨损速率都发生变化。根据耐用时间T双对数变换后结合BP神经网络进行仿真,结果显示偏离值降低至0.1,偏离度降低至0.2%,证明BP神经网络结合双对数变换算法在一致性与试验结果的符合度都高于单纯采用BP神经网络作为预测算法的计算结果,能更好的预测刀具寿命。Aiming at the problem that the tool wear state and life prediction are complicated and difficult to predict accurately due to the influence of tool material,cutting parameters and machining materials,a tool wear analysis and life prediction model based on BP neural network combined with double logarithm algorithm was established.By changing the cutting parameters with cross verification method,the failure analysis of the front and back tool faces shows that the main wear of the back tool faces is main.The wear value VB and time T of the blade in the cutting process were found by double logarithm.In a certain range,only the initial wear of the back tool face changes when a single cutting parameter is changed.When multiple cutting parameters are changed,the initial wear amount and wear rate of the back tool face are changed.The results show that the deviation value is reduced to 0.1 and the deviation degree is reduced to 0.2%,which proves that the consistency and conformity of the test results of the BP neural network combined with the BP neural network as the prediction algorithm are higher than the calculation results of the BP neural network as the prediction algorithm,and can better predict the tool life.

关 键 词：BP神经网络 双对数算法 切削参数 磨损分析 寿命预测 

分 类 号：TG115.58[金属学及工艺—物理冶金]