基于切削力的小波神经网络刀具磨损状态监测  

Monitoring of Cutting Tool Wear Based on Cutting Force by Using Wavelet Neural Network

作　　者：杨永[1,2] 

机构地区：[1]广东技术师范学院机电学院,广东广州510635 [2]广东省高等学校科研型重点实验室,广东广州510635

出　　处：《机床与液压》2009年第7期250-251,269,共3页Machine Tool & Hydraulics

基　　金：国家自然科学基金项目(40676040)

摘　　要：为了有效地进行刀具状态监测,采用小波神经网络对刀具进行故障诊断。通过小波变换提取刀具磨损切削力信号的特征,利用小波包分解技术对信号进行分析,得到有效的特征量作为BP神经网络的输入样本,并对网络进行学习训练,完成对刀具磨损状态的有效识别。仿真结果表明该方法是有效的。In order to improve cutting tool condition monitor, a method of cutting tool fault diagnosis based on wavelet and artificial networks with relaxed structure was proposed. Features of cutting force were extracted from wavelet decomposition. The selected features were considered as inputs to BP neural networks to complete recognition of the status of the cutting tool. Experiments indicate that the methed is effective.

关 键 词：切削力 小波变换 神经网络 刀具监测 

分 类 号：TG7[金属学及工艺—刀具与模具]