摘要
介绍了一种采集旋转工件图像的光学监测系统,提出通过二维小波分析工件纹理图像,提取纹理特征,设计了基于动态和静态神经网络的刀具状态识别系统,该系统可用于自动化加工中刀具诊断,仿真证明了有效性。
A Optical monitoring system for collecting the shape of turning workpice is introduced here, through 2-D wavelet analysis work piece image, extract texture feature, a tool conditions recognition system based on static and dynamic neural network is devised,the system can be used in cutting tool diagnosis in automatic precise processing, the validity of the theoretical algorithm is demonstrated by simulation results.
出处
《组合机床与自动化加工技术》
2007年第12期46-49,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
河北省科技厅科技攻关项目"数控加工中心智能监控技术的研究(05212110d)"
关键词
刀具状态监测
图像处理
纹理分析
神经网络
tool conditions monitoring
image processing
texture analysis
neural network
