摘要
提出了一种基于小波神经网络的切削刀具状态监测方法 ,即提取反映刀具磨损状态的特征参数 ,利用小波神经网络的非线性模型 ,实现在线状态监测 ;同时针对多输入输出问题带来的网络规模大、收敛速度慢等问题 ,提出了一种网络优化算法 ,即采用改进的遗传算法寻找最优小波基元 ,从而简化小波网络并加快收敛。仿真实例证明该方法是有效的。
A condition detection method for cutting tools based on wavelet neural network(WNN) which collects multi-source feature parameters of cutting tools was proposed to realize on-line state detection based on the non-liner model of WNN.Then aiming at the problem of 'MIMO' diagnosis system-the 'dimension disaster' and the slow learning speed, the wavelet network is improved by optimization genetic algorithm in order to find the optimum wavelet neurons. Finally, the simpler structure and quickly convergent velocity of the new algorithm is demonstrated by simulation results.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2004年第4期321-324,共4页
China Mechanical Engineering
基金
河北省教育厅基金资助项目 (2 0 0 0 2 18)
关键词
刀具
状态监测
小波网络
优化的遗传算法
cutting tool
condition detection
wavelet neural network
optimum genetic algorithm
