基于小波包分析和Elman网络的切削表面粗糙度预测方法  

Reasearch on Prediction of Cutting Surface Roughness Based on Wavelet Packet Analysis and Elman Network

作　　者：迟军[1] 陈廉清[1] 杨超珍[1] 

机构地区：[1]宁波工程学院,宁波315016

出　　处：《中国机械工程》2010年第7期822-826,共5页China Mechanical Engineering

基　　金：宁波市自然科学基金资助项目(2006A610035)

摘　　要：提出了一种基于松散型小波网络的切削表面粗糙度预测方法。结合切削参数和切削振动理论,建立了预测网络结构,为避免频域混叠,采用小波包改进算法来实现振动信号去噪。根据振动加速度及切削参数,利用Elman网络的非线性映射和学习机制,实现切削表面粗糙度的实时在线预测。为减少训练时间,用遗传算法对网络权重进行预先优化。实验表明,该方法的预测误差小于3%。A forecast method based on relax--type wavelet network for cutting surface toughness was indicated. The forecasting network structure was established by considering the intluence ot cutting parameters and vibration. The noise in cutting vibration signals was tiltered with the retormed wavelet pack algorithm to avoid aliasing in frequency domain. The real--time forecast was achieved by the nonlinear mapping and learning mechanism in Elman network according to the vibration accelera- tion and cutting parameters. The weights in network were optimized with genetic algorithm in ad- vance to reduce learning time. The forecasting error of this method is less than 3 ~ in experiments.

关 键 词：遗传算法 切削振动 小波网络 表面粗糙度 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]