车削刀具磨损声发射信号的云特征分析

发布时间：2018-06-16 03:27

本文选题：切削刀具 + 刀具磨损　；参考：《农业工程学报》2016年20期

【摘要】：针对刀具磨损状态监测和磨损量预测研究中特征提取这一关键技术,该文提出了基于云理论的信号特征提取方法。首先,采用小波包分析对声发射信号进行信号分解和重构,滤除噪声对提取特征参数的影响;其次根据重构信号的统计分布特性,利用逆向云算法提取信号敏感频带的期望值、熵及超熵云特征参数,定量分析刀具在不同切削条件下3种云特征参数随磨损量增大所呈现的变化规律;最后,通过散点图分析3种特征参数表征刀具磨损声发射信号的有效性。结果表明:刀具磨损声发射信号具有明显的云特性,3种云特征参数与刀具磨损状态具有明显的对应关系,可作为刀具磨损状态监测、磨损量预测的特征参数;云理论在刀具磨损监测领域的应用,扩大了知识的表示范围。
[Abstract]:Aiming at the key technology of feature extraction in tool wear condition monitoring and wear prediction research, a method of feature extraction based on cloud theory is proposed in this paper. Firstly, wavelet packet analysis is used to decompose and reconstruct the acoustic emission signal to filter the effect of noise on extracting characteristic parameters. Secondly, according to the statistical distribution characteristics of reconstructed signal, the expected value of signal sensitive frequency band is extracted by reverse cloud algorithm. Entropy and hyperentropy cloud characteristic parameters, quantitative analysis of the tool under different cutting conditions with the increase of wear characteristics of the three cloud parameters of the law; finally, The validity of tool wear acoustic emission signal is characterized by three characteristic parameters. The results show that the acoustic emission signals of tool wear have obvious cloud characteristics and three kinds of cloud characteristic parameters have obvious corresponding relationship with tool wear state and can be used as characteristic parameters of tool wear condition monitoring and wear quantity prediction. The application of cloud theory in tool wear monitoring expands the scope of knowledge representation.
【作者单位】：东北电力大学机械工程学院;
【分类号】：TH165+.3;;TP206

【相似文献】