| 基于神经网络的多特征融合刀具磨损量识别 |
| |
| 引用本文： | 郑建明,李言,肖继明,李淑娟,袁启龙,洪伟.基于神经网络的多特征融合刀具磨损量识别[J].机械科学与技术(西安),2002,21(1):111-113. |
| |
| 作者姓名： | 郑建明 李言 肖继明 李淑娟 袁启龙 洪伟 |
| |
| 作者单位： | 西安理工大学机仪学院 西安710048
(郑建明，李言，肖继明，李淑娟，袁启龙)，西安理工大学机仪学院 西安710048(洪伟) |
| |
| 基金项目： | 机械工业发展基金资助项目 (CF0 0 13 ) |
| |
| 摘 要： | 采用切削力信号监测钻削过程钻头的磨损量 ,分别从时域、频域提取了切削力信号的均值、方差、峭度系数和特定频段能量作为刀具磨损的特征信号 ,讨论了特征信号随着刀具磨损量增加的变化规律 ,并将各个特征信号构成的特征矢量输入多层反传神经网络进行融合 ,实现钻削过程刀具磨损量的智能识别。试验结果表明该方法能有效实现多特征融合 ,但识别精度和推广能力有待进一步提高
|
| 关 键 词： | 钻头磨损 识别 特征 神经网络 |
| 文章编号： | 1003-8728(2002)01-0111-03 |
| 修稿时间： | 2000年11月27 |
On Identification of Tool Wear by Multiple Features Fusion Based on Artificial Neural Network |
| |
| ZHENG Jian ming,LI Yan,XIAO Ji ming,LI Shu juan,YUAN Qi long,HONG Wei.On Identification of Tool Wear by Multiple Features Fusion Based on Artificial Neural Network[J].Mechanical Science and Technology,2002,21(1):111-113. |
| |
| Authors: | ZHENG Jian ming LI Yan XIAO Ji ming LI Shu juan YUAN Qi long HONG Wei |
| |
| Abstract: | This paper presents a method for the monitoring of tool wear in drilling process using cutting force signal. The following were used as the signal features of tool wear: the Kurtosis coefficient; the energy of special frequency range of cutting force signal; and the peak value and the standard deviation from the time and frequency domain. The relationships between the signal features and tool were discussed, then the vectors of the signal features were inputted to neural network for fusion in order to realize intelligent identification of tool wear. The experimental results show that this method can realize fusion of multiple features effectively. |
| |
| Keywords: | Tool wear Monitoring Feature Neural network |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
