摘要
研究了径向基函数神经网络在硬质合金刀具切屑形态图像识别中的应用 ,提出了面积比、欧拉数、分散度等硬质合金刀具切屑形态图像的几何特征 ,以上述特征作为神经网络的输入矢量 ,利用径向基函数网络 (RBF) ,采用了递推最小二乘法训练该网络。最后开发了相应的计算机程序 ,通过实验验证本算法具有良好的实时处理性和适应性 ,识别率达到 95 % ,有利于硬质合金刀具切削过程的监控和切削参数的优选。
In this paper chip shapes were recognized by using of radbas neural network. We put forward area ratio feature, Euler number feature, etc. geometry feature of chip shape image and thing of those features as inputting vector of neural network. Adopt radbas neural network and training the network using RLS. On the base of experiment, we develop calculating program and it has excellent real time processing capability and adaptability. The recognizing ratio reaches to 95%.
出处
《硬质合金》
CAS
2002年第3期152-156,共5页
Cemented Carbides
基金
黑龙江省博士后科学研究基金项目
