ISSN   1004-0595

CN  62-1224/O4

高级检索
因子模糊化BP神经网络在磨粒识别中的应用[J]. 摩擦学学报, 2000, 20(2): 143-146.
引用本文: 因子模糊化BP神经网络在磨粒识别中的应用[J]. 摩擦学学报, 2000, 20(2): 143-146.
Application of Fuzzified-factor Based BP-network in Wear Debris Identification[J]. TRIBOLOGY, 2000, 20(2): 143-146.
Citation: Application of Fuzzified-factor Based BP-network in Wear Debris Identification[J]. TRIBOLOGY, 2000, 20(2): 143-146.

因子模糊化BP神经网络在磨粒识别中的应用

Application of Fuzzified-factor Based BP-network in Wear Debris Identification

  • 摘要: 在引入磨粒形态学描述了提取磨损颗粒显微形态特征的基础上,用人工神经网络技术,编制了用于磨损颗粒自动识别的BP网络计算机模拟程序,应用所引入的因子模糊化训练法可使训练速度加快,以异或问题为例,速度可提高5~10倍。用此网络对磨粒测试库进行识别实验发现,识别速度快且正常率在90%以上,优于传统的磨粒识别方法。

     

    Abstract: The program of auto identification of wear particles has been made by means of artificial neural network (ANN) technique,with which a set of morphology descriptors of wear debris are cited to describe the micro features of wear particles. During training of the network, the fuzzified factor based training technique is used, and the training process is accelerated rapidly. Taking the exclusive or problem (XOR problem) as an example, the training speed increases by five to ten times. The network has an identifying accuracy higher than 90% and is effective in identifying various wear particles.

     

/

返回文章
返回