各单一选线判据从原始故障数据中提取出各自需要的故障特征量并离散化。
The fault characteristic quantity with each selection method is extracted from the original data and discretized.
给出了该方法的理论分析,故障特征量的选取,神经网络设置和训练的具体步骤。
Theoretical analysis, choice of fault characteristics and practical procedure of neural network setting and training are given out.
本文着重讨论了在内燃机故障诊断中常用的故障特征量。通过理论和实验方法,对这些故障特征量的敏感性进行了分析。
This paper discusses some common fault eigenvalues in the fault diagnosis of internal combustion engines and makes analysis of this eigenvalues by using theoretical and experimental methods.
应用推荐