主成分分析法在机车柴油机故障诊断中的应用

Application of Principle Component Analysis for Fault Diagnosis of Locomotive Disel Engine

运用主成分分析方法 ,经过矩阵变换、降低维数以提取故障信息的主要特征 ,实现对机车柴油机燃烧性能故障的诊断分析 ;通过实例说明 ,在有用信息量损失较小的前提下 ,该方法可以提炼故障信息而不影响分析结果 ,是解决多变量高维复杂系统简便有效的一种统计识别方法 .

The main characteristic of fault messages by reducing its dimensions through matrix conversion in the principal component analysis, and the fault of combustion function of locomotive disel engine is analyzed. Illustrated by an example, the paper proposes an approach which can concentrate fault information without influencing analytical results under the condition that the loss of useful messages is relatively small. It can also be a simple and effective statistical recognition method to solve multi-variable and multi-dimensional complicated system.