基于SVM和BP神经网络的轴系故障诊断

阐述SVM（support vector machine）和BP（back propagation）两种神经网络的基本原理和算法,将其应用于柴油机轴系的故障诊断与识别,建立轴系故障的SVM故障诊断模型,并与BP神经网络进行对比分析研究。结果表明,SVM和BP神经网络都具有精度较高的故障识别能力,但SVM整体性能优于BP神经网络,具有较快的训练速度和较强的非线性映射能力,非常适用于轴系的状态监测和故障诊断。

Fault Diagnosis of Rotating Shaft Systems Based on SVM and BP Neural Network

The basic theory and arithmetic of SVM（support vector machine） and BP（back propagation） neural network are expatiated,which is applied successfully to fault diagnosis of Marine Diesel Engine＇s rotating shaft system.The SVM fault diagnosis model of gearbox was constructed,and was analyzed contrastively with the BP neural network.The study result showed that SVM and BP neural net all have highly accurate capability of fault identification,but the performance of SVM neural net is better than that of BP neural net.It has the quick training pace and strong nonlinear mapped capability,and is very suitable to the condition monitoring and fault diagnosis of rotating shaft system.