基于集合经验模态分解-支持向量机的高压共轨系统故障诊断方法

柴油机高压共轨系统运行时轨压波动信号波动较大且非线性特征较为明显，使其故障诊断较为困难。针对高压共轨系统轨压信号状态参数难以提取与识别的问题，提出一种基于集合经验模态分解（EEMD）—支持向量机（SVM）的故障诊断方法。通过EEMD将轨压信号分解为一系列固有模态函数，利用过零率曲线确定的特征提取准则提取本征模态函数中的特征值。将提取的特征值输入SVM中进行故障类型的诊断。通过AME Sim软件仿真实验获得轨压信号，对比7种不 同的特征值选择方法，最终选取能量特征值构建特征值向量并进行识别和诊断结果分析，以验证该方法的正确性与准确性。结果表明：所提出的基于EEMD—SVM的高压共轨系统故障诊断方法能够对6种不同的运行状态进行状态识别，平均故障诊断正确率可达96.11%。

Fault Diagnosis Method of High-pressure Common Rail System Based on EEMD-SVM

When the high-pressure common rail system for diesel engine is running， the rail pressure fluctuation signal fluctuates greatly and has obvious nonlinear characteristics， which makes the fault diagnosis more difficult. For the problem that the state parameters of rail pressure signal in high-pressure common rail system are difficult to extract and identify， a fault diagnosis method based on ensemble empirical mode decomposition (EEMD)-support vector machine (SVM) is proposed. The rail pressure signal is decomposed into a series of eigenmode functions by EEMD， and the eigenvalues in the eigenmode functions are extracted using the feature extraction criterion determined by the zero-crossing rate curve. The extracted eigenvalues are input into SVM for fault type diagnosis. The rail pressure signal is obtained through AMESim software simulation experiment， and seven different eigenvalue selection methods are compared. Finally， the energy eigenvalue is selected to construct the eigenvalue vector for identification， and the diagnosis results are analyzed to verify the correctness and accuracy of the proposed method. The results show that the proposed EEMD-SVM-based fault diagnosis method for high-pressure common rail system can be used to identify six different operating states， with the average fault diagnostic accuracy rate of 96.11%.