摘要
提出基于希尔伯特黄变换边际谱的柴油机故障诊断方法,对3110型柴油机几种故障工况及正常情况下的缸盖振动信号进行测试,采用抽区间采样分析法对缸盖振动信号进行时域特性分析,得出信号随时间和频率变化的精确表达。尝试以边际谱的最大峰值和最大峰值频率作为特征向量,用SVM分类器对柴油机的工作状态和故障类型识别。实验分析表明,该方法即使在小样本情况下也能准确有效地识别柴油机气门间隙变化和断油故障。
A new method of fault diagnosis for diesel engine based on Hilbert-Huang transformation （HHT） marginal spectrum and SVM model was put forward. The surface vibration signals were obtained under the fault condition and the normal condition for 3110 diesel. Interval sample method was used to analysis the property of its time domain characteristic to get an exact expression of signal over time and frequency variation. The maximum peak value of the marginal spec- trum and its frequency were regarded as the eigenvectors and served as input parameters of support vector machine （SVM） classifier to classify working condition of the diesel engine. The experimental results showed that the proposed approach can classify working condition of the diesel engine accurately and effectively even in the case of small number of samples.
出处
《船海工程》
2010年第3期73-76,80,共5页
Ship & Ocean Engineering
关键词
柴油机
故障诊断
HHT
边际谱
SVM
diesel engine
fault diagnosis
HHT
marginal spectrum
SVM
