摘要
液压泵的性能直接影响整个液压系统的正常工作,为此需要对其进行状态监测和故障预测。采集液压泵的振动信号,运用集总经验模式分解(EEMD)和平滑能量算子解调相结合的方法进行包络解调;采取小波包分析方法得到了故障特征向量;在研究支持向量机回归估计基本原理的基础上,建立了小波包分解和支持向量机相结合的预测模型。采用液压泵历史数据对模型进行了验证,结果表明,基于支持向量机的预测模型和故障映射模型可以有效地对液压泵进行故障预测。
The performance of hydraulic pump will directly affect the entire hydraulic system, so it is essential for its condition monitoring and fault prediction. The vibration signals for hydraulic pump were collected and a kind of method was presented,which can get fault feature based on EEMD and smoothed energy operation separation. Wavelet packet was used to decompose energy of frequen- cy area in order to get fault feature vectors. On the basis of studying the principles of SVM regression estimate, a prediction model was built, which was based on wavelet packet theory and SVM. The model were validated through the historical data of the hydraulic pump, and the experimental results show that the SVM regression model and fault mapping model can predict the faults effectively.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2013年第7期926-931,共6页
China Mechanical Engineering
基金
国家自然科学基金资助项目(51275524)
关键词
集总经验模式分解(EEMD)
能量算子
小波包
支持向量机
液压泵
ensemble empirical mode decomposition（EEMD）
energy operator
wavelet packet
support vector machine（SVM）
hydraulic pump
