摘要
特征提取是往复泵状态监测及故障诊断的关键环节。小波包变换是时间频率的局部化分析,尤其适合于非平稳信号。应用小波包变换,将往复泵振动信号分解到8个不同的频带,对各频带内的信号进行统计分析,形成包含待诊断部件故障信息的频带能量值作为故障诊断的特征指标。实例中,将小波包变换应用于往复泵泵阀故障分析,提取到了弹簧断裂时的频带能量特征指标,为往复泵故障诊断奠定了可靠的基础。
Characteristic extraction is a key step in the condition monitoring and fault diagnosis of reciprocating pump. Wavelet packet transform is the localization analysis of time and frequency, and especially suitable for non-stationary signal. In this paper, vibration signal of reciprocating pump was decomposed into eight frequency bands by wavelet packet transform and then energy of each band was calculated. At last, the wavelet packet transform was applied to the vibration analysis of reciprocating pump valve and the frequency energy characteristic of spring fault was extracted, which established a liable foundation for the fault diagnosis of reciprocating pump.
出处
《石油矿场机械》
2007年第1期1-4,共4页
Oil Field Equipment
基金
国家自然科学基金资助项目(编号50375103)
北京市教育委员会共建项目建设计划资助项目(编号XK114140478)
关键词
往复泵
故障诊断
特征提取
小波包变抉
reciprocating pump
fault diagnosis
characteristic extraction
wavelet packet
