摘要
在螺杆泵井故障诊断技术中,有功功率信号最能全面反映螺杆泵井的泵况。提出一种基于小波包分析结合Elman神经网络的故障诊断方法,该方法采用小波包对螺杆泵有功功率信号进行消噪滤波,将不同频段的故障信号进行3层db4小波包分解,根据各频段功率谱的变化提取故障特征,应用Elman神经网络进行识别。利用Matlab仿真,结果表明,该方法能有效提高螺杆泵井的故障诊断准确性。
In the fault diagnosis technology of progressing cavity pump well,the signals of active power can fully reflect the status of progressing cavity pump wells.A fault diagnosis method for cavity pump wells based on wavelet analysis and Elman neural network was proposed.This method used wavelet time-frequency analysis technology for de-noising and filtering of active power signals,used 3-layer db4 wavelet packet to decomposition fault signal of different frequencies,extracted fault feature based on changes in band power spectrum,then used Elman neural network to identify the fault.By use of Matlab simulation,the results show that this method can effectively improve the diagnostic accuracy of progressing cavity pump wells.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2012年第4期912-915,共4页
Journal of System Simulation
基金
国家自然科学基金青年科学基金项目(61004067)
黑龙江省教育厅科学技术研究项目(12511014)
关键词
故障诊断
小波包分析
ELMAN神经网络
螺杆泵
fault diagnosis
wavelet analysis
Elman neural network
progressing cavity pump
