摘要
为准确诊断潜油直驱螺杆泵系统故障,提出了一种基于小波包和BP神经网络的螺杆泵系统故障诊断方法。对螺杆泵在不同工况下有功功率进行3层小波包分解,提取小波包特征能量,然后构造小波包特征能量向量,并以该向量作为故障样本对3层BP神经网络进行训练,实现了智能化故障诊断。仿真结果表明:训练的BP网络能很好地诊断潜油直驱螺杆泵系统的故障。
To diagnose fault of direct-drive progressing cavity pump accurately, a new method of fault diagnosis based on wavelet packet and BP neural network is presented. Active powers in different working conditions are decomposed using three-layer wavelet packet. Wavelet packet characteristic energy(WPCE) is extracted. WPCE vectors are constructed. The vector is used as fault samples to train three-layer BP neural network. Intelligent fault diagnosing is realized. The simulation results show the trained BP neural network can diagnose the fault of direct-drive progressing cavity pump well.
作者
辛宏
杨海涛
魏韦
张岩
呼苏娟
Xin Hong Yang Haitao Wei Wei Zhang Yan Hu Sujuan(National Engineering Laboratory of Low Permeability Oil & Gas Field, Oil&Gas Process Technology Research Institute, Changqing Oilfield Company PetroChina, Xi'an, 710021, China)
出处
《石油化工自动化》
CAS
2017年第3期5-7,17,共4页
Automation in Petro-chemical Industry
基金
基金项目:长庆姬塬油田特低渗透油藏综合利用示范基地(国土资源部:1301-4-3)
关键词
故障诊断
小波包
BP神经网络
螺杆泵
fault diagnosis
wavelet packets
BP neural network
progressing cavity pump