基于小波包和BP神经网络的潜油直驱螺杆泵系统故障诊断

Fault Diagnosis in Direct-drive Progressing Cavity Pump System Based on Wavelet Packets and BP Neural Network

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.