Fault Identification of Rod-less Pumping with Water as Power Based on BP Neural Network

DOI

10.2991/icmmct-18.2018.16How to use a DOI?

Keywords

Fault identification, rod-less pumping, BP neural network, vibration signal.

Abstract

According to the time-varying and nonlinear characteristics of rod-less pumping system with water as power, a fault identification method was put forward based on BP neural network. Through studying fault mechanism and vibration signal characteristics on pumping unit, the time and frequency domain feature parameters which were used as the input of neural network were extracted.Then, according to the specific characteristics of the fault identification of pumping unit, the fault identification system was constructed. Finally, it use the experimental data obtained by fault simulation experiment platform to construct the training samples, and train neural network based on MATLAB. The results show that BP neural network can identify the fault types of the pumping unit, which has a relatively high accuracy and feasibility.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Junyan Lv
AU  - Fanzhao Meng
AU  - Xinwei Wang
PY  - 2018/06
DA  - 2018/06
TI  - Fault Identification of Rod-less Pumping with Water as Power Based on BP Neural Network
BT  - Proceedings of the 2018 6th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2018)
PB  - Atlantis Press
SP  - 90
EP  - 93
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-18.2018.16
DO  - 10.2991/icmmct-18.2018.16
ID  - Lv2018/06
ER  -