Research on Automatic Diagnosis Based on ANN Well Conditions Fault

DOI

10.2991/isca-13.2013.6How to use a DOI?

Keywords

Pump Indicator Diagram; Finite-Difference; Neural Network; Fault Diagnosis

Abstract

This thesis combines the extraction of geometric characteristics and the neural network, which supplies a method that can define the operating conditions relatively accurately through the diagram feature parameter of the rod pumping system pump and avoids setting up and solving complex nonlinear dynamic equation while also achieving the automatic diagnosis functions of the malfunctions of oil wells. According to the analysis of the error results, we identify the accuracy and effectiveness of this model. Besides, we test the neural network which we have just set up by using the real-time data, and the test results indicate the validity of the method in this thesis.

Copyright

© 2013, 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  - ZhengJia Wu
AU  - ShaoXiong Huang
AU  - YueSheng Luo
PY  - 2013/10
DA  - 2013/10
TI  - Research on Automatic Diagnosis Based on ANN Well Conditions Fault
BT  - Proceedings of 2013 International Conference on Information Science and Computer Applications
PB  - Atlantis Press
SP  - 33
EP  - 39
SN  - 1951-6851
UR  - https://doi.org/10.2991/isca-13.2013.6
DO  - 10.2991/isca-13.2013.6
ID  - Wu2013/10
ER  -