Time Series Analysis in the Task of Oil Equipment Malfunctions Forecasting

DOI

10.2991/icfcce-14.2014.39How to use a DOI?

Keywords

Forecasting, neural network, oilfield equipment, malfunction, Kalman filter.

Abstract

The task of oilfield equipment malfunctions’ early prevention is considered in the paper. Input data for the analysis are the indications of sensors, established in the well and represented as time series set. Due to the forecasting analysis (predictive analytics) of the given set it is possible to discover a new data vector, which will allow to classify the possible equipment failure and to eliminate it proactively. The main stage of this task is the prediction of a single time series. In this paper, we propose a new method of forecasting using r/ - algorithm and the artificial neural network training algorithm (GAhNN) [1], previously developed by the authors. In the paper a new forecasting method, based on the r/ algorithm and the algorithm of artificial neural network training (GAhNN) [1], developed by authors before, is offered. Comparison with the known mostly applied forecasting algorithms – Kalman filter and ARIMA is fulfilled.

Copyright

© 2014, 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  - Iakov S. Korovin
AU  - Maxim V. Khisamutdinov
PY  - 2014/03
DA  - 2014/03
TI  - Time Series Analysis in the Task of Oil Equipment Malfunctions Forecasting
BT  - Proceedings of the 2014 International Conference on Future Computer and Communication Engineering
PB  - Atlantis Press
SP  - 157
EP  - 159
SN  - 1951-6851
UR  - https://doi.org/10.2991/icfcce-14.2014.39
DO  - 10.2991/icfcce-14.2014.39
ID  - Korovin2014/03
ER  -