Identificación de fallas en sistemas de bombeo mecánico de petróleo utilizando neurofuzzy

Jorge Enrique Meneses Flórez; Fredy A. Garavito; Edxon Meneses

doi:10.24054/rcta.v1i37.973

Authors

Jorge Enrique Meneses Flórez Universidad Industrial de Santander (UIS)
Fredy A. Garavito Universidad Industrial de Santander (UIS)
Edxon Meneses Universidad Industrial de Santander (UIS)

DOI:

https://doi.org/10.24054/rcta.v1i37.973

Keywords:

Dynagrams, sucker-rod pumping, neurofuzzy

Abstract

In mechanical oil pumping, to minimize operating costs and maximize production, it is essential to identify problems quickly and accurately. The downhole dynagram is decisive in analyzing the working conditions of the pumping system, and normally the fault diagnosis has been based on the visual interpretation of its shape by a human expert. An architecture (NeFSuckerRod) is presented for the automatic diagnosis of the dynagram, based on a NeuroFuzzy system, which allows to identify faults and dispense with the human expert. By combining the learning power of artificial neural networks and the explicit representation of fuzzy logic knowledge and presenting a set of dynamometric charts with different faults, the NeuroFuzzy system is trained obtaining a fuzzy model capableof diagnosing faults in a system of pumping.

Downloads

Download data is not yet available.

References

Caballero F. y Salamanca (2011). Herramienta de aplicación software para clasificación de patrones de datos implementando una arquitectura Neuro-fuzzy. Universidad Industrial de Santander (UIS), Bucaramanga (Colombia). Tesis de pregrado.

Chemielewski M., y Grzymal J. (1996). Global discretization of continuous attributes as preprocessing for machine learning. International Journal of Approximate Reasoning, pp319–331.

DaCunha, J.J. y Gibbs, S.G. (2007). Modeling a Finite-Length Sucker Rod using the Semi-Infinite Wave Equation and a Proof to Gibbs’ Conjecture. SPE 108762.

de Best L. (2012). Shell's Smart Fields – Sustaining and Accelerating Benefits from Intelligent Fields. Intelligent Energy International, Utrecht, 150407-MS SPE Conference Paper.

Dickinson R. y Jennings J. (1990). Use of pattern-recognition techniques in analyzing downhole dynamometer cards, SPE Production Engineering, Vol. 5, No. 2, SPE-17313-PA.

Eickmeier, J.R. (1967). Diagnostic Analysis of Dynamometer Cards. SPE 1643. Journal of Petroleum Technology, January 1967, pp 97-106.

Gabor T. (2015). Sucker-Rod Pumping Handbook. Gulf Professional Publishing.

Gibbs, S. y Nelly, A. (1966). Computer diagnosis of down hole conditions in sucker rod pumping wells. Journal of Petroleum Technology, Vol. 18, No.1, SPE1165PA.

Gilbert, W.E. (1936). An Oil-Well Pump Dynagraph. Drilling and Production Practice, American Petroleum Institute. New York.

Gómez, A.E., Archila, J.F. y Meneses, J.E. (2013). Adquisición y tratamiento de señales de un acelerómetro triaxial MEMS, para la medición del desplazamiento de una extremidad inferior, Revista Colombiana de Tecnologías de Avanzada Vol. 1 No. 21, pp. 113-118.

McCoy J. y Podio L. (1995). Method and Apparatus for measuring pumping rod position and other aspects of a pumping system by use of an accelerometer. Patent US5406482.

Meneses J.E. y Meneses D.P. (2020). Arquitectura hardware/software para un prototipo de pozo inteligente en un campo petrolero maduro, Revista Colombiana de Tecnologías de Avanzada Vol. 2, No. 36, pp. 109-121

Meneses J.E., García J.D. y Ferreira D.A. (2015). Acelerómetros MEMS en el desarrollo de pozos y campos petroleros inteligentes. Revista Colombiana de Tecnologías de Avanzada Vol. 2, No. 26, pp. 128-135.

Nauck, D., Kruse, R. (1995). Nefclass - a Neuro- fuzzy Approach for the Classification of Data. Proceedings of the 1995 ACM symposium on Applied computing.

Nauck, D. (1994) A fuzzy perceptron as a generic model for neuro-fuzzy approaches. Proc. Fuzzy-Systems’94, 2nd GI-Workshop, Munich, Siemens Corporation.

Sanchez J. P., Festini D. y Bel O. (2007). Beam Pumping System Optimization Through Automation. Latin American & Caribbean Petroleum Engineering Conference, Buenos Aires (Argentina), SPE 108112.

Sletcha B., Vivas, C., K. Saleh, F., Ghalambor A. y Salehi S. (2020). Digital Oilfield: Review of Real-time Data-flow Architecture for Upstream Oil and Gas Rigs, International Conference and Exhibition on Formation Damage Control, Lafayette, (Louisiana, USA), 199298-MS SPE Conference Paper.

Yousefi J., y Hamilton-Wright A. (2016). Classification Confusion within NEFCLASS Caused by Feature Value Skewness in Multi-dimensional Datasets. Proceedings of the 8th International Joint Conference on Computational Intelligence (IJCCI 2016) - Volume 2: FCTA, pages 21-29 ISBN: 978-989-758-201-1. Porto (Portugal) Nov 9 al 11.

Zarate C. (2016). Preprocesador de fuzzy inference system (FIS) y motor de inferencia difusa para la plataforma de desarrollo embebida Freescale TWR-K70F120M. Universidad Industrial de Santander (UIS), Bucaramanga (Colombia). Tesis de pregrado.