UCS Neural Network Model for Real Time Sand Prediction


Article Preview

Exploration and production activities have moved into more challenging deep-water and subsea environments. Many of the clastic reservoirs in these environments are characterized by thick overburden, HP-HT and largely unconsolidated formations with challenging sand management issues. For effective overall field/reservoir management, it is crucial to know if and when sand would fail and be ultimately produced. Field-life sanding potential evaluation and analysis, which seeks to evaluate the sanding potential of reservoir formations during the appraisal stage and all through the development to the abandonment stage, is therefore necessary so that important reservoir/field management decisions regarding sand control deployment can be made. Recent work has identified Unconfined Compressive Strength (UCS) as a key parameter required for the evaluation and analysis of sanding potential of any reservoir formation. There is therefore the need to be able to predict this important sanding potential parameter accurately and in real time to reduce the level of uncertainties usually associated with sanding potential evaluation and analysis. In this work, neural network coded in C++ was trained with log-derived petrophysical, geomechanical and textural data to develop a stand-alone model for predicting UCS. Real-time functionality of this model is guaranteed by real time data gathering via logging while drilling (LWD) and other measurement while drilling (MWD) tools. The choice of neural network over and above other methods and techniques which have been widely used in the industry was informed by its ability to better resolve the widely known complex relationship between petrophysical, textural and geomechanical strength parameters.







G. F. Oluyemi et al., "UCS Neural Network Model for Real Time Sand Prediction", International Journal of Engineering Research in Africa, Vol. 2, pp. 1-13, 2010

Online since:

June 2010




[1] G. Oluyemi , B. Oyeneyin and C. Macleod, Prediction of directional grain size distribution: An integrated approach. SPE 105989 presented at the 30th SPE Nigeria International Technical Conference and Exhibition, Abuja, Nigeria, July 31st - Aug 2 nd (2006).

DOI: 10.2118/105989-ms

[2] G.F. Oluyemi, Intelligent Grain Size Profiling Using Neural Network and Application to Sanding Potential Prediction in Real Time. PhD Thesis, Robert Gordon University, Aberdeen UK, (2007).

[3] K. Edlmann, J. M. Somerville, B. G. D. Hamilton and B. R. Crawford, Predicting rock mechanical properties from wireline porosities. SPE/ISRM 47344 presented at the SPE/ISRM Eurock '98, Trondheim, Norway, 8 - 10 July, (1998).

DOI: 10.2118/47344-ms

[4] K. Tokle, P. Horsrud and R. K. Bratli, Predicting uniaxial compressive strength from log parameters. SPE 15645 presented at the 61st Annual Technical Conference and Exhibition of the Society of Petroleum Engineers, New Orleans, LA Oct. 5 - 8. (1986).

DOI: 10.2118/15645-ms

[5] T. Master, Practical Neural network Recipe in C++. Academic Press Inc. San Diego, (1993).

[6] M.B. Oyeneyin and A.T. Faga, Formation-grain-size prediction whilst drilling: A key factor in intelligent sand control completions. SPE 56626 presented 1999 SPE Annual Tech. Conf. and Exhibition, Houston, Texas, 3-6 Oct (1999).

DOI: 10.2118/56626-ms

[7] L. Yu, S. Wang, S. and K.K. Lai, An Integrated Data Preparation Scheme for Neural Network Data Analysis. IEEE Transactions on Knowledge and Data Engineering 18 (2), (2006).

DOI: 10.1109/tkde.2006.22

In order to see related information, you need to Login.