Bottom hole pressure estimation using evolved neural networks by real coded ant colony optimization and genetic algorithm

Abstract Experience has proved that in the right conditions, significant technical and economic benefits like formation damage mitigation, increase in the rate of penetration, higher recovery, etc. can be achieved when the correct design of an Under-Balanced Drilling (UBD) program is considered. It is a fact that UBD precise bottom hole pressure (BHP) maintenance ascertains UBD success. Two phase flow through annulus is an ambiguous area of study to evaluate the flow parameters especially bottom hole pressure. Therefore, the ambiguous challenge of UBD hydraulics design which is greatly dependent on the annular pressure drop or BHP could be dealt with by virtue of intelligent solution. Therefore in this project, bottom hole pressure is estimated through 3 proposed methods. First, ANN with 7 neurons in its hidden layer is utilized to solve the non-straightforward problem of two phase flow in annulus (back propagation neural network, BP-ANN). The next methods correspond to optimized or evolved neural networks. Much more promising results were obtained when the highly efficacious tool of Ant Colony Optimization (ACO) was utilized as the second method to optimize the weights and thresholds of the neural networks. This method is called ACO-BP. In the third method called GA-BP, a trained neural network evolved by highly effective optimizing tool of Genetic Algorithm (GA) is trained. GA-BP shows perform better than BP-ANN. As a result, both GA and ACO are strongly shown to be highly effective to optimize the performance of the neural networks to estimate BHP.

[1]  Stuart L. Scott,et al.  A Neural Network Model for Prediction of Liquid Holdup in Two-Phase Horizontal Flow , 2004 .

[2]  Lakhmi C. Jain,et al.  Automatic generation of a neural network architecture using evolutionary computation , 1995, Proceedings Electronic Technology Directions to the Year 2000.

[3]  Chang-Hsu Chen,et al.  A committee machine with empirical formulas for permeability prediction , 2006, Comput. Geosci..

[4]  Mehmet Evren Ozbayoglu,et al.  Flow Pattern and Frictional-Pressure-Loss Estimation Using Neural Networks for UBD Operations , 2007 .

[5]  Lakhmi C. Jain,et al.  Neural Network Training Using Genetic Algorithms , 1996 .

[6]  Kwok-wing Chau,et al.  Application of a PSO-based neural network in analysis of outcomes of construction claims , 2007 .

[7]  Tom Gedeon,et al.  An integrated neural-fuzzy-genetic-algorithm using hyper-surface membership functions to predict permeability in petroleum reservoirs , 2001 .

[8]  Paulin Coulibaly,et al.  Nonstationary hydrological time series forecasting using nonlinear dynamic methods , 2005 .

[9]  Firat Hardalaç.  Classification of Educational Backgrounds of Students Using Musical Intelligence and Perception with the Help of Artificial Neural Networks , 2006, Proceedings. Frontiers in Education. 36th Annual Conference.

[10]  Whitfield Diffie,et al.  New Directions in Cryptography , 1976, IEEE Trans. Inf. Theory.

[11]  J. P. Brill,et al.  Pressure Drop Correlations for Inclined Two-Phase Flow , 1985 .

[12]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[13]  M. Mohammadi.  A Comprehensive Neural Network Model for Predicting Two-Phase Liquid Holdup Under Various Angles of Pipe Inclinations , 2006 .

[14]  Morteza Ahmadi,et al.  Design of neural networks using genetic algorithm for the permeability estimation of the reservoir , 2007 .

[15]  El-Sayed A. Osman,et al.  Artificial Neural Network Models for Identifying Flow Regimes and Predicting Liquid Holdup in Horizontal Multiphase Flow , 2004 .

[16]  Jack Salz.  Generation-recombination noise in solids , 1969, IEEE Trans. Inf. Theory.

[17]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[18]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[19]  J. P. Brill,et al.  Liquid Holdup in Wet-Gas Pipelines , 1987 .

[20]  Ge Xiurun,et al.  An improved PSO-based ANN with simulated annealing technique , 2005, Neurocomputing.

[21]  S. M. Lo,et al.  Application of evolutionary neural network method in predicting pollutant levels in downtown area of Hong Kong , 2003, Neurocomputing.

[22]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[23]  Stefan Bornholdt,et al.  General asymmetric neural networks and structure design by genetic algorithms: a learning rule for temporal patterns , 1992, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.