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

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. ore 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.