The present study investigates the effectiveness of evolutionary algorithms such as genetic algorithm (GA) evolved neural network in estimating roller compacted concrete pavement (RCCP) characteristics including flexural and compressive strength of RCC and also energy absorbency of mixes with different compositions. A real coded GA was implemented as training algorithm of feed forward neural network to simulate the models. The genetic operators were carefully selected to optimize the neural network, avoiding premature convergence and permutation problems. To evaluate the performance of the genetic algorithm neural network model, Nash-Sutcliffe efficiency criterion was employed and also utilized as fitness function for genetic algorithm which is a different approach for fitting in this area. The results showed that the GA-based neural network model gives a superior modeling. The well-trained neural network can be used as a useful tool for modeling RCC specifications.
Determination of fluid contacts in a hydrocarbon reservoir is extremely important in calculation of initial hydrocarbon in place and field development planning. The uncertainty in the present fluid type and fluid levels may have a significant impact on the reserves estimation and well completion strategies. Wireline Formation Testing is widely used to discover fluid contacts (or its generic term, Free Fluid Levels). Precise analysis of pressure data obtained from these tests is crucial in defining the type of fluid and fluid contacts. Although the traditional method of P-D Plot to determine a Free Fluid Level (FFL) is easy to implement, however it has the disadvantage of lack of information on uncertainty of the analysis. It is often difficult to identify and remove noisy data which may result in inaccurate estimation of contacts. A method has been mentioned in the literature by which Fluid Level is discovered using formation pressure data that are projected to a datum depth. With this method, it is very simple to find noisy data points which contribute to uncertainty in the FFL estimates. Another benefit of applying such method is to authenticate compositional grading presence in the reservoir. Also it can discriminate layers with different pressure behaviors in a multilayered reservoir. In this paper, several wireline formation testing data such as data from MDT and RFT tools -in different fields in Middle East-have been analyzed by previously mentioned method. A good agreement was observed between the results of this method and other data like petrophysical interpretation, geological evidences, DST results and finally PVT analysis. Also a correlation has been developed to confirm existence of compositional grading and a strategy has been proposed to calculate the rate of density change with depth in those reservoirs where variation of density is not extremely nonlinear.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.