International audienceScale deposition can damage equipment in the oil & gas production industry. Hence, the reliable and accurate prediction of the scale deposition rate is critical for production availability. In this study, we consider the problem of predicting the scale deposition rate, providing an indication of the associated prediction uncertainty. We tackle the problem using an empirical modeling approach, based on experimental data. Specifically, we implement a multi-objective genetic algorithm (namely, non-dominated sorting genetic algorithm-II (NSGA-II)) to train a neural network (NN) (i.e. to find its parameters, that is its weights and biases) to provide the prediction intervals (PIs) of the scale deposition rate. The PIs are optimized both in terms of accuracy (coverage probability) and dimension (width). We perform k-fold cross-validation to guide the choice of the NN structure (i.e. the number of hidden neurons). We use hypervolume indicator metric to evaluate the Pareto fronts in the validation step. A case study is considered, with regards to a set of experimental observations: the NSGA-II-trained neural network is shown capable of providing PIs with both high coverage and small width
A physical model for scale growth in the Dynamic Tube Blocking Test (TBT) is presented aiming at the determination of the first layer formation time and the scale growing rate. The proposed model has been applied to 38 experimental results, each one with a different water composition. The fluid compositions were selected to represent the majority of the fluids found in typical Brazilian oil wells. For the application of this model, no differential pressure was considered before pumping. Additionally, the pressure rising time was not taken into account in the calculation of the first layer formation time. The model showed excellent fitting to the experimental data, with correlation coefficients superior to 0.98 for most data. Furthermore, the results of the scale growing rate were compatible to the results from other experiments, utilizing: rotating cage; static reactors; and full scale Inflow Control Valves (ICVs). Furthermore, on a scientific perspective, the model can also be used for the development of scale growing models as a function of pressure, temperature, composition.
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.