No abstract

This paper proposes and implements a new approach for predicting Pressure -Volume-Temperature (PVT) properties of crude oils. Instead of the usual single or multi-data point prediction for any crude oil PVT property that is described by a curve, the approach in this study predicts such a property over a specified range of required reservoir pressures. Moreover, the shapes of the predicted curves are smooth and consistent with the experimental curves. Prediction models based on Artificial Neural Networks (ANN) and two of its advances; Support Vector Regression (SVR) and Functional Networks (FN), have been developed to execute the formulated approach. The approach has been demonstrated for viscosity and solution gas/oil ratio (GOR) curves. These two properties vary with reservoir pressures and they are often required to be estimated over a specified range of pressures. In this study, three different data sets have been used. The first Data set consists of 12 variables which are the predictors, including crude oil hydrocarbon and non-hydrocarbon compositions and some reservoir properties. The other two data sets consist of laboratory viscosity-pressure measurements and laboratory gas/oil ratio-pressure measurements for plotting the viscosity and solution GOR curves respectively. In the simulation results, SVR and FN give better performances than the conventional ANN technique. Graphical plots and two common statistical measures (root mean square error, RMSE, and absolute percent relative error, AAPRE) have been used to evaluate the performances of all the developed models. Introduction In petroleum engineering, characterization of reservoir fluids plays an important role of developing strategies for operating and managing existing reservoirs and development of new ones. These reservoir fluid properties are important in petroleum engineering computations for: simulating reservoirs, evaluating reserves, forecasting production, designing production facilities and transportation systems. Crude oil viscosity and GOR are two of these important PVT properties which are required to be calculated or estimated at different stages of crude oil exploration. These properties are traditionally determined from laboratory analyses on samples collected from the bottom of the wellbore or after recombining the liquid and vapour samples collected from the separator at the surface. To solve the problem of going through the rigorous laboratory experimentations which consume valuable production resources: time and money, equations of states (EOS) and empirically derived correlations have been used to predict these reservoir fluid properties. The two methods were used for a long period of time until Soft Computing (SC) techniques were introduced to improve the prediction performances. The mostly used SC technique in solving Petroleum Engineering is ANN. Although SC techniques have not being widely-utilised in the Petroleum Industries compared with some other fields, they have been applied successfully in some Petroleum Engineering problems with exceptional and acceptable performances. A review of applications of some of these intelligent systems and their potentials in oil and gas industry can be found in (Mohaghegh 2005). In this study, we introduce a new approach for predicting any PVT property that can be represented as a curve. All predictions have been done using ANN as well as two of its advanced algorithms: SVR and FN.

A multistage data-driven neuro-fuzzy system is considered for the multiobjective trajectory planning of Parallel Kinematic Machines (PKMs). This system is developed in two major steps. First, an offline planning based on robot kinematic and dynamic models, including actuators, is performed to generate a large dataset of trajectories, covering most of the robot workspace and minimizing time and energy, while avoiding singularities and limits on joint angles, rates, accelerations, and torques. An augmented Lagrangian technique is implemented on a decoupled form of the PKM dynamics in order to solve the resulting nonlinear constrained optimal control problem. Then, the outcomes of the offline-planning are used to build a data-driven neuro-fuzzy inference system to learn and capture the desired dynamic behavior of the PKM. Once this system is optimized, it is used to achieve near-optimal online planning with a reasonable time complexity. Simulations proving the effectiveness of this approach on a 2-degrees-of-freedom planar PKM are given and discussed.

No abstract