Development and Testing of Two-Phase Relative Permeability Predictors Using Artificial Neural Networks SPE 69392
Language: Inglés Series: Silpngarmlers, N ; Publication details: Dallas, Texas Society of Petroleum Engineers 2001Online resources: Summary: Abstract Artificial neural networks (ANNs) provide a powerful toolbox to perform nonlinear, multi-dimensional interpolations. In this paper, we include a new methodology to identify some of the vague nonlinear relationships that exist between rock and fluid properties and relative permeability characteristics. More specifically, we report liquid/liquid and liquid/gas two-phase relative permeability predictors that we have developed using back-propagation networks. In this class of ANNs, information is passed from input layer to output layer, and calculated errors are propagated back to adjust the connection weights in a sequential manner to improve the predictive capabilities of the models. In the development stage, some of the relative permeability data from literature are used during the training stage while some other sets are preserved to test the prediction capabilities of the models. Various rock and fluid properties such as end-point saturations, porosity, permeability, viscosity and interfacial tension and some functional links (mathematical groups coupling various rock and fluid properties) constitute the input parameters of the models. These rock and fluid parameters together with the functional links highlight the dependency of relative permeability characteristics on such properties and functional groups. The models developed for oil/water and oil/gas systems are different in terms of their respective topologies, functional links, and the weight updating schemes. The models are found to successfully predict the field and experimental relative permeability data.| Current library | Status | Barcode | |
|---|---|---|---|
| Biblioteca virtual | Not for loan | 200002868 |
Abstract Artificial neural networks (ANNs) provide a powerful toolbox to perform nonlinear, multi-dimensional interpolations. In this paper, we include a new methodology to identify some of the vague nonlinear relationships that exist between rock and fluid properties and relative permeability characteristics. More specifically, we report liquid/liquid and liquid/gas two-phase relative permeability predictors that we have developed using back-propagation networks. In this class of ANNs, information is passed from input layer to output layer, and calculated errors are propagated back to adjust the connection weights in a sequential manner to improve the predictive capabilities of the models. In the development stage, some of the relative permeability data from literature are used during the training stage while some other sets are preserved to test the prediction capabilities of the models. Various rock and fluid properties such as end-point saturations, porosity, permeability, viscosity and interfacial tension and some functional links (mathematical groups coupling various rock and fluid properties) constitute the input parameters of the models. These rock and fluid parameters together with the functional links highlight the dependency of relative permeability characteristics on such properties and functional groups. The models developed for oil/water and oil/gas systems are different in terms of their respective topologies, functional links, and the weight updating schemes. The models are found to successfully predict the field and experimental relative permeability data.
