... algorithm pvt property simulation annealing cross validation plot pvt correlation prediction crude oil oil formation volume factor regression correlation self organizing map equation Introduction Proper evaluation of physical properties of hydrocarbon mixture based on pressure-volume...

..., the proposed model can be integrated into simulators and it can also be applied towards predicating other oil and gas properties, in the gas-liquid two-phase flow pattern identification, and in predicting rock properties. As an interpretable approach in predicting the PVT properties of crude oils, the proposed...

... improve the ability to correct PVT data on contaminated samples to obtain representative PVT properties. In order to test the experimental test method, base oil from an OBM was used to contaminate a gas condensate PVT sample with Condensate Gas Ratio (CGR) of 25 stb/MMscf. The data obtained from results...

... with the laboratory-measured PVT (pressure/volume/temperature) properties for more than 1,000 fluids. The GOR, formation volume factor (FVF), and density predictions are in good agreement with the laboratory measurements. The established EOS model is then able to predict other PVT properties, and the results...

..., highlighting limitations of neural networks, and illustrating how the proposed approach can alleviate many such limitations. The technique is demonstrated by developing two models for predicting oil Pressure-Volume-Temperature (PVT) properties. Limitations of Neural Networks Experience with neural...

.... The proposed RBFNM is tested using PVT properties of other samples that has not been used during the training process. Accuracy of the proposed network model to predict PVT properties crude oils and gas systems is compared to the accuracy of numerous published PVT correlations. The physical behavior...

... Abstract This study presents a universal neural network based models for the prediction of PVT properties of crude oil samples obtained from all over the world. The data, on which the network was trained, contains 5200 experimentally obtained PVT data sets of different crude oil and gas...