Modelling asphaltene precipitation titration data: A committee of machines and a group method of data handling

Abstract

AbstractAsphaltene precipitation causes different problems in the oil industry. In this study, a large data bank was used to model asphaltene precipitation titration data as a function of temperature, type of solvent, and solvent to crude oil dilution ratio. Three multilayer perceptron (MLP) neural networks and three radial basis function (RBF) neural networks were developed to estimate asphaltene precipitation data. The MLP models were optimized with scaled conjugate gradient (SCG), Levenberg‐Marquardt (LM), and Bayesian regularization (BR) algorithms and the RBF models were optimized with the particle swarm optimization (PSO) algorithm, imperialist competitive algorithm (ICA), and genetic algorithm (GA). All of the proposed models show an acceptable degree of accuracy and have an average absolute percent relative error (AAPRE) less than 4 %. Afterwards, three of the best models including MLP‐LM, MLP‐BR, and RBF‐GA were combined and a committee machine intelligent system (CMIS) was designed, which offers a higher accuracy compared to the other intelligent models. Aside from these intelligent models, the group method of data handling (GMDH) was used to develop an explicit and simple expression for estimating asphaltene precipitation. The proposed CMIS and GMDH models were compared to models developed based on scaling theory and the results show that the proposed models in this study outperform pre‐existing models. The validity and accuracy of the CMIS and GMDH models were proven by statistical and graphical techniques. Finally, a sensitivity analysis suggested that the solvent to crude oil dilution ratio has the largest effect on asphaltene precipitation.