Prediction of Optimal Salinities for Surfactant Formulations Using a Quantitative Structure-Property Relationships Approach

Prediction of Optimal Salinities for Surfactant Formulations Using a Quantitative Structure-Property Relationships Approach

Muller, C.
Maldonado, A.G.
Varnek, A.
Creton, B.

2015

Each oil reservoir could be characterized by a set of parameters such as temperature, pressure, oil composition, and brine salinity, etc. In the context of the chemical enhanced oil recovery (EOR), the selection of high performance surfactants is a challenging and time-consuming task since this strongly depends on the reservoir's conditions. The situation becomes even more complicated if the surfactant formulation is a blend of two or more surfactants. In the present work, we report quantitative structure-property relationships (QSPR) correlating surfactants'structures and their composition in a mixture with optimal salinity (Sopt), corresponding to minimal interfacial tension in the reference brine/surfactants/n-dodecane system, at T = 313 K and P = 0.1 MPa. Particular attention was paid to selected families of surfactants: α-olefin sulfonate (AOS), internal olefin sulfonate (IOS), alkyl ether sulfate (AES), and alkyl glyceryl ether sulfonate (AGES). The models were built and validated on the database containing Sopt values for 75 surfactants' formulations. Molecular structures of amphiphilic molecules were encoded by functional group count descriptors (FGCD), ISIDA substructural molecular fragment (SMF) descriptors, and CODESSA molecular descriptors (CMD). For mixtures, descriptors were calculated as linear combinations of descriptors of individual compounds weighted by their mass fractions in mixtures. Different machine-learning methods-support vector machine (SVM), partial least-squares (PLS) regression, and random subspace (RS)-have been used for the modeling. Both global (on the entire database) and local (on individual families) models have been built. Models display reasonable accuracy (about 0.2 log Sopt units) which is comparable with the experimental error of measured Sopt. Our results show that the suggested approach can be successfully used to build predictive models for relatively small data sets of mixtures of chemical compounds. © 2015 American Chemical Society.

Life
RAPID - Risk Analysis for Products in Development
ELSS - Earth, Life and Social Sciences
Energy
Artificial intelligence
Blending
Chemical compounds
Enhanced recovery
Ethers
Learning systems
Least squares approximations
Mixtures
Oil well flooding
Olefins
Petroleum reservoir engineering
Petroleum reservoirs
Support vector machines
Alpha olefin sulfonates
Chemical enhanced oil recoveries
Internal olefin sulfonates
Machine learning methods
Molecular descriptors
Partial least-squares regression
Quantitative structure property relationships
Surfactant formulation
Surface active agents

http://resolver.tudelft.nl/uuid:7b5ccf08-2e27-4592-825e-cbc1afa53246

https://doi.org/10.1021/acs.energyfuels.5b00825

527786

0887-0624

Energy and Fuels, 29 (7), 4281-4288

article