Comprehensive two-dimensional gas chromatography in combination with pixel-based analysis for fouling tendency prediction

- Gas condensate samples were analyzed using comprehensive GC × GC.
- A pixel-based data analysis approach was successfully applied.
- Feature selection methodologies for partial-least squares regression were compared.
- The RReliefF algorithm and F-statistics were efficient feature selection techniques.
- A methodology is presented to predict fouling tendencies.

Fouling tendencies of a series of gas condensates were evaluated using comprehensive two-dimensional gas chromatography with flame ionization detection and sulfur chemiluminescence detection. A pixel-based approach was applied in order to identify parts of the chromatograms which were associated with the reactor coil fouling. Particular emphasis is given in this work to evaluate several feature selection methodologies along with various data preprocessing procedures. It was found that both aspects were crucial for studying the fouling tendencies and, as part of the subsequent partial least squares model development, predominantly the feature selection. Based on the flame ionization detector chromatograms and using the RReliefF algorithm for feature selection, a partial least squares regression model with one latent variable resulted in a root mean square error of the cross-validation of 0.65 g deposit/6 h (17%). Based on the sulfur chemiluminescence detector chromatograms, the F-statistics feature selection generated a slightly better partial least squares regression model compared to using RReliefF, thus generating a model using one latent variable with a root mean square error of the cross-validation of 0.81 g deposit/6 h (21%). Heavy aromatic compounds and heavy sulfur containing compounds were negatively associated with the fouling rate. Both were crucial in developing a partial least squares model with good prediction power, however, worked independently as predictors.