Monitoring industrial hydrogenation of soybean oil using self-organizing maps
DOI:
https://doi.org/10.9755/ejfa.2019.v31.i10.2019Keywords:
process control; gas chromatography; artificial neural networks.Abstract
Monitoring the hydrogenation reaction is crucial to guarantee a product with desired properties. The combination of gas chromatography (GC) with self-organizing maps (SOM) may be an alternative to extract relevant information during the hydrogenation. We analyzed two partially hydrogenated fats produced in an industrial reactor. The quantification of the fatty acids methyl esters and the iodine value (IV) calculation was performed by GC. The SOM was able to cluster the samples according to the IV and reaction time. The weight maps depicted the variation of monounsaturated fatty acids associated with the increase of 18:1 and the variation of poly-unsaturated are mainly correlated with 18:2. An increase was observed in saturated fatty acids and trans-fatty acids associated respectively with 18:0 and 18:1(trans). Besides, it was confirmed that trans-isomers are more stable than the cis-isomers. Therefore, the SOM with GC was an efficient tool for monitoring the hydrogenation process.