Multivariate optimization in the biosynthesis of a triethanolamine (TEA)-based esterquat cationic surfactant using an artificial neural network

Molecules. 2011 Jun 29;16(7):5538-49. doi: 10.3390/molecules16075538.

Abstract

An Artificial Neural Network (ANN) based on the Quick Propagation (QP) algorithm was used in conjunction with an experimental design to optimize the lipase-catalyzed reaction conditions for the preparation of a triethanolamine (TEA)-based esterquat cationic surfactant. Using the best performing ANN, the optimum conditions predicted were an enzyme amount of 4.77 w/w%, reaction time of 24 h, reaction temperature of 61.9 °C, substrate (oleic acid: triethanolamine) molar ratio of 1:1 mole and agitation speed of 480 r.p.m. The relative deviation percentage under these conditions was less than 4%. The optimized method was successfully applied to the synthesis of the TEA-based esterquat cationic surfactant at a 2,000 mL scale. This method represents a more flexible and convenient means for optimizing enzymatic reaction using ANN than has been previously reported by conventional methods.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Ethanolamines / chemistry*
  • Multivariate Analysis*
  • Neural Networks, Computer*
  • Surface-Active Agents / chemical synthesis*

Substances

  • Ethanolamines
  • Surface-Active Agents
  • triethanolamine