The optimal design of a divided wall distillation column (DWC) involves a number of variables and is a multivariable nonlinear problem. Various process parameters such as reflux rate, liquid split, and vapor split affect the product quality and energy efficiency of a DWC. Response surface methodology (RSM) based on Box-Behnken surface statistical design (BBD) was used in this article to study the process parameter optimization. A commercial process simulation software was used for rigorous simulation using several multicomponent mixtures. It was found that the number of simulation runs reduced significantly for the optimization of a DWC using BBD. The optimization results of RSM take care of interactions between process variables, and the predictions agreed well with the rigorous simulation results. [Supplementary materials are available for this article. Go to the publisher's online edition of Chemical Engineering Communications for the following free supplemental resources: 17 data tables.]