Abstract: Thermally Coupled Distillation Columns are more efficient than conventional sequences. Because of the difficulties of proper design, their applications are restricted. In this paper, a new approach using genetic algorithm and artificial neural network for the optimization of thermally coupled distillation is presented. Mathematical model constructed with artificial neural network based on the simulation results with ASPEN PLUS. The Comparison of ANN prediction results and ASPEN PLUS simulation results shows that the model can simulate thermally coupled distillation rightly. Modified genetic algorithm is used to optimize the artificial neural network model. With the proposed model and optimization algorithm, the decision variables and the target value can be solved automatically and quickly. The convergence curve proves the efficiency of the genetic algorithm. A practical example is used to demonstrate the algorithm.