A system identification problem can be considered as an optimization task where the purpose is to find a model and a set of parameters that minimize the prediction error between the plant outputs and the model outputs. In some cases, the objective function is not mathematically and analytically available, like in distillation column, in addition the obtained parameters may not be globally optimal. In these situations, Genetic Algorithms are superior to gradient descent parameter learning algorithms. The idea of this paper is to identify unknown parameters of the distillation column model. The novelty and contribution of this article is in applying the genetic algorithm in identification of distillation column. Two different models are investigated and their step responses are compared to each other.