In distillation column control, secondary measurements such as temperatures and flows are widely used to infer product composition. This paper addressed the development of nonlinear static estimators using secondary measurements for estimating product compositions of distillation columns. An open equation-based optimization problem, which minimizes the differences between the measured outputs and the estimated outputs, has been formulated and solved by using the nonlinear program (NLP) solver, MINOS5. It is shown that the proposed nonlinear estimator is robust and more powerful than the conventional PLS (Partial-Least-Squares) estimator.