An optimal design for an engineering optimization problem involves various decision variables and constraints. In engineering applications, objectives under consideration conflict with each other, and optimizing a meticulous solution with respect to a single objective can result in objectionable results with respect to the other objectives. A practical solution to a multi-objective problem is to examine a set of solutions, each of which satisfies the objectives at a satisfactory level without being conquered by any other solution. In this paper, a new population based evolutionary algorithm used to optimize the gear drive with combined objective function which maximises the power, efficiency and minimises the overall weight, centre distance has been considered. The performance of the proposed algorithms is validated and results are compared.