Abstract: For multi-objective optimization problems, in the previous optimization methods, human participation will eventually lead to a certain error in the optimal solution. Among the various methods for dealing with multi-objective optimization problems, the method of linearly weighting multi-objectives into single-objectives is more commonly used. In the process of linear weighting weight selection, there are more parts of human involvement and strong intervention. The optimization result has a certain error influence. In order to reduce human participation in the process and reduce errors, the linear weighting process is improved, and the simplex method is integrated into the multi-objective optimization process, and a multi-objective optimization compound algorithm based on the simplex method is proposed. A composite algorithm based on the simplex method is proposed. The simplex initial point and weight are selected by algorithm, instead of manual selection, so as to reduce the influence of subjective judgment on the optimal solution, and the objective function is processed by algorithm to reduce errors. Numerical examples verify the effectiveness of the algorithm.