Topology optimization problem, which involves many design variables, is commonly solved by finite element method, a method must recalculate structure-stiffness matrix each time of analysis. OC method is a good way to solve topology optimization problem, nevertheless, it can not solve multiobjective topology optimization problems. This paper introduces an effective solution to Multi-objective topology optimization problems by using Neural Network algorithms to improve the traditional OC method. Specifically, in each iteration, calculate the new neural network link weight vector by using the previous link weight vector in the last iteration and the compliance vector in the last time of optimization, then work out the impact factor of each optimization objective on the overall objective of the optimization in order to determine the optimal direction of each design variable.