Abstract: The current situation of China’s railway network is that existing railway lines and high-speed railway lines crisscross. The existing rescue equipment bases can better cover the existing railway lines. In order to further improve the coverage of railway rescue equipment base to high-speed railway network, this paper proposed to add new type high-speed railway rescue cranes and diesel locomotives in the existing railway rescue equipment base, built a mixed level railway rescue equipment network optimization model including hub rescue equipment base and fast rescue equipment base, and established a multi-objective optimization model with the largest coverage of accident risk points and the smallest average rescue response time, and used Ant colony algorithm to solve the problem. Under the condition of not changing the number of rescue equipment bases, the average rescue response time of the rescue equipment base network given by the model is significantly improved; in the case of changing the number of rescue equipment bases, the model can significantly reduce the number of rescue equipment bases and reduce the cost on the premise of ensuring the coverage and response time.