Maintenance resources are important part of the maintenance support system. The whole efficiency of weapon system is directly affected by the allocation of maintenance resources. Joint support for weapon system of multi-kinds of equipments is the main fashion of maintenance support in the future. However, there is a lack of the efficiency tools and methods for predication and optimization of weapon system maintenance resources presently. For the prediction requirement of maintenance resources of weapon system, the primary infection factors for the requirement of maintenance resources were analyzed. According to the different characteristics of maintenance resources and the analysis for the traditional classification methods, a kind of classification for weapon system’s maintenance resources was given. A prediction flow for the maintenance resources requirement was designed. Four kinds of models for predicting the maintenance resources requirement in a weapon system were designed and described in detail. In this paper, approaches of the optimal selection from the simulation schemes and reverse simulation for the resources allocation optimization were analyzed; some optimization models for maintenance resources such as spare parts and personnel were constructed. Further more, an optimization and decision-making system was not only designed but also developed. At last, an example was presented, which proved the prediction and optimization methods were applicability and feasibility, the decision-making system for the optimization of maintenance resources was a supportable and efficient tool.