The optimization on demand of initial spare part in equipment is a complicated nonlinear mixed integral programming problem, and it is a key factor affecting the cost and efficiency of weapon system. In order to reduce the cost and improve the reliability of equipment, a new particle warm optimization (PSO) method, which can be used to find optimal regions of complex search spaces through the interaction of individuals in a population of particles, is constructed to solve this optimization problem and the best scheme is achieved. The test shows that this optimization method is scientific and valid for this problem.