The reliability of acquisition terminal software is an essential criterion for the life span of software system.In order to solve problems such as: high difficulty in parameter optimization during software system reliability evaluation using multi neural network (NN) method and SVP method and low accuracy of prediction using predictive model for software system, method of building model based on Simulated Annealing Genetic Fusion Algorithm (SAGFA) BP NN is raised in this article.Firstly, PCA is used to reduce the dimension of the experimental data, this is to eliminate the redundancy and interference sample that will affect the accuracy of model.Then, SAGFA is developed based on the optimization of SA and GA method. Furthermore, by utilizing the global optimization property of SAGFA method and the non-linear mapping property of BP NN, we are able to produce SAGFA-BPNN and the method of building this model. This will raise the training speed, improve the ability of global optimization and increase the accuracy of prediction. This method is then applied to predict the reliability of acquisition terminal software and the prediction result shows that the method can effectively raise the accuracy of model.