Abstract: Intelligent air combat is a hot research topic in military aviation field, and missile hit prediction is an important part of intelligent air combat. Aiming at the shortcomings such as: the research on missile hit prediction at home and abroad is not enough, algorithm optimization ability is not strong and the model prediction accuracy is not high, a model of missile hit prediction based on adaptive mutation chaos particle swarm optimization (AMCPSO) and support vector machine (SVM) is proposed. Firstly, feature extraction of air combat data is carried out to build sample library for model training; then, the improved AMCPSO algorithm is used to optimize the penalty factor C and the kernel function parameter g in SVM, and the optimized model is used to predict the samples; finally, a comparison test is made with the classical PSO algorithm、the BP neural network method and the method of lattice. The results show that the global optimization ability and local optimization ability of the proposed algorithm is improved, and the prediction accuracy of the proposed model is higher, which can provide a reference for missile hit prediction research.