Aiming at the problem of increasingly complex structure of airborne missile, lack of diagnostic data in the traditional expert system, low efficiency and accuracy of fault diagnosis, a method based on Belief Rule Base (BRB) is proposed to diagnose the airborne missile. Firstly, this paper describes the reasoning method of BRB based on evidence reasoning and establishes the nonlinear model between input and output. Secondly, in order to solve the problem of inaccurate initial BRB parameters in traditional expert system, the parameter optimization learning model is established combining with the fault location information. Finally, taking a kind of airborne missile refrigeration system as an example, the fault diagnosis method of the airborne missile based on belief rule base is verified. The results show that this method can not only overcome the problem of low efficiency of traditional expert system diagnosis, but also improve the diagnosis accuracy of the airborne missile by parameter training. This method can improve the fault diagnosis efficiency of airborne missile and provide reference for the maintenance and support of airborne missile.