In order to solve the problem that the linear function can not solve the variation, uncertainty, and strong nonlinearity of component parameters in initiation process of initiating explosive device, a new identification algorithm for initiation process of initiating explosive device is designed by combining Volterra series model with gene expression programming. Volterra series can accurately reflect the characteristics of non-linear system to describe the initiation process of initiating explosive devices. GEP algorithm overcomes the shortcomings of traditional identification methods and identifies the correct model. The simulation results show that the method can accurately and quickly identify initiating process of initiating explosive device.