The gear box of high-speed trains is the key to transfer the traction torque. It is an important bridge connecting the motor with wheel and rail, and its dynamic characteristics directly affect the reliability and safety of high-speed trains. Under the complicated excitation of the trains, the tooth surface will inevitably produce small cracks, and then form the pitting of the tooth surface. It is of great significance to accurately identify the pitting degree of tooth surface to prevent the occurrence of major safety accidents. In order to solve the problem of pitting state identification, a dynamic model of helical gear transmission system considering pitting tooth surface is proposed in this paper. The calculation model of the time-varying meshing stiffness of helical gear was established by slice method, and the shape of pitting pit was simulated by rectangular geometry. Then, this paper uses MATLAB to simulate the dynamic model under different pitting degree. The simulation results show that the greater the pitting degree, the more obvious the effect on meshing stiffness. Under the pitting condition, the time domain response will produce periodic abrupt change, and the fault frequency band will appear in the frequency domain response. The research can provide a theoretical basis for the identification and detection of pitting corrosion under the condition of tooth surface damage.