Abstract:

In order to improve the performance of the singleaxis rotation inertial navigation system, a least squares support vector machine (LSSVM) model optimized by the chaos particle swarm optimization (CPSO) to identify the axial drift of 〖JP2〗ring laser gyroscope （RLG） is proposed. Latitude and temperature variation during the identification stage are adopted as inputs of LSSVM. The CPSO is used to optimize the parameters of the LSSVM. 〖JP〗The proposed CPSO-LSSVM can reach an identification accuracy of 0.000 2 （°）/h for  Zaxis RLG drift and radial position error of the system is less than 1 nm/72 h. The navigational results show that the proposed method is an effective approach for LSSVM parameters and the identification model has a better identification precision. The proposed method can be widely used in engineering practice.