A new constrained filtering method based on Unscented Kalman Filter (UKF) and pseudo-observation called SPUKF (Sub-system Parallel Unscented Kalman Filter) was proposed for state estimation of nonlinear system with nonlinear constraints. In the proposed method, the system and constraint equations were fictitiously divided and reconstructed into two sub-systems, and then the state estimation was obtained from two concurrent filtering processes which were established on these two sub-systems alternately. Compared to sequential processing method of pseudo-measurement, SPUKF did not need to determine the processing order between measurement and constraint, but achieved better performances, so as to address the problem of deciding processing order beforehand in sequential processing method. In the simulation of pendulum motion, it is verified that SPUKF gets better estimation performance and less running time than the two forms of sequential processing method, and enhances the estimation error improvement ratio by 22 percentage points than UKF. Furthermore, it obtains comparable estimation results with batch processing way.