The aim of the research is to present methodology of dynamical reliability analysis of flexible mechanism kinematical parameters. A general model of kinematical parameters dynamical reliability was introduced for flexible mechanism analysis. Stochastic variables included driven forces

torques

frictions and damps were considered basically. In the first

Monte Carlo （MC） method was applied to generate stochastic variables and dynamical responds of mechanism. Secondly

the application of Artificial Neural Network （ANN） was motivated by the approximate concepts inherent in reliability analysis and time consuming repeated analyses required for MC. Finally

statistical distribution of kinematical parameters was yielded from the outputs of ANN. As an example

one flexible space station expand mechanism model was employed to test this method. The results proved that this method could be used to account for the complicated dynamical reliability analysis at a reasonable computational cost.