Research on Reliability Method of Complex Mechanical Structure Based on Active Learning

In order to solve the problem of implicit function and long simulation time in reliability analysis of complex mechanical structure, the reliability calculation method based on Kriging and Monte Carlo is adopted. In order to improve the accuracy of Kriging model quickly, the sample points which minimize the value of learning function are selected and substituted into the model. A learning stopping condition is proposed, which ensures the prediction accuracy of sample point symbols and significantly reduces the number of learning times. Finally, the numerical minimization problem and the artillery coordinator are taken as examples to verify the correctness of the proposed method.