This study proposed a Kriging surrogate model incorporating active learning to overcome the high computational costs associated with conducting reliability and sensitivity analyses of industrial liquid storage tank structures. In the proposed method, the Kriging surrogate model efficiently captures the functional relationships between basic variables and structural responses. Two learning functions, i.e., the U learning function and the EFF learning function, are adopted to screen the training sample pool to identify and iteratively update the optimal next training sample point in the model. This strategy significantly reduces the number of limit state functions and finite element analysis calculations required, considerably decreasing the computational cost of analysis. Results from the liquid storage tank case study demonstrate that the adaptive learning Kriging method can achieve failure probability estimation at the order of 10−5 with only approximately 100 limit state function (LSF) evaluations. Additionally, it is found that the pressure exerted by the tank contents has the most significant impact on the tank’s structural reliabilityreliability, followed by tank thickness and then tank radius.
Xu et al. (Wed,) studied this question.