Structural reliability analysis for rare events and its application in aerospace equipment
Please login to view abstract download link
Developing efficient, accurate, and robust structural reliability analysis methods for problems characterized by low failure probability, high computational cost, and high-dimensional inputs is crucial to ensuring the high reliability and long service life of aerospace equipment. In this work, we developed an analytical method based on the conjugate gradient algorithm and a simulation-based method with rejection control. Furthermore, by integrating machine learning algorithms and adopting strategies such as scale normalization, weight control, and approximate numerical differentiation, The accurately and efficiently intelligent structural reliability analysis is achieved. These methods were successfully applied to the reliability assessment of turbine bladed disk of aeroengine and slender pipeline of aircraft. The results demonstrate that the proposed methods can effectively address complex engineering problems.
