A novel framework for reliability assessment of payload fairing separation considering multi-source uncertainties and multiple failure modes

Payload fairing separation is a critical process for various aerospace structures. To further guarantee the safety of separation, multi-source uncertainties in the processes of manufacturing, fabrication and assembly need to be considered in the stage of structural design. Reliability assessment is a powerful tool to deal with multi-source uncertainties, however, the high computational cost of structural analyses is the main challenge of the numerical simulation of payload fairing separation. In this paper, a novel framework for reliability assessment of payload fairing separation is proposed. In general, since not all potential failure modes will be happened for a certain design, sampling method is utilized to identify the active failure mode firstly. Then, an efficient global sensitivity analysis method is used for the dimension reduction to simply the high dimensional problem. And then, the MPP-based simplified bivariate dimension reduction method (MPP-based SBDRM) is proposed to improve the accuracy of MPP-based DRM for calculating the failure probability. In the proposed method, the augmented step size adjustment (ASSA) method is employed to ensure the robustness and efficiency of the most probable point (MPP) searching process. To further improve the efficiency, an adaptive surrogate model is constructed to replace the time-consuming finite element analysis (FEA). Two mathematical benchmarks are used to validate the performance of the proposed method. Finally, a typical practical payload fairing demonstrates that the proposed framework is able to assess the reliability of fairing separation in an efficient and accurate manner.