Probabilistic Fatigue Assessment for Complex Engineering Structures with Time-dependent Surrogate Modelling | Chapter 4 | Recent Developments in Engineering Research Vol. 12

 Thousands of simulations with nonlinear characteristics and hyperparameters are required for the dynamic probabilistic analysis of complex engineering structures, indicating that unacceptable computational loads exist. In this case, the efficiency and accuracy of complex structural dynamic probabilistic analysis are directly determined by the model's performance. We present a time-dependent particle swarm optimization (PSO)-based general regression neural network (GRNN) surrogate model (TD/PSO-GRNN) that integrates the proposed space-filling Latin hypercube to improve the computational efficiency and accuracy of probabilistic fatigue life prediction for complex structures. PSO-GRNN regression function and sampling technique The related theory and method of the TD/PSOGRNN model are first thoroughly investigated. The probabilistic fatigue life prediction framework is then demonstrated using the TD/PSO-GRNN surrogate model. Furthermore, the TD/PSO-GRNN model is validated by performing a probabilistic fatigue life prediction of an aircraft turbine blisk under multi-physics interaction. We obtain the fatigue failure cycle's distributional characteristics, reliability degree, and sensitivity degree, which are useful for turbine blisk design. By contrasting the direct and The TD/PSO-GRNN surrogate model is promising for performing the probabilistic fatigue life prediction of the turbine blisk with high computational efficiency and acceptable computational accuracy, as demonstrated by simulation (FE/FV model), RSM, GRNN, PSO-GRNN, and TD/PSO-GRNN. This study's efforts provide useful insight for the probabilistic design optimization of complex structures, as well as enrich mechanical reliability theory and methods.

Author(s) Details

Chengwei Fei
Department of Aeronautics and Astronautics, Fudan University, Shanghai 200433, P.R. China.

Lei Han
Department of Aeronautics and Astronautics, Fudan University, Shanghai 200433, P.R. China.

Cheng Lu
Department of Aeronautics and Astronautics, Fudan University, Shanghai 200433, P.R. China.

Yan Hu
Commercial Aircraft Engine Co., Ltd, AECC, Shanghai 200241, P.R. China.

Bo Huang
Commercial Aircraft Engine Co., Ltd, AECC, Shanghai 200241, P.R. China.

Liu Yuan
Commercial Aircraft Engine Co., Ltd, AECC, Shanghai 200241, P.R. China.

View Book :-  https://stm.bookpi.org/RDER-V12/article/view/1481