Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling

To improve the computational efficiency and accuracy of reliability-based fatigue life prediction for complex structure, a time-varying particle swarm optimization- (PSO-) based general regression neural network (GRNN) surrogate model (called as TV/PSO-GRNN) is developed. By integrating the proposed...

Full description

Bibliographic Details
Main Authors: Lu-Kai Song, Guang-Chen Bai, Cheng-Wei Fei, Jie Wen
Format: Article
Language:English
Published: Hindawi Limited 2018-01-01
Series:Advances in Materials Science and Engineering
Online Access:http://dx.doi.org/10.1155/2018/3469465
id doaj-985a2f09775740d29c47e060a97f54dd
record_format Article
spelling doaj-985a2f09775740d29c47e060a97f54dd2020-11-24T21:15:36ZengHindawi LimitedAdvances in Materials Science and Engineering1687-84341687-84422018-01-01201810.1155/2018/34694653469465Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate ModelingLu-Kai Song0Guang-Chen Bai1Cheng-Wei Fei2Jie Wen3School of Energy and Power Engineering, Beihang University, Beijing 100191, ChinaSchool of Energy and Power Engineering, Beihang University, Beijing 100191, ChinaSchool of Energy and Power Engineering, Beihang University, Beijing 100191, ChinaSchool of Energy and Power Engineering, Beihang University, Beijing 100191, ChinaTo improve the computational efficiency and accuracy of reliability-based fatigue life prediction for complex structure, a time-varying particle swarm optimization- (PSO-) based general regression neural network (GRNN) surrogate model (called as TV/PSO-GRNN) is developed. By integrating the proposed space-filling Latin hypercube sampling technique and PSO-GRNN regression function, the mathematical model of TV/PSO-GRNN is studied. The reliability-based fatigue life prediction framework is illustrated in respect of the TV/PSO-GRNN surrogate model. Moreover, the reliability-based fatigue life prediction of an aircraft turbine blisk under multiphysics interaction is performed to validate the TV/PSO-GRNN model. We obtain the distributional characteristics, reliability degree, and sensitivity degree of fatigue failure cycle, which are useful for the turbine blisk design. By comparing the direct simulation (FE/FV model), RSM, GRNN, PSO-GRNN, and TV/PSO-GRNN, we observe that the TV/PSO-GRNN surrogate model is promising to perform the reliability-based fatigue life prediction of the turbine blisk and enhance the computational efficiency while ensuring an acceptable computational accuracy. The efforts of this study offer a useful insight for the reliability-based design optimization of complex structure.http://dx.doi.org/10.1155/2018/3469465
collection DOAJ
language English
format Article
sources DOAJ
author Lu-Kai Song
Guang-Chen Bai
Cheng-Wei Fei
Jie Wen
spellingShingle Lu-Kai Song
Guang-Chen Bai
Cheng-Wei Fei
Jie Wen
Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling
Advances in Materials Science and Engineering
author_facet Lu-Kai Song
Guang-Chen Bai
Cheng-Wei Fei
Jie Wen
author_sort Lu-Kai Song
title Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling
title_short Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling
title_full Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling
title_fullStr Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling
title_full_unstemmed Reliability-Based Fatigue Life Prediction for Complex Structure with Time-Varying Surrogate Modeling
title_sort reliability-based fatigue life prediction for complex structure with time-varying surrogate modeling
publisher Hindawi Limited
series Advances in Materials Science and Engineering
issn 1687-8434
1687-8442
publishDate 2018-01-01
description To improve the computational efficiency and accuracy of reliability-based fatigue life prediction for complex structure, a time-varying particle swarm optimization- (PSO-) based general regression neural network (GRNN) surrogate model (called as TV/PSO-GRNN) is developed. By integrating the proposed space-filling Latin hypercube sampling technique and PSO-GRNN regression function, the mathematical model of TV/PSO-GRNN is studied. The reliability-based fatigue life prediction framework is illustrated in respect of the TV/PSO-GRNN surrogate model. Moreover, the reliability-based fatigue life prediction of an aircraft turbine blisk under multiphysics interaction is performed to validate the TV/PSO-GRNN model. We obtain the distributional characteristics, reliability degree, and sensitivity degree of fatigue failure cycle, which are useful for the turbine blisk design. By comparing the direct simulation (FE/FV model), RSM, GRNN, PSO-GRNN, and TV/PSO-GRNN, we observe that the TV/PSO-GRNN surrogate model is promising to perform the reliability-based fatigue life prediction of the turbine blisk and enhance the computational efficiency while ensuring an acceptable computational accuracy. The efforts of this study offer a useful insight for the reliability-based design optimization of complex structure.
url http://dx.doi.org/10.1155/2018/3469465
work_keys_str_mv AT lukaisong reliabilitybasedfatiguelifepredictionforcomplexstructurewithtimevaryingsurrogatemodeling
AT guangchenbai reliabilitybasedfatiguelifepredictionforcomplexstructurewithtimevaryingsurrogatemodeling
AT chengweifei reliabilitybasedfatiguelifepredictionforcomplexstructurewithtimevaryingsurrogatemodeling
AT jiewen reliabilitybasedfatiguelifepredictionforcomplexstructurewithtimevaryingsurrogatemodeling
_version_ 1716744656733077504