Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation
The durability and reliability of structural components are usually assessed based on fatigue loading under operating conditions. To obtain accurate fatigue loading in the form of continuous strain histories, a novel approach is proposed based on the combination of a recurrent neural network and sim...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2019/7289314 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563843077767168 |
|---|---|
| author | Huan Luo Miaohua Huang Wei Xiong |
| author_facet | Huan Luo Miaohua Huang Wei Xiong |
| author_sort | Huan Luo |
| collection | DOAJ |
| description | The durability and reliability of structural components are usually assessed based on fatigue loading under operating conditions. To obtain accurate fatigue loading in the form of continuous strain histories, a novel approach is proposed based on the combination of a recurrent neural network and simplified semianalytical method. The recurrent neural network named nonlinear autoregressive model with exogenous inputs (NLARX) is applied to determine the relationship between external loads and corresponding fatigue loading. Owing to the generalization ability of NLARX, semianalytical method, which is used to obtain sample database for NLARX model training and testing, is implemented with simplified multibody model. Durability tests of a torsion beam rear suspension are introduced to demonstrate the effectiveness of the proposed approach. The experimental results show that our proposed approach is able to achieve better estimation results, when compared with the conventional semianalytical method. |
| format | Article |
| id | doaj-art-547b4996982a4ac598a69eeb36290d9e |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-547b4996982a4ac598a69eeb36290d9e2025-02-03T01:12:25ZengWileyShock and Vibration1070-96221875-92032019-01-01201910.1155/2019/72893147289314Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories EstimationHuan Luo0Miaohua Huang1Wei Xiong2GAC Automotive Research & Development Center, Guangzhou 511434, ChinaHubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, ChinaGAC Automotive Research & Development Center, Guangzhou 511434, ChinaThe durability and reliability of structural components are usually assessed based on fatigue loading under operating conditions. To obtain accurate fatigue loading in the form of continuous strain histories, a novel approach is proposed based on the combination of a recurrent neural network and simplified semianalytical method. The recurrent neural network named nonlinear autoregressive model with exogenous inputs (NLARX) is applied to determine the relationship between external loads and corresponding fatigue loading. Owing to the generalization ability of NLARX, semianalytical method, which is used to obtain sample database for NLARX model training and testing, is implemented with simplified multibody model. Durability tests of a torsion beam rear suspension are introduced to demonstrate the effectiveness of the proposed approach. The experimental results show that our proposed approach is able to achieve better estimation results, when compared with the conventional semianalytical method.http://dx.doi.org/10.1155/2019/7289314 |
| spellingShingle | Huan Luo Miaohua Huang Wei Xiong Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation Shock and Vibration |
| title | Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation |
| title_full | Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation |
| title_fullStr | Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation |
| title_full_unstemmed | Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation |
| title_short | Application of a Recurrent Neural Network and Simplified Semianalytical Method for Continuous Strain Histories Estimation |
| title_sort | application of a recurrent neural network and simplified semianalytical method for continuous strain histories estimation |
| url | http://dx.doi.org/10.1155/2019/7289314 |
| work_keys_str_mv | AT huanluo applicationofarecurrentneuralnetworkandsimplifiedsemianalyticalmethodforcontinuousstrainhistoriesestimation AT miaohuahuang applicationofarecurrentneuralnetworkandsimplifiedsemianalyticalmethodforcontinuousstrainhistoriesestimation AT weixiong applicationofarecurrentneuralnetworkandsimplifiedsemianalyticalmethodforcontinuousstrainhistoriesestimation |