Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven
With the development of wind turbine，high-speed railway，aero-engine and other large equipment towards the direction of high reliability，long life and intelligence，it has put forward higher requirements for the life of basic components such as gears and bearings. It is urgent to use more scientific a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2021-10-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2021.10.001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841547323657682944 |
|---|---|
| author | Xiuhua Zhang Huaiju Liu Caichao Zhu Peitang Wei Shaojie Wu |
| author_facet | Xiuhua Zhang Huaiju Liu Caichao Zhu Peitang Wei Shaojie Wu |
| author_sort | Xiuhua Zhang |
| collection | DOAJ |
| description | With the development of wind turbine，high-speed railway，aero-engine and other large equipment towards the direction of high reliability，long life and intelligence，it has put forward higher requirements for the life of basic components such as gears and bearings. It is urgent to use more scientific and efficient fatigue life prediction method. The life prediction methods of mechanical components can be divided into physical failure model，data-driven model and fusion model（physical failure and data-driven model fusion） three types. With the development of components life prediction research towards high precision and high efficiency，physical model is difficult to meet modern needs due to its complexity，time-consuming and non-universal disadvantages. With the rapid development of machine learning，deep learning and other technologies，data-driven model has become a hot topic in the research of components fatigue life prediction of due to the advantages of no need to know detailed failure mechanism and accurate prediction results. In view of this，the fatigue life prediction method of components based on data-driven is described. The application of these methods in the life prediction of components is introduced，including neural network，support vector machine，random forest and deep learning，and the characteristics of each method are summarized，and the developing trend of the life prediction method of components based on data-driven is discussed. And a case study of gear contact fatigue life prediction based on GA-BP neural network is presented. |
| format | Article |
| id | doaj-art-3fff3a6e702f4c2ba49a86aeac61fd9b |
| institution | Kabale University |
| issn | 1004-2539 |
| language | zho |
| publishDate | 2021-10-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj-art-3fff3a6e702f4c2ba49a86aeac61fd9b2025-01-10T14:47:51ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392021-10-014511419864812Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-drivenXiuhua ZhangHuaiju LiuCaichao ZhuPeitang WeiShaojie WuWith the development of wind turbine，high-speed railway，aero-engine and other large equipment towards the direction of high reliability，long life and intelligence，it has put forward higher requirements for the life of basic components such as gears and bearings. It is urgent to use more scientific and efficient fatigue life prediction method. The life prediction methods of mechanical components can be divided into physical failure model，data-driven model and fusion model（physical failure and data-driven model fusion） three types. With the development of components life prediction research towards high precision and high efficiency，physical model is difficult to meet modern needs due to its complexity，time-consuming and non-universal disadvantages. With the rapid development of machine learning，deep learning and other technologies，data-driven model has become a hot topic in the research of components fatigue life prediction of due to the advantages of no need to know detailed failure mechanism and accurate prediction results. In view of this，the fatigue life prediction method of components based on data-driven is described. The application of these methods in the life prediction of components is introduced，including neural network，support vector machine，random forest and deep learning，and the characteristics of each method are summarized，and the developing trend of the life prediction method of components based on data-driven is discussed. And a case study of gear contact fatigue life prediction based on GA-BP neural network is presented.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2021.10.001Data-drivenComponentsLife predictionMachine learningPrediction accuracy |
| spellingShingle | Xiuhua Zhang Huaiju Liu Caichao Zhu Peitang Wei Shaojie Wu Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven Jixie chuandong Data-driven Components Life prediction Machine learning Prediction accuracy |
| title | Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven |
| title_full | Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven |
| title_fullStr | Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven |
| title_full_unstemmed | Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven |
| title_short | Current Situation and Developing Trend of Fatigue Life Prediction of Components based on Data-driven |
| title_sort | current situation and developing trend of fatigue life prediction of components based on data driven |
| topic | Data-driven Components Life prediction Machine learning Prediction accuracy |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2021.10.001 |
| work_keys_str_mv | AT xiuhuazhang currentsituationanddevelopingtrendoffatiguelifepredictionofcomponentsbasedondatadriven AT huaijuliu currentsituationanddevelopingtrendoffatiguelifepredictionofcomponentsbasedondatadriven AT caichaozhu currentsituationanddevelopingtrendoffatiguelifepredictionofcomponentsbasedondatadriven AT peitangwei currentsituationanddevelopingtrendoffatiguelifepredictionofcomponentsbasedondatadriven AT shaojiewu currentsituationanddevelopingtrendoffatiguelifepredictionofcomponentsbasedondatadriven |