Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines
Developments in engineering techniques have concentrated on how to build better solutions for engineering structures in order to main the integrity and to reduce the costs in operations. Since the last two decades, advances in computational power have allowed machine learning algorithms to be appl...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hitit University
2020-09-01
|
| Series: | Hittite Journal of Science and Engineering |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/1506500 |
| _version_ | 1797662691590930432 |
|---|---|
| author | Mahmut Pekedis |
| author_facet | Mahmut Pekedis |
| author_sort | Mahmut Pekedis |
| collection | DOAJ |
| description | Developments in engineering techniques have concentrated on how to build better solutions for engineering structures in order to main the integrity and to reduce the costs in operations. Since the last two decades, advances in computational power have allowed machine learning algorithms to be applied as a powerful tool in anomaly detection problems, classification as well as in regression analysis. The objective of this study is to detect the damage using the vector auto regression model VAR coupled with support vector machines SVM . A base excited three storey manufactured from an aluminium is investigated in a lab medium for various structural states. Accelerometers are fastened to the each corner of structure's floor to collect time series data. Damage simulation scenarios in structure are performed by releasing the bolt load which cause the nonlinear effects. Once the sensors' measurements are collected for each state and organized to represent the appropriate scenario's label, they are processed in VAR model to obtain feature vectors such as residuals and VAR parameters. Then, SVM with optimal kernels are implemented on those features to classify and locate the damage. The results demonstrate that the VAR residuals shows a significant performance over VAR parameters once they are used as features in SVM technique. Moreover, it is also found that detection performance rises as the number of damage increases. |
| first_indexed | 2024-03-11T19:03:53Z |
| format | Article |
| id | doaj.art-ee2aa70f88474b7ba2a1960fc0cbe1af |
| institution | Directory Open Access Journal |
| issn | 2148-4171 |
| language | English |
| last_indexed | 2024-03-11T19:03:53Z |
| publishDate | 2020-09-01 |
| publisher | Hitit University |
| record_format | Article |
| series | Hittite Journal of Science and Engineering |
| spelling | doaj.art-ee2aa70f88474b7ba2a1960fc0cbe1af2023-10-10T11:17:29ZengHitit UniversityHittite Journal of Science and Engineering2148-41712020-09-017316917910.17350/HJSE19030000186150Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector MachinesMahmut Pekedis0Ege University, Department of Mechanical Engineering, Izmir, TurkeyDevelopments in engineering techniques have concentrated on how to build better solutions for engineering structures in order to main the integrity and to reduce the costs in operations. Since the last two decades, advances in computational power have allowed machine learning algorithms to be applied as a powerful tool in anomaly detection problems, classification as well as in regression analysis. The objective of this study is to detect the damage using the vector auto regression model VAR coupled with support vector machines SVM . A base excited three storey manufactured from an aluminium is investigated in a lab medium for various structural states. Accelerometers are fastened to the each corner of structure's floor to collect time series data. Damage simulation scenarios in structure are performed by releasing the bolt load which cause the nonlinear effects. Once the sensors' measurements are collected for each state and organized to represent the appropriate scenario's label, they are processed in VAR model to obtain feature vectors such as residuals and VAR parameters. Then, SVM with optimal kernels are implemented on those features to classify and locate the damage. The results demonstrate that the VAR residuals shows a significant performance over VAR parameters once they are used as features in SVM technique. Moreover, it is also found that detection performance rises as the number of damage increases.https://dergipark.org.tr/tr/download/article-file/1506500structural health monitoring pattern recognition machine learning damage diagnosis vector autoregressive - support vector machines |
| spellingShingle | Mahmut Pekedis Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines Hittite Journal of Science and Engineering structural health monitoring pattern recognition machine learning damage diagnosis vector autoregressive - support vector machines |
| title | Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines |
| title_full | Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines |
| title_fullStr | Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines |
| title_full_unstemmed | Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines |
| title_short | Damage Diagnosis of Bolt Loosening via Vector Autoregressive - Support Vector Machines |
| title_sort | damage diagnosis of bolt loosening via vector autoregressive support vector machines |
| topic | structural health monitoring pattern recognition machine learning damage diagnosis vector autoregressive - support vector machines |
| url | https://dergipark.org.tr/tr/download/article-file/1506500 |
| work_keys_str_mv | AT mahmutpekedis damagediagnosisofboltlooseningviavectorautoregressivesupportvectormachines |