Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model
Although the use of fiber-reinforced plastic (FRP) rebars instead of mild steel can effectively avoid rebar corrosion, the bonding performance gets weakened. To accurately estimate the bond strength of FRP bars, this paper proposes a particle swarm optimization-based extreme learning machine model b...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/12/10/1654 |
| _version_ | 1797474634802659328 |
|---|---|
| author | Ran Li Lulu Liu Ming Cheng |
| author_facet | Ran Li Lulu Liu Ming Cheng |
| author_sort | Ran Li |
| collection | DOAJ |
| description | Although the use of fiber-reinforced plastic (FRP) rebars instead of mild steel can effectively avoid rebar corrosion, the bonding performance gets weakened. To accurately estimate the bond strength of FRP bars, this paper proposes a particle swarm optimization-based extreme learning machine model based on 222 samples. The model used six variables including the bar position (<i>P</i>), bar surface condition (<i>SC</i>), bar diameter (<i>D</i>), concrete compressive strength (<i>f<sub>c</sub></i>), the ratio of the bar depth to the bar diameter (<i>L</i>/<i>D</i>), and the ratio of the concrete protective layer thickness to the bar diameter (<i>C</i>/<i>D</i>) as input features, and the relative importance of the input parameters was quantified using a sensitivity analysis. The results showed that the proposed model can effectively and accurately estimate the bond strength of the FRP bar with R<sup>2</sup> = 0.945 compared with the R<sup>2</sup> = 0.926 of the original ELM model, which shows that the model can be used as an auxiliary tool for the bond performance analysis of FRP bars. The results of the sensitivity analysis indicate that the parameter <i>L</i>/<i>D</i> is of the greatest importance to the output bond strength. |
| first_indexed | 2024-03-09T20:32:56Z |
| format | Article |
| id | doaj.art-46d3f2525c82408ca829637efc425ca5 |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-09T20:32:56Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-46d3f2525c82408ca829637efc425ca52023-11-23T23:17:49ZengMDPI AGBuildings2075-53092022-10-011210165410.3390/buildings12101654Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning ModelRan Li0Lulu Liu1Ming Cheng2School of Architecture and Civil Engineering, Zhengzhou University of Industrial Technology, Zhengzhou 451100, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaChina Construction Fifth Engineering Division Corp., Ltd., Changsha 410000, ChinaAlthough the use of fiber-reinforced plastic (FRP) rebars instead of mild steel can effectively avoid rebar corrosion, the bonding performance gets weakened. To accurately estimate the bond strength of FRP bars, this paper proposes a particle swarm optimization-based extreme learning machine model based on 222 samples. The model used six variables including the bar position (<i>P</i>), bar surface condition (<i>SC</i>), bar diameter (<i>D</i>), concrete compressive strength (<i>f<sub>c</sub></i>), the ratio of the bar depth to the bar diameter (<i>L</i>/<i>D</i>), and the ratio of the concrete protective layer thickness to the bar diameter (<i>C</i>/<i>D</i>) as input features, and the relative importance of the input parameters was quantified using a sensitivity analysis. The results showed that the proposed model can effectively and accurately estimate the bond strength of the FRP bar with R<sup>2</sup> = 0.945 compared with the R<sup>2</sup> = 0.926 of the original ELM model, which shows that the model can be used as an auxiliary tool for the bond performance analysis of FRP bars. The results of the sensitivity analysis indicate that the parameter <i>L</i>/<i>D</i> is of the greatest importance to the output bond strength.https://www.mdpi.com/2075-5309/12/10/1654FRPbond strengthELMhybrid modelparameter importance analysis |
| spellingShingle | Ran Li Lulu Liu Ming Cheng Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model Buildings FRP bond strength ELM hybrid model parameter importance analysis |
| title | Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model |
| title_full | Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model |
| title_fullStr | Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model |
| title_full_unstemmed | Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model |
| title_short | Estimating the Bond Strength of FRP Bars Using a Hybrid Machine Learning Model |
| title_sort | estimating the bond strength of frp bars using a hybrid machine learning model |
| topic | FRP bond strength ELM hybrid model parameter importance analysis |
| url | https://www.mdpi.com/2075-5309/12/10/1654 |
| work_keys_str_mv | AT ranli estimatingthebondstrengthoffrpbarsusingahybridmachinelearningmodel AT lululiu estimatingthebondstrengthoffrpbarsusingahybridmachinelearningmodel AT mingcheng estimatingthebondstrengthoffrpbarsusingahybridmachinelearningmodel |