Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network
In this study, polyvinyl alcohol (PVA) fibers and nanoparticles were incorporated to enhance the durability of geopolymer mortar (GM) with metakaolin (MK) and fly ash (FA). The dosage of nano-SiO2 (NS) was 0–2.5% and that of PVA fiber was 0–1.2%. The durability of GM includes resistance to chloride...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2024-03-01
|
| Series: | Nanotechnology Reviews |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/ntrev-2023-0214 |
| _version_ | 1797266185405857792 |
|---|---|
| author | Zhang Xuemei Zhang Peng Yuan Weisuo Hu Shaowei |
| author_facet | Zhang Xuemei Zhang Peng Yuan Weisuo Hu Shaowei |
| author_sort | Zhang Xuemei |
| collection | DOAJ |
| description | In this study, polyvinyl alcohol (PVA) fibers and nanoparticles were incorporated to enhance the durability of geopolymer mortar (GM) with metakaolin (MK) and fly ash (FA). The dosage of nano-SiO2 (NS) was 0–2.5% and that of PVA fiber was 0–1.2%. The durability of GM includes resistance to chloride ion penetration, freeze–thaw cycles, and sulfate erosion. Compared with the single BP neural network (BPNN) model, a particle swarm optimized BPNN (PSO-BPNN) model was utilized to predict the resistance to chloride ion penetration, freeze–thaw cycles, and sulfate erosion of GMs with different dosages of nanoparticles and PVA fibers. In the model, the dosage of NS, PVA fiber, FA, and MK were used as input layers, and the durability parameters of electric flux, mass loss, and compressive strength loss of GMs were used as output layers. The result exhibits that the root mean square errors (RMSEs) of BPNN for resistance to chloride ion penetration, freeze–thaw cycles, and sulfate erosion of GM mixed with nanoparticles and PVA fibers are 145.39, 6.43, and 2.19, whereas RMSEs obtained from PSO-BPNN are 76.33, 2.87, and 1.03, respectively. The NN optimized by particle swarm algorithm has better prediction accuracy. The PSO-BPNN can be utilized for estimating durability of GM reinforced by NS and PVA fiber, which can provide a guide for the proportion design of GM with PVA fiber and NS as well as for the engineering practice in the future. |
| first_indexed | 2024-04-25T00:56:40Z |
| format | Article |
| id | doaj.art-f455b5c3a414473189cbc7c3fffbfd36 |
| institution | Directory Open Access Journal |
| issn | 2191-9097 |
| language | English |
| last_indexed | 2024-04-25T00:56:40Z |
| publishDate | 2024-03-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Nanotechnology Reviews |
| spelling | doaj.art-f455b5c3a414473189cbc7c3fffbfd362024-03-11T10:04:52ZengDe GruyterNanotechnology Reviews2191-90972024-03-011311326565610.1515/ntrev-2023-0214Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural networkZhang Xuemei0Zhang Peng1Yuan Weisuo2Hu Shaowei3School of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou450001, ChinaSchool of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou450001, ChinaSchool of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou450001, ChinaSchool of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou450001, ChinaIn this study, polyvinyl alcohol (PVA) fibers and nanoparticles were incorporated to enhance the durability of geopolymer mortar (GM) with metakaolin (MK) and fly ash (FA). The dosage of nano-SiO2 (NS) was 0–2.5% and that of PVA fiber was 0–1.2%. The durability of GM includes resistance to chloride ion penetration, freeze–thaw cycles, and sulfate erosion. Compared with the single BP neural network (BPNN) model, a particle swarm optimized BPNN (PSO-BPNN) model was utilized to predict the resistance to chloride ion penetration, freeze–thaw cycles, and sulfate erosion of GMs with different dosages of nanoparticles and PVA fibers. In the model, the dosage of NS, PVA fiber, FA, and MK were used as input layers, and the durability parameters of electric flux, mass loss, and compressive strength loss of GMs were used as output layers. The result exhibits that the root mean square errors (RMSEs) of BPNN for resistance to chloride ion penetration, freeze–thaw cycles, and sulfate erosion of GM mixed with nanoparticles and PVA fibers are 145.39, 6.43, and 2.19, whereas RMSEs obtained from PSO-BPNN are 76.33, 2.87, and 1.03, respectively. The NN optimized by particle swarm algorithm has better prediction accuracy. The PSO-BPNN can be utilized for estimating durability of GM reinforced by NS and PVA fiber, which can provide a guide for the proportion design of GM with PVA fiber and NS as well as for the engineering practice in the future.https://doi.org/10.1515/ntrev-2023-0214geopolymer mortarpso-bp neural networkdurabilityprediction |
| spellingShingle | Zhang Xuemei Zhang Peng Yuan Weisuo Hu Shaowei Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network Nanotechnology Reviews geopolymer mortar pso-bp neural network durability prediction |
| title | Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network |
| title_full | Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network |
| title_fullStr | Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network |
| title_full_unstemmed | Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network |
| title_short | Durability prediction of geopolymer mortar reinforced with nanoparticles and PVA fiber using particle swarm optimized BP neural network |
| title_sort | durability prediction of geopolymer mortar reinforced with nanoparticles and pva fiber using particle swarm optimized bp neural network |
| topic | geopolymer mortar pso-bp neural network durability prediction |
| url | https://doi.org/10.1515/ntrev-2023-0214 |
| work_keys_str_mv | AT zhangxuemei durabilitypredictionofgeopolymermortarreinforcedwithnanoparticlesandpvafiberusingparticleswarmoptimizedbpneuralnetwork AT zhangpeng durabilitypredictionofgeopolymermortarreinforcedwithnanoparticlesandpvafiberusingparticleswarmoptimizedbpneuralnetwork AT yuanweisuo durabilitypredictionofgeopolymermortarreinforcedwithnanoparticlesandpvafiberusingparticleswarmoptimizedbpneuralnetwork AT hushaowei durabilitypredictionofgeopolymermortarreinforcedwithnanoparticlesandpvafiberusingparticleswarmoptimizedbpneuralnetwork |