Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete
Additive usage like micro silica (MS) and fly ash (FA) through partial substitution of cohesive materials in concrete design has positive impacts on the concrete’s mechanical properties, reducing concrete production costs and declining environmental pollution. The concrete’s compressive strength is...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2022-07-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_153129_d4e2491fefa5ff570721b73c1d7c7789.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856408608636928 |
|---|---|
| author | Hanlie Cheng Shiela Kitchen Graciela Daniels |
| author_facet | Hanlie Cheng Shiela Kitchen Graciela Daniels |
| author_sort | Hanlie Cheng |
| collection | DOAJ |
| description | Additive usage like micro silica (MS) and fly ash (FA) through partial substitution of cohesive materials in concrete design has positive impacts on the concrete’s mechanical properties, reducing concrete production costs and declining environmental pollution. The concrete’s compressive strength is the main factor considered in the mechanical properties of the concrete, which is estimated by experimental efforts or non-destructive models as developed artificial models. In the present work, two hybrid radial base neural networks (RBFN) coupled with an arithmetic optimization algorithm (AORBFN) and an antlion optimization algorithm (ALRBFN) were developed for the prediction of compressive strength. The models' variables contain the binder, fly ash, micro silica, superplasticizer, coarse aggregate, water, and the target's curing time as input and compressive strength. The results showed that both models have the capability of delivering a precise compressive strength prediction. The best R2 value for the AORBF is 0.9706 in the test phase, and the best-obtained R2 for the ALRBF model is 0.9669, which is achieved in the same phase. The results conclude that the AORBF model can be preferred as an applicable model for compressive strength prediction. |
| format | Article |
| id | doaj-art-2b3fd6e4f5264b028deb6a97f7e2c520 |
| institution | Kabale University |
| issn | 2821-0263 |
| language | English |
| publishDate | 2022-07-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Advances in Engineering and Intelligence Systems |
| spelling | doaj-art-2b3fd6e4f5264b028deb6a97f7e2c5202025-02-12T08:46:21ZengBilijipub publisherAdvances in Engineering and Intelligence Systems2821-02632022-07-0100102697910.22034/aeis.2022.340732.1012153129Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC ConcreteHanlie Cheng0Shiela Kitchen1Graciela Daniels2Faculty of Contemporary Sciences and Technologies, South East European University, Tetovo, 1200, MacedoniaCollege of Arts and Sciences, University of New England, Armidale, New South Wales, 2351, AustraliaCentral Arizona College, Coolidge, Arizona, 85128, United StatesAdditive usage like micro silica (MS) and fly ash (FA) through partial substitution of cohesive materials in concrete design has positive impacts on the concrete’s mechanical properties, reducing concrete production costs and declining environmental pollution. The concrete’s compressive strength is the main factor considered in the mechanical properties of the concrete, which is estimated by experimental efforts or non-destructive models as developed artificial models. In the present work, two hybrid radial base neural networks (RBFN) coupled with an arithmetic optimization algorithm (AORBFN) and an antlion optimization algorithm (ALRBFN) were developed for the prediction of compressive strength. The models' variables contain the binder, fly ash, micro silica, superplasticizer, coarse aggregate, water, and the target's curing time as input and compressive strength. The results showed that both models have the capability of delivering a precise compressive strength prediction. The best R2 value for the AORBF is 0.9706 in the test phase, and the best-obtained R2 for the ALRBF model is 0.9669, which is achieved in the same phase. The results conclude that the AORBF model can be preferred as an applicable model for compressive strength prediction.https://aeis.bilijipub.com/article_153129_d4e2491fefa5ff570721b73c1d7c7789.pdfcompressive strengthhpc concretearithmetic optimizationantlion optimizationradial base neural networks |
| spellingShingle | Hanlie Cheng Shiela Kitchen Graciela Daniels Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete Advances in Engineering and Intelligence Systems compressive strength hpc concrete arithmetic optimization antlion optimization radial base neural networks |
| title | Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete |
| title_full | Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete |
| title_fullStr | Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete |
| title_full_unstemmed | Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete |
| title_short | Novel Hybrid Radial-Based Neural Network Model for Predicting the Compressive Strength of Long-Term HPC Concrete |
| title_sort | novel hybrid radial based neural network model for predicting the compressive strength of long term hpc concrete |
| topic | compressive strength hpc concrete arithmetic optimization antlion optimization radial base neural networks |
| url | https://aeis.bilijipub.com/article_153129_d4e2491fefa5ff570721b73c1d7c7789.pdf |
| work_keys_str_mv | AT hanliecheng novelhybridradialbasedneuralnetworkmodelforpredictingthecompressivestrengthoflongtermhpcconcrete AT shielakitchen novelhybridradialbasedneuralnetworkmodelforpredictingthecompressivestrengthoflongtermhpcconcrete AT gracieladaniels novelhybridradialbasedneuralnetworkmodelforpredictingthecompressivestrengthoflongtermhpcconcrete |