Application of artificial neural networks to predict compressive strength of high strength concrete
A method to predict 28-day compressive strength of high strength concrete (HSC) by using MFNNs is proposed in this paper. The artificial neural networks (ANN) model is constructed trained and tested using the available data. A total of 368 different data of HSC mix-designs were collected from tech...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Academic Journals
2011
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/7901/ http://eprints.uthm.edu.my/7901/1/J14684_8bd68f76e56b12f43d7e299154b6ff90.pdf |
| _version_ | 1848889239569170432 |
|---|---|
| author | Seyed Hakim, Seyed Jamalaldin Noorzaei, Jamaloddin Jaafar, M. S. Mohammed Jameel, Mohammed Jameel Mohammadhassani, Mohammad |
| author_facet | Seyed Hakim, Seyed Jamalaldin Noorzaei, Jamaloddin Jaafar, M. S. Mohammed Jameel, Mohammed Jameel Mohammadhassani, Mohammad |
| author_sort | Seyed Hakim, Seyed Jamalaldin |
| building | UTHM Institutional Repository |
| collection | Online Access |
| description | A method to predict 28-day compressive strength of high strength concrete (HSC) by using MFNNs is
proposed in this paper. The artificial neural networks (ANN) model is constructed trained and tested
using the available data. A total of 368 different data of HSC mix-designs were collected from technical
literature. The data used to predict the compressive strength with ANN consisted of eight input
parameters which include cement, water, coarse aggregate, fine aggregate, silica fume,
superplasticizer, fly ash and granulated grated blast furnace slag. For the training phase, different
combinations of layers, number of neurons, learning rate, momentum and activation functions were
considered. The training was terminated when the root mean square error (RMSE) reached or was less
than 0.001 and the results were tested with test data set. A total of 30 architectures were studied and
the 8-10-6-1 architecture was the best possible architecture. The results show that the relative
percentage error (RPE) for the training set was 7.02% and the testing set was 12.64%. The ANNs models
give high prediction accuracy, and the research results demonstrate that using ANNs to predict
concrete strength is practical and beneficial. |
| first_indexed | 2025-11-15T20:23:01Z |
| format | Article |
| id | uthm-7901 |
| institution | Universiti Tun Hussein Onn Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:23:01Z |
| publishDate | 2011 |
| publisher | Academic Journals |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uthm-79012022-10-17T06:23:00Z http://eprints.uthm.edu.my/7901/ Application of artificial neural networks to predict compressive strength of high strength concrete Seyed Hakim, Seyed Jamalaldin Noorzaei, Jamaloddin Jaafar, M. S. Mohammed Jameel, Mohammed Jameel Mohammadhassani, Mohammad T Technology (General) A method to predict 28-day compressive strength of high strength concrete (HSC) by using MFNNs is proposed in this paper. The artificial neural networks (ANN) model is constructed trained and tested using the available data. A total of 368 different data of HSC mix-designs were collected from technical literature. The data used to predict the compressive strength with ANN consisted of eight input parameters which include cement, water, coarse aggregate, fine aggregate, silica fume, superplasticizer, fly ash and granulated grated blast furnace slag. For the training phase, different combinations of layers, number of neurons, learning rate, momentum and activation functions were considered. The training was terminated when the root mean square error (RMSE) reached or was less than 0.001 and the results were tested with test data set. A total of 30 architectures were studied and the 8-10-6-1 architecture was the best possible architecture. The results show that the relative percentage error (RPE) for the training set was 7.02% and the testing set was 12.64%. The ANNs models give high prediction accuracy, and the research results demonstrate that using ANNs to predict concrete strength is practical and beneficial. Academic Journals 2011 Article PeerReviewed text en http://eprints.uthm.edu.my/7901/1/J14684_8bd68f76e56b12f43d7e299154b6ff90.pdf Seyed Hakim, Seyed Jamalaldin and Noorzaei, Jamaloddin and Jaafar, M. S. and Mohammed Jameel, Mohammed Jameel and Mohammadhassani, Mohammad (2011) Application of artificial neural networks to predict compressive strength of high strength concrete. International Journal of the Physical Sciences, 6 (5). pp. 975-981. |
| spellingShingle | T Technology (General) Seyed Hakim, Seyed Jamalaldin Noorzaei, Jamaloddin Jaafar, M. S. Mohammed Jameel, Mohammed Jameel Mohammadhassani, Mohammad Application of artificial neural networks to predict compressive strength of high strength concrete |
| title | Application of artificial neural networks to predict
compressive strength of high strength concrete |
| title_full | Application of artificial neural networks to predict
compressive strength of high strength concrete |
| title_fullStr | Application of artificial neural networks to predict
compressive strength of high strength concrete |
| title_full_unstemmed | Application of artificial neural networks to predict
compressive strength of high strength concrete |
| title_short | Application of artificial neural networks to predict
compressive strength of high strength concrete |
| title_sort | application of artificial neural networks to predict
compressive strength of high strength concrete |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/7901/ http://eprints.uthm.edu.my/7901/1/J14684_8bd68f76e56b12f43d7e299154b6ff90.pdf |