Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete
This study develops and presents an Artificial Neural Network (ANN) model employing the Levenberg-Marquardt Backpropagation (LMBP) training algorithm to predict the compressive strength of both normal and high strength concrete. The model's robustness was evaluated using an extensive dataset co...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Cleaner Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772397623000448 |
| _version_ | 1797389356822953984 |
|---|---|
| author | Arslan Qayyum Khan Hasnain Ahmad Awan Mehboob Rasul Zahid Ahmad Siddiqi Amorn Pimanmas |
| author_facet | Arslan Qayyum Khan Hasnain Ahmad Awan Mehboob Rasul Zahid Ahmad Siddiqi Amorn Pimanmas |
| author_sort | Arslan Qayyum Khan |
| collection | DOAJ |
| description | This study develops and presents an Artificial Neural Network (ANN) model employing the Levenberg-Marquardt Backpropagation (LMBP) training algorithm to predict the compressive strength of both normal and high strength concrete. The model's robustness was evaluated using an extensive dataset comprising 1637 samples. Eight input variables, including the cement content, blast furnace slag, fly ash, fine aggregate, coarse aggregate, water content, superplasticizer, and testing age, were considered. The optimal number of hidden layers and neurons in the layer were identified through analysis, and the effectiveness of the model was assessed through k-fold cross-validation and statistical measures, including correlation coefficient (R), coefficient of determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MEA). Comparison with other models was carried out, and the perturbation/super-position method was employed for parametric studies to investigate the effect of each input variable on the output variable. The k-fold cross-validation confirmed the generalizability of the model, and statistical measures showed good results, with unit cement content and superplasticizers having the highest impact on compressive strength. The findings demonstrate that the suggested ANN model is an extremely precise, economical, and practical predictive tool for concrete compressive strength. |
| first_indexed | 2024-03-08T22:55:42Z |
| format | Article |
| id | doaj.art-9d1dbba84d3f4e0c8d480aa3e5751843 |
| institution | Directory Open Access Journal |
| issn | 2772-3976 |
| language | English |
| last_indexed | 2024-03-08T22:55:42Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Cleaner Materials |
| spelling | doaj.art-9d1dbba84d3f4e0c8d480aa3e57518432023-12-16T06:11:11ZengElsevierCleaner Materials2772-39762023-12-0110100211Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concreteArslan Qayyum Khan0Hasnain Ahmad Awan1Mehboob Rasul2Zahid Ahmad Siddiqi3Amorn Pimanmas4Department of Civil Engineering, The University of Lahore, Lahore, Pakistan; Corresponding author at: Department of Civil Engineering, The University of Lahore, Lahore 54000, Pakistan.Department of Civil Engineering, The University of Lahore, Lahore, PakistanDepartment of Civil Engineering, Yokohama National University, Yokohama, JapanDepartment of Civil Engineering, The University of Lahore, Lahore, PakistanDepartment of Civil Engineering, Kasetsart University, Bangkok, ThailandThis study develops and presents an Artificial Neural Network (ANN) model employing the Levenberg-Marquardt Backpropagation (LMBP) training algorithm to predict the compressive strength of both normal and high strength concrete. The model's robustness was evaluated using an extensive dataset comprising 1637 samples. Eight input variables, including the cement content, blast furnace slag, fly ash, fine aggregate, coarse aggregate, water content, superplasticizer, and testing age, were considered. The optimal number of hidden layers and neurons in the layer were identified through analysis, and the effectiveness of the model was assessed through k-fold cross-validation and statistical measures, including correlation coefficient (R), coefficient of determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MEA). Comparison with other models was carried out, and the perturbation/super-position method was employed for parametric studies to investigate the effect of each input variable on the output variable. The k-fold cross-validation confirmed the generalizability of the model, and statistical measures showed good results, with unit cement content and superplasticizers having the highest impact on compressive strength. The findings demonstrate that the suggested ANN model is an extremely precise, economical, and practical predictive tool for concrete compressive strength.http://www.sciencedirect.com/science/article/pii/S2772397623000448Artificial neural network (ANN)K-fold cross-validationCompressive strengthPrediction modelMix proportioning of concrete |
| spellingShingle | Arslan Qayyum Khan Hasnain Ahmad Awan Mehboob Rasul Zahid Ahmad Siddiqi Amorn Pimanmas Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete Cleaner Materials Artificial neural network (ANN) K-fold cross-validation Compressive strength Prediction model Mix proportioning of concrete |
| title | Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete |
| title_full | Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete |
| title_fullStr | Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete |
| title_full_unstemmed | Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete |
| title_short | Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete |
| title_sort | optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete |
| topic | Artificial neural network (ANN) K-fold cross-validation Compressive strength Prediction model Mix proportioning of concrete |
| url | http://www.sciencedirect.com/science/article/pii/S2772397623000448 |
| work_keys_str_mv | AT arslanqayyumkhan optimizedartificialneuralnetworkmodelforaccuratepredictionofcompressivestrengthofnormalandhighstrengthconcrete AT hasnainahmadawan optimizedartificialneuralnetworkmodelforaccuratepredictionofcompressivestrengthofnormalandhighstrengthconcrete AT mehboobrasul optimizedartificialneuralnetworkmodelforaccuratepredictionofcompressivestrengthofnormalandhighstrengthconcrete AT zahidahmadsiddiqi optimizedartificialneuralnetworkmodelforaccuratepredictionofcompressivestrengthofnormalandhighstrengthconcrete AT amornpimanmas optimizedartificialneuralnetworkmodelforaccuratepredictionofcompressivestrengthofnormalandhighstrengthconcrete |