Prediction of Concrete Compressive Strength and Slump by Machine Learning Methods
Прогнозирование прочности бетона на сжатие и осадки с использованием методов машинного обучения
2019-01-01
SCID: 54.1/ab5e59bm
Discuss with AI
ReliefF feature selectionconcrete compressive strengthconcrete slumpfuzzy logic regressionmin-max normalization
Figures from the paper
Abstract (AI)
Machine learning methods have been successfully applied to many engineering disciplines. Prediction of the concrete compressive strength ( f c ) and slump ( S ) is important in terms of the desirability of concrete and its sustainability. The goals of this study were (i) to determine the most successful normalization technique for the datasets, (ii) to select the prime regression method to predict the f c and S outputs, (iii) to obtain the best subset with the ReliefF feature selection method, and (iv) to compare the regression results for the original and selected subsets. Experimental results demonstrate that the decimal scaling and min‐max normalization techniques are the most successful methods for predicting the compressive strength and slump outputs, respectively. According to the evaluation metrics, such as the correlation coefficient, root mean squared error, and mean absolute error, the fuzzy logic method makes better predictions than any other regression method. Moreover, when the input variable was reduced from seven to four by the ReliefF feature selection method, the predicted accuracy was within the acceptable error rate.
Key Findings
1
Decimal scaling was the most successful normalization technique for predicting concrete compressive strength.
2
Fuzzy logic regression outperformed the other evaluated regression methods according to correlation coefficient, root mean squared error, and mean absolute error.
3
Min–max normalization produced the best predictions for concrete slump.
4
ReliefF reduced the input variables from seven to four while maintaining prediction accuracy within an acceptable error rate.
5
The study compared prediction performance using the original and ReliefF-selected feature subsets for both concrete properties.
Research Object
Concrete, characterized by its compressive strength and slump
Research Subject
Prediction accuracy of concrete compressive strength and slump, including the effects of normalization, regression method, and feature selection
Publication Details
Publication Date
2019-01-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest