High correlated variables creator machine: Prediction of the compressive\n strength of concrete

2020/09/11 by Aydin Shishegaran, Shishegaran, Aydin, Hessam Varaee +5
Engineering · #FOS: Computer and information sciences #Innovative concrete reinforcement materials #Machine Learning (cs.LG) #Non-Destructive Testing Techniques #Ultrasonics and Acoustic Wave Propagation

paper · pdf · doi:10.48550/arxiv.2009.06421

openalex publication_date 2020/09/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we introduce a novel hybrid model for predicting the\ncompressive strength of concrete using ultrasonic pulse velocity (UPV) and\nrebound number (RN). First, 516 data from 8 studies of UPV and rebound hammer\n(RH) tests was collected. Then, high correlated variables creator machine\n(HVCM) is used to create the new variables that have a better correlation with\nthe output and improve the prediction models. Three single models, including a\nstep-by-step regression (SBSR), gene expression programming (GEP) and an\nadaptive neuro-fuzzy inference system (ANFIS) as well as three hybrid models,\ni.e. HCVCM-SBSR, HCVCM-GEP and HCVCM-ANFIS, were employed to predict the\ncompressive strength of concrete. The statistical parameters and error terms\nsuch as coefficient of determination, root mean square error (RMSE), normalized\nmean square error (NMSE), fractional bias, the maximum positive and negative\nerrors, and mean absolute percentage error (MAPE), were computed to evaluate\nand compare the models. The results show that HCVCM-ANFIS can predict the\ncompressive strength of concrete better than all other models. HCVCM improves\nthe accuracy of ANFIS by 5% in the coefficient of determination, 10% in RMSE,\n3% in NMSE, 20% in MAPE, and 7% in the maximum negative error.\n

Related

• Mechanical Strength Prediction of Steel-Polypropylene Fiber-based High-Performance Concrete Using Hybrid Machine Learning Algorithms
• Analysis of Strength Prediction Models using Machine Learning for Mongolian Fly Ash Concrete
• Predicting Confinement Effect of Carbon Fiber Reinforced Polymers on Strength of Concrete using Metaheuristics-based Artificial Neural Networks
• Learning from Sparse Datasets: Predicting Concrete's Strength by Machine Learning
• An Extended Multi-Model Regression Approach for Compressive Strength Prediction and Optimization of a Concrete Mixture