Machine learning techniques to evaluate the ultrasonic pulse velocity of hybrid fiber-reinforced concrete modified with nano-silica

Abstract

It is evident that preparing materials, casting samples, curing, and testing all need time and money. The construction sector will benefit if these problems can be handled using cutting-edge techniques like machine learning. Also, a material’s ultrasonic pulse velocity (UPV) is affected by various variables, and it is difficult to study their combined effect experimentally. This research used machine learning to assess the UPV and SHapley Additive ExPlanations techniques to study the impact of input parameters of hybrid fiber-reinforced concrete modified with nano-silica (HFRNSC). Three ML algorithms were employed, i.e., gradient boosting regressor, adaptive boosting regressor, and extreme gradient boosting, for ultrasonic pulse velocity evaluation. The accuracy of machine learning models was measured via the coefficient of determination (R2), k-fold analysis, statistical tests, and comparing the predicted and actual ultrasonic pulse velocity. This study determined that the gradient boosting and adaptive boosting models had a good level of accuracy for ultrasonic pulse velocity, but the extreme gradient boosting method estimated the ultrasonic pulse velocity of HFRNSCs with a greater degree of precision. Also, from the statistical checks and k-fold approach, it was discovered that the extreme gradient boosting method is more exact in estimating the ultrasonic pulse velocity of HFRNSCs. The SHapley Additive ExPlanations analysis revealed that the age of the specimen and nano-silica had a greater positive impact on the ultrasonic pulse velocity of HFRNSCs, whereas the coarse aggregate to fine aggregate ratio had a negative impact. In addition, fiber volume was found to have both positive and negative effects. By aiding the development of rapid and low-cost methods for determining material properties and the influence of input parameters, the construction industry may profit from the use of such technologies.

A Study to Improve the Reliability of High-Strength Concrete Strength Evaluation Using an Ultrasonic Velocity Method

“…This is because of the different thermal-expansion characteristics of the aggregate and paste, which cause the aggregate to expand and the paste to contract. Moreover, lightweight aggregates exhibit a low coefficient of thermal expansion owing to their relatively high porosity; hence, LAC is likely to exhibit a higher residual strength than NAC, owing to the lower stress reduction at the interface [15]. Andiç-Çakır et al evaluated the high-temperature properties of concrete mixed with limestone aggregate and two types of pumice-based lightweight aggregates.…”

“…Most of the recent research trends through UPV analysis are predictions of strength through computer programming such as machine learning and deep learning for elements such as materials and mixing and existing prediction formulas. However, it is also considered important to analyze and evaluate the differences between UPV and predictive models caused by material factors [14][15][16]. Conceptual diagrams of the concrete matrix during curing and after high-temperature exposure are shown in Figure 2.…”

Statistical Reliability Analysis of Ultrasonic Velocity Method for Predicting Residual Strength of High-Strength Concrete under High-Temperature Conditions

“…Unfortunately, there is a notable deficiency in analyses that explore the strength prediction model under diverse conditions (early age, middle age, and high temperature) and evaluate the discrepancies. UPV lacks a direct causal relationship with strength, but it is dominated by factors such as concrete voids, cracks, and elasticity of the matrix; thus, even with the same strength, different UPVs may appear depending on the matrix state [ 18 , 19 , 20 ].…”