Document Type

Article

Publication Date

2023

Publication Title

Applied Sciences

Keywords

regression analysis, numerical analysis, concrete construction methods, material strength prediction, experiment and testing, variance

Abstract

Because concrete strengths and quality are affected by various factors, multivariate regression models are often used to analyze the differences between predicted and target outputs. However, the variableness of a predicted output and how individual input parameters affect prediction reliabilities are still uncertain in practical applications, especially for the prediction of compressive strengths of concrete. This study aims to develop multivariate models for predicting concrete strengths and providing the variance analysis of prediction results by comparisons with experiment outcomes. First, this paper provides an in-depth examination of established variance analysis methods in the context of commonly used multivariate regression models. Then, based on Gaussian process regression, this study melds principal component analysis (PCA), linear discriminant analysis (LDA), and multivariate analysis of variance (MANOVA) to assess the variability in concrete strength prediction using different curing methods. This innovative approach proves effective in evaluating the precision of the correlation and regression models (R-squared values ≥ 0.9049). The comparison between prediction results and experiment outcomes shows that retaining heat in cylinders can make them become too hot and overestimate in-place concrete strength. This study improves the methodologies of regression modeling for variance analysis and improves the reliability of concrete strength prediction. Additionally, the outcomes of this research can help save a substantial amount of financial resources and time that are required to obtain experimental data on the strengths of concrete components.

Funding Source

This research was funded by the Illinois Department of Transportation grant number ICT-R27-219.

DOI

10.3390/app132212239

Comments

First published in Applied Sciences 2023, 13(22), 12239; https://doi.org/10.3390/app132212239.

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

The data presented in this study are available on request from the corresponding author. The data are not publicly available due to privacy issues.

Download

Share

COinS