Sustainable use of chemically modified tyre rubber in concrete: Machine learning based novel predictive model

Li, Piyu; Khan, Mohsin Ali; El‐Zahar, Essam R.; Awan, Hamad Hassan; Zafar, Adeel; Javed, Muhammad Faisal; Khan, M. Ijaz; Qayyum, Sumaira; Malik, M.Y.; Wang, Fuzhang

doi:10.1016/j.cplett.2022.139478

Cited by 28 publications

(14 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-collinearity problem, which developed owing to the inter-dependence of the input parameters, is a predominant issue in the applications related to machine learning algorithms [12,69,70]. It has the ability to raise the strength of relationships between variables, thus dropping the efficiency of the models being developed.…”

Section: Multi-collinearitymentioning

confidence: 99%

Predicting Marshall Flow and Marshall Stability of Asphalt Pavements Using Multi Expression Programming

Awan¹,

Hussain²,

Javed

et al. 2022

Buildings

View full text Add to dashboard Cite

The traditional method to obtain optimum bitumen content and the relevant parameters of asphalt pavements entails time-consuming, complicated and expensive laboratory procedures and requires skilled personnel. This research study uses innovative and advanced machine learning techniques, i.e., Multi-Expression Programming (MEP), to develop empirical predictive models for the Marshall parameters, i.e., Marshall Stability (MS) and Marshall Flow (MF) for Asphalt Base Course (ABC) and Asphalt Wearing Course (AWC) of flexible pavements. A comprehensive, reliable and wide range of datasets from various road projects in Pakistan were produced. The collected datasets contain 253 and 343 results for ABC and AWC, respectively. Eight input parameters were considered for modeling MS and MF. The overall performance of the developed models was assessed using various statistical measures in conjunction with external validation. The relationship between input and output parameters was determined by performing parametric analysis, and the results of trends were found to be consistent with earlier research findings stating that the developed predicted models are well trained. The results revealed that developed models are superior and efficient in terms of prediction and generalization capability for output parameters, as evident by the correlation coefficient (R) (in this case >0.90) for both ABC and AWC.

show abstract

Section: Multi-collinearitymentioning

confidence: 99%

Predicting Marshall Flow and Marshall Stability of Asphalt Pavements Using Multi Expression Programming

Awan¹,

Hussain²,

Javed

et al. 2022

Buildings

View full text Add to dashboard Cite

show abstract

“…GEP is a powerful and valuable technique for the development of prediction models. [ 23 , 57 , 69 ].…”

Section: Methodsmentioning

confidence: 99%

“…ANNs are generally considered to be robust prediction models in comparison to other AI models; however, it has a black box nature. GEP extracts nonlinear correlation among the variables in the form of simple mathematical equations [ 23 , 56 , 57 ]. Therefore, this study compared a black box model (ANN) with the easily determined mathematical equation-generating model (GEP) to identify the most influential properties of the shielding material and to develop a reliable correlation for the calculation of radiation shielding of bricks in terms of their mechanical properties.…”

Section: Introductionmentioning

confidence: 99%

Estimating Radiation Shielding of Fired Clay Bricks Using ANN and GEP Approaches

et al. 2022

View full text Add to dashboard Cite

This study aimed to determine how radiation attenuation would change when the thickness, density, and compressive strength of clay bricks, modified with partial replacement of clay by fly ash, iron slag, and wood ash. To conduct this investigation, four distinct types of bricks—normal, fly ash-, iron slag-, and wood ash-incorporated bricks were prepared by replacing clay content with their variable percentages. Additionally, models for predicting the radiation-shielding ability of bricks were created using gene expression programming (GEP) and artificial neural networks (ANN). The addition of iron slag improved the density and compressive strength of bricks, thus increasing shielding capability against gamma radiation. In contrast, fly ash and wood ash decreased the density and compressive strength of burnt clay bricks, leading to low radiation shielding capability. Concerning the performance of the Artificial Intelligence models, the root mean square error (RMSE) was determined as 0.1166 and 0.1876 nC for the training and validation data of ANN, respectively. The training set values for the GEP model manifested an RMSE equal to 0.2949 nC, whereas the validation data produced RMSE = 0.3507 nC. According to the statistical analysis, the generated models showed strong concordance between experimental and projected findings. The ANN model, in contrast, outperformed the GEP model in terms of accuracy, producing the lowest values of RMSE. Moreover, the variables contributing towards shielding characteristics of bricks were studied using parametric and sensitivity analyses, which showed that the thickness and density of bricks are the most influential parameters. In addition, the mathematical equation generated from the GEP model denotes its significance such that it can be used to estimate the radiation shielding of burnt clay bricks in the future with ease.

show abstract

“…[27][28][29][30] However, limited research has been conducted on the strength estimation of NaOHpretreated CRC using ML techniques. In the study of Li et al, 31 the key components of CRC mixture, along with the NaOH concentration and pretreatment time, were considered as input variables. They utilized gene expression programming (GEP) to predict the 28-day CS value of NaOH-modified CRC, and conducted an analysis of feature importance as well as parametric analysis.…”

Section: Introductionmentioning

confidence: 99%

Random forest and Shapley additive explanation for compressive strength prediction of NaOH-pretreated crumb rubber concrete

Sun

2023

Progress in Rubber, Plastics and Recycling Technology

View full text Add to dashboard Cite

The compressive strength (CS) of crumb rubber concrete (CRC) can be improved through a chemical pretreatment involving immersion of the crumb rubber particles in a NaOH solution. Despite the potential benefits of this treatment, accurately estimating the CS value of NaOH-pretreated CRC remains challenging. To address this issue, a comprehensive database encompassing 118 entries on the fundamental mixtures of CRC along with NaOH concentration and pretreatment duration has been meticulously compiled for machine learning analysis. The random forest (RF) algorithm is employed to predict the 28-day CS value of NaOH-pretreated CRC. The model hyperparameters are optimized using a random search technique with 10-fold cross-validation. The findings reveal that the optimized RF attains acceptable predictive performance, yielding RMSE, MAE, and R2 values of 3.83 MPa, 2.84 MPa, and 0.85, respectively, on the testing dataset. Additionally, the model is interpreted using multiple techniques, including permutation importance, RF model-based feature importance, and Shapley additive explanation from global or local perspectives. The feature importance analyses consistently highlight the crucial role of crumb rubber content in determining the 28-day CS value of NaOH-pretreated CRC, and the influence of NaOH concentration and pretreatment time appear relatively inconsequential compared to features associated with the CRC mixture. This research contributes to a deeper understanding and better mixture design of CS for NaOH-pretreated CRC.

show abstract

Sustainable use of chemically modified tyre rubber in concrete: Machine learning based novel predictive model

Cited by 28 publications

References 105 publications

Predicting Marshall Flow and Marshall Stability of Asphalt Pavements Using Multi Expression Programming

Predicting Marshall Flow and Marshall Stability of Asphalt Pavements Using Multi Expression Programming

Estimating Radiation Shielding of Fired Clay Bricks Using ANN and GEP Approaches

Random forest and Shapley additive explanation for compressive strength prediction of NaOH-pretreated crumb rubber concrete

Contact Info

Product

Resources

About