Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches

Eidgahee, Danial Rezazadeh; Jahangir, Hashem; Solatifar, Nader; Fakharian, Pouyan; Rezaeemanesh, Mansoureh

doi:10.1007/s00521-022-07382-3

Cited by 35 publications

(12 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By decreasing the requirement for cement, using supplemental cement ingredients like SF and FA has a favorable impact on energy, economical, and environmental considerations in the concrete industry (Dong et al, 2015;Hossain et al, 2016;Liu et al, 2017;de Matos et al, 2020;Kumar et al, 2021a;Alaloul et al, 2021;Çelik et al, 2022). Optimizing concrete mixes using supplementary content is another important consideration in literature (AlShareedah and Nassiri, 2021;Bhuva and Bhogayata, 2022;Wang et al, 2022b;Chen et al, 2022;Rezazadeh Eidgahee et al, 2022;Siamardi, 2022;Solouki et al, 2022;Sun et al, 2022;Warda et al, 2022). As an example, the mechanical characteristics of FA-SF plain concrete (FA-SPC) and FA SF coconut fiber reinforced concrete (FA-SCFRC) are examined in Khan and Ali's study (Khan and Ali, 2019).…”

Section: Introduction 1general Research Backgroundmentioning

confidence: 99%

Global warming potential-based life cycle assessment and optimization of the compressive strength of fly ash-silica fume concrete; environmental impact consideration

Onyelowe

Ebid

Riofrio

et al. 2022

Front. Built Environ.

Self Cite

View full text Add to dashboard Cite

In this research study, extensive literature searches on the compressive strength of concrete produced from the addition of fly ash (FA) and silica fume (SF) as extra constituents to the conventional concrete mixes, which gave rise to 330 mix points of concrete database. Due to the worrisome environmental impact of concrete production and usage in concrete activities, it has been pertinent to conduct the life cycle impact assessment of this procedure. Secondly, due to the over dependence of concrete production experts on laboratory exercise, there is also an urgent need to propose equations that reduce this dependence, that can be used in design, construction and performance evaluation of concrete infrastructure, hence the multi-objective nature of this research work. The results of the global warming potential (GWP) based on cement dosage show that Portland cement contributes about 90% of the total score. This is followed by the use of coarse aggregate contributing 6%, superplasticizer, 3% and fine aggregates, 2%. These show the functions of CO2 emissions and other greenhouses gas emissions in the entire system. Also, the result of the terrestrial acidification potential (TAP) for the concrete mixes in this study show that the lowest cement mix “C340-FAg658-FA0-SF15ˮ has a human toxicity, both carcinogenic and non-carcinogenic that showed an added impact of about 14 kg of 1, 4 equivalents of dichlorobenzene (DCB eq.). This result is 428% less impact than other studies found in the literature that used FA. Finally, it was found that the addition of FA and SF in concrete has a lowering effect on the environmental impact indicators due to reduced cement dosage. Furthermore, the results of the model predictions show that ANN with a performance index of 0.986 (4.8%) showed decisive superiority to predict the compressive strength of the FA-SF concrete over EPR, 0.951 (8.7%), GP, 0.94 (9.5%) and GEP, 0.93 (10%).

show abstract

Section: Introduction 1general Research Backgroundmentioning

confidence: 99%

Global warming potential-based life cycle assessment and optimization of the compressive strength of fly ash-silica fume concrete; environmental impact consideration

Onyelowe

Ebid

Riofrio

et al. 2022

Front. Built Environ.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The value of the single-layer self-organizing algorithms comprises straightforwardness and their ability to categorize model structure [70,71]. It should be noted that in the GMDH-Combi approach, different combinations of input variable with user-defined-power-orders is considered and apparently a time-consuming calculation process would be formed [71][72][73]. For instance, considering to model a dataset with two inputs, (x1 and x2) and a target variable (y), a function of quadratic polynomial that the optimization process needs to be performed would be as y=c0+c1…”

Section: Gmdh-combinatorial Predictionmentioning

confidence: 99%

Optimal Compressive Strength of RHA Ultra-High-Performance Lightweight Concrete (UHPLC) and Its Environmental Performance Using Life Cycle Assessment

Onyelowe

Ebid²,

Mahdi³

et al. 2022

Civ Eng J

View full text Add to dashboard Cite

Frequent laboratory needs during the production of concrete for infrastructure development purposes are a factor of serious concern for sustainable development. In order to overcome this trend, an intelligent forecast of the concrete properties based on multiple data points collected from various concrete mixes produced and cured under different conditions is adopted. It is equally important to consider the impact of the concrete components in this attempt to take care of the environmental risks involved in this production. In this work, 192 mixes of an ultra-high-performance lightweight concrete (UHPLC) were collected from literature representing different mixes cured under different periods and laboratory conditions. These mix proportions constitute measured variables, which are curing age (A), cement content (C), fine aggregate (FAg), plasticizer (PL), and rice husk ash (RHA). The studied concrete property was the unconfined compressive strength (Fc). This exercise was necessary to reduce multiple dependence on laboratory examinations by proposing concrete strength equations. First, the life cycle assessment evaluation was conducted on the rice husk ash-based UHPLC, and the results from the 192 mixes show that the C-783 mix (87 kg/m3 RHA) has the highest score on the environmental performance evaluation, while C-300 (75 kg/m3 RHA) with life cycle indices of 289.85 kg CO2eq. Global warming potential (GWP), 0.66 kg SO2eq. Terrestrial acidification and 5.77 m3 water consumption was selected to be the optimal choice due to its good profile in the LCA and the Fc associated with the mix. Second, intelligent predictions were conducted by using six algorithms (ANN-BP), (ANN-GRG), (ANN-GA), (GP), (EPR), and (GMDH-Combi). The results show that (ANN-BP) with performance indices of R; 0.989, R2; 0.979, mean square error (MSE); 2252.55, root mean squared error (RMSE); 42.46 MPa and mean absolute percentage error (MAPE); 4.95% outclassed the other five techniques and is selected as the decisive model. However, it also compared well and outclassed previous models, which had used gene expression programming (GEP) and random forest regression (RFR) and achieved R2of 0.96 and 0.91, respectively. Doi: 10.28991/CEJ-2022-08-11-03 Full Text: PDF

show abstract

“…On the other hand, the dynamic modulus characterizes the stiffness of the asphalt mixtures under continuous and successive loading. Variations of this modulus are a function of loading time (frequency) and temperature (Rezazadeh Eidgahee et al 2022). Therefore, the pavement response to the applied loads is highly affected by the depth temperature.…”

Section: Introductionmentioning

confidence: 99%

Regression Predictive Models for Depth Temperature of Asphalt Layers in Iran

Sedighian-Fard,

Solatifar

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Depth temperature of asphalt layers is one of the most predominant required factors for asphalt pavements analysis, design, maintenance, and rehabilitation purposes. In this study, using the results from field experiments in six asphalt pavement sites located in different climatic conditions in Iran, the depth temperature of asphalt layers was investigated. By employing the four well-known regression-based predictive models including, Gedafa et al., Albayati and Alani, BELLS, and Park et al., the depth temperatures of asphalt layers were predicted. Two statistical criteria, accuracy and bias, have been adopted for evaluating the performance and capability of these models in predicting the depth temperature of asphalt layers. Results exhibited a fair correlation between the predicted depth temperature values and those measured during the Falling Weight Deflectometer (FWD) testing. However, it is necessary to enhance the prediction accuracy and diminish its bias by calibrating the mentioned models for determining the depth temperature of asphalt layers in pavements in Iran. For this reason, these existing prediction models were calibrated, and new predictive models were developed. Performance evaluation and validation of the newly developed models showed an excellent correlation between predicted and measured values. In addition, results exhibit the capability of the developed models in predicting the depth temperature of asphalt layers with very good prediction precision (R2 = 0.94) and low predictive bias.

show abstract

Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches

Cited by 35 publications

References 70 publications

Global warming potential-based life cycle assessment and optimization of the compressive strength of fly ash-silica fume concrete; environmental impact consideration

Global warming potential-based life cycle assessment and optimization of the compressive strength of fly ash-silica fume concrete; environmental impact consideration

Optimal Compressive Strength of RHA Ultra-High-Performance Lightweight Concrete (UHPLC) and Its Environmental Performance Using Life Cycle Assessment

Regression Predictive Models for Depth Temperature of Asphalt Layers in Iran

Contact Info

Product

Resources

About