The Influence of Urtica dioica and Vitis vinifera Fibers on the Thermal Properties and Flammability of Polylactide Composites.

This study focuses on examining the influence of bast fibers on the flammability and thermal properties of the polylactide matrix (PLA). For this purpose, Urtica dioica and Vitis vinifera fibers were subjected to two types of modifications: mercerization in NaOH solution (M1 route) and encapsulation in an organic PLA solution (M2 route). In a further step, PLA composites containing 5, 10, and 15 wt% of unmodified and chemically treated fibers were obtained. The results of the tests show that only biocomposites containing mercerized fibers had a nearly 20% reduced flammability compared to that of PLA. Moreover, the biofiller obtained in this way belongs to the group of flame retardants that generate char residue during combustion, which was also confirmed by TGA tests. The M2 modification route allowed to achieve higher mass viscosity than the addition of unmodified and M1-modified fibers. The reason is that fibers additionally encapsulated in a polymer layer impede the mobility of the chain segments. The inferior homogenization of the M2-modified fibers in the PLA matrix translated into a longer combustion time and only a 15% reduction in flammability.

Research on the Development of a Way to Modify Asphalt Mixtures with PET Recyclates.

Due to the growing need to recycle plastics, new possibilities for their reuse are intensively sought. In the Asian market, waste polymers are increasingly used to modify road bitumen. This solution is beneficial in many aspects, especially in economic and ecological terms. In this work, recycled poly(ethylene terephthalate) (RPET), obtained from storage points located in Lesser Poland, was subjected to material recycling, and its properties were examined using three analyses: differential scanning calorimetry (DSC), thermogravimetric analysis (TG), and Fourier transform infrared spectroscopy (FTIR). The most important point of this research was the selection of conditions for obtaining modified asphalt mixtures through the addition of RPET. Subsequently, the effect of the polymer on the properties of road bitumens was assessed on the basis of penetration tests, softening point, elastic recovery, and structure. In the last stage of our research work, asphalt mixtures with the addition of modified waste PET (PMA) containing mineral filler in the form of basalt dust were obtained. The properties of the obtained mineral-polymer-asphalt mixtures were compared in terms of frost resistance, structure, and abrasion resistance with the properties of mineral-asphalt mixtures that were taken from damaged road surfaces in four points in the city of Tarnów (Lesser Poland) in the winter of 2022. It has been shown that the modification of road bitumen with the use of recyclate and mineral filler has a significant impact on its performance properties.

Electrospinning of Poly (Acrylamide), Poly (Acrylic Acid) and Poly (Vinyl Alcohol) Nanofibers: Characterization and Optimization Study on the Effect of Different Parameters on Mean Diameter Using Taguchi Design of Experiment Method.

In this study, nanofibers of poly (acrylic acid) (PAAc), polyacrylamide (PAAm) and poly (vinyl alcohol) (PVOH) were prepared using the electrospinning technique. Based on the Taguchi DOE (design of experiment) method, the effects of electrospinning parameters, i.e., needle tip to collector distance, polymer solution concentration, applied voltage, polymer solution feed rate and polymer type, on the diameter and morphology of polymer nanofibers were evaluated. Analyses of the experiments for the diameters of the polymer nanofibers showed that the type of polymer was the most significant factor. The optimal combination to obtain the smallest diameters with minimum deviations for electrospun polymer nanofibers was also determined. For this purpose, the appropriate factor levels were determined as follows: polymer PAAm, applied voltage 10 kV, delivery rate 0.1 mL/h, needle tip to collector distance 10 cm, and polymer solution concentration 8%, to obtain the thinnest nanofibers. This combination was further validated by conducting a confirmation experiment, and the average diameter of the polymer nanofibers was found to be close to the optimal conditions estimated by the Taguchi DOE method.

Preparation and Characterization of Novel Microgels Containing Nano-SiO2 and Copolymeric Hydrogel Based on Poly (Acrylamide) and Poly (Acrylic Acid): Morphological, Structural and Swelling Studies.

In this paper, novel microgels containing nano-SiO2 were prepared by in situ copolymerization using nano-SiO2 particles as a reinforcing agent, nanosilica functional monomer (silane-modified nano-SiO2) as a structure and morphology director, acrylamide (AAm) as a monomer, acrylic acid (AAc) as a comonomer, potassium persulfate (KPS) as a polymerization initiator, and N,N'-methylene bis (acrylamide) (MBA) as a crosslinker. In addition, a conventional copolymeric hydrogel based on poly (acrylamide/acrylic acid) was synthesized by solution polymerization. The microgel samples, hydrogel and nanoparticles were characterized by transmission electron microscopy (TEM), field emission scanning electron microscopy (FESEM), Fourier transform infrared (FTIR) spectroscopy, thermogravimetric analysis (TGA) and differential scanning calorimetry (DSC). A FESEM micrograph of copolymeric hydrogel showed the high porosity and 3D interconnected microstructure. Furthermore, FESEM results demonstrated that when nano-SiO2 particles were used in the AAm/AAc copolymerization process, the microstructure and morphology of product changed from porous hydrogel to a nanocomposite microgel with cauliflower-like morphology. According to FESEM images, the copolymerization of AAm and AAc monomers with a nanosilica functional monomer or polymerizable nanosilica particle as a seed led to a microgel with core-shell structure and morphology. These results demonstrated that the polymerizable vinyl group on nano-SiO2 particles have controlled the copolymerization and the product morphology. FTIR analysis showed that the copolymeric chains of polyacrylamide (PAAm) and poly (acrylic acid) (PAAc) were chemically bonded to the surfaces of the nano-SiO2 particles and silane-modified nano-SiO2. The particulate character of microgel samples and the existence of long distance among aggregations of particles led to rapid swelling and increasing of porosity and therefore increasing of degree of swelling.

Consideration of Critical Parameters for Improving the Efficiency of Concrete Structures Reinforced with FRP.

Fibre-reinforced polymer materials (FRP) are increasingly used to reinforce structural elements. Due to this, it is possible to increase the load-bearing capacity of polymer, wooden, concrete, and metal structures. In this article, the authors collected all the crucial aspects that influence the behaviour of concrete elements reinforced with FRP. The main types of FRP, their characterization, and their impact on the load-carrying capacity of a composite structure are discussed. The most significant aspects, such as type, number of FRP layers including fibre orientation, type of matrix, reinforcement of concrete columns, preparation of a concrete surface, fire-resistance aspects, recommended conditions for the lamination process, FRP laying methods, and design aspects were considered. Attention and special emphasis were focused on the description of the current research results related to various types of concrete reinforced with FRP composites. To understand which aspects should be taken into account when designing concrete reinforcement with composite materials, the main guidelines are presented in tabular form.

Novel Synthesis, Characterization and Amoxicillin Release Study of pH-Sensitive Nanosilica/Poly(acrylic acid) Macroporous Hydrogel with High Swelling.

The effect of SiO2 nanoparticles on the formation of PAA (poly acrylic acid) gel structure was investigated with seeded emulsion polymerization method used to prepare SiO2/PAA nanoparticles. The morphologies of the nanocomposite nanoparticles were studied by transmission electron microscopy (TEM). Fourier-transform infrared (FTIR) spectroscopy results indicated that the PAA was chemically bonded to the surface of the SiO2 nanoparticles. Additionally, the resulting morphology of the nanocomposite nanoparticles confirmed the co-crosslinking role of the SiO2 nanoparticles in the formation of the 3D structure and hydrogel of PAA. SiO2/PAA nanocomposite hydrogels were synthesized by in situ solution polymerization with and without toluene. The morphology studies by field emission scanning electron microscopy (FESEM) showed that when the toluene was used as a pore forming agent in the polymerization process, a macroporous hydrogel structure was achieved. The pH-sensitive swelling behaviors of the nanocomposite hydrogels showed that the formation of pores in the gels structure was a dominant factor on the water absorption capacity. In the current research the absorption capacity was changed from about 500 to 4000 g water/g dry hydrogel. Finally, the macroporous nanocomposite hydrogel sample was tested as an amoxicillin release system in buffer solutions with pHs of 3, 7.2, and 9 at 37 °C. The results showed that the percentage cumulative release of amoxicillin from the hydrogels was higher in neutral and basic mediums than in the acidic medium and the amoxicillin release rate was decreased with increasing pH. Additionally, the release results were very similar to swelling results and hence amoxicillin release was a swelling controlled-release system.

Assessment of Soft Computing Techniques for the Prediction of Compressive Strength of Bacterial Concrete.

In this investigation, the potential of M5P, Random Tree (RT), Reduced Error Pruning Tree (REP Tree), Random Forest (RF), and Support Vector Regression (SVR) techniques have been evaluated and compared with the multiple linear regression-based model (MLR) to be used for prediction of the compressive strength of bacterial concrete. For this purpose, 128 experimental observations have been collected. The total data set has been divided into two segments such as training (87 observations) and testing (41 observations). The process of data set separation was arbitrary. Cement, Aggregate, Sand, Water to Cement Ratio, Curing time, Percentage of Bacteria, and type of sand were the input variables, whereas the compressive strength of bacterial concrete has been considered as the final target. Seven performance evaluation indices such as Correlation Coefficient (CC), Coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Bias, Nash-Sutcliffe Efficiency (NSE), and Scatter Index (SI) have been used to evaluate the performance of the developed models. Outcomes of performance evaluation indices recommend that the Polynomial kernel function based SVR model works better than other developed models with CC values as 0.9919, 0.9901, R2 values as 0.9839, 0.9803, NSE values as 0.9832, 0.9800, and lower values of RMSE are 1.5680, 1.9384, MAE is 0.7854, 1.5155, Bias are 0.2353, 0.1350 and SI are 0.0347, 0.0414 for training and testing stages, respectively. The sensitivity investigation shows that the curing time (T) is the vital input variable affecting the prediction of the compressive strength of bacterial concrete, using this data set.

Predicting the Mechanical Properties of RCA-Based Concrete Using Supervised Machine Learning Algorithms.

Environment-friendly concrete is gaining popularity these days because it consumes less energy and causes less damage to the environment. Rapid increases in the population and demand for construction throughout the world lead to a significant deterioration or reduction in natural resources. Meanwhile, construction waste continues to grow at a high rate as older buildings are destroyed and demolished. As a result, the use of recycled materials may contribute to improving the quality of life and preventing environmental damage. Additionally, the application of recycled coarse aggregate (RCA) in concrete is essential for minimizing environmental issues. The compressive strength (CS) and splitting tensile strength (STS) of concrete containing RCA are predicted in this article using decision tree (DT) and AdaBoost machine learning (ML) techniques. A total of 344 data points with nine input variables (water, cement, fine aggregate, natural coarse aggregate, RCA, superplasticizers, water absorption of RCA and maximum size of RCA, density of RCA) were used to run the models. The data was validated using k-fold cross-validation and the coefficient correlation coefficient (R2), mean square error (MSE), mean absolute error (MAE), and root mean square error values (RMSE). However, the model's performance was assessed using statistical checks. Additionally, sensitivity analysis was used to determine the impact of each variable on the forecasting of mechanical properties.

Development of Prediction Model to Predict the Compressive Strength of Eco-Friendly Concrete Using Multivariate Polynomial Regression Combined with Stepwise Method.

Concrete is the most widely used building material, but it is also a recognized pollutant, causing significant issues for sustainability in terms of resource depletion, energy use, and greenhouse gas emissions. As a result, efforts should be concentrated on reducing concrete's environmental consequences in order to increase its long-term viability. In order to design environmentally friendly concrete mixtures, this research intended to create a prediction model for the compressive strength of those mixtures. The concrete mixtures that were used in this study to build our proposed prediction model are concrete mixtures that contain both recycled aggregate concrete (RAC) and ground granulated blast-furnace slag (GGBFS). A white-box machine learning model known as multivariate polynomial regression (MPR) was developed to predict the compressive strength of eco-friendly concrete. The model was compared with the other two machine learning models, where one is also a white-box machine learning model, namely linear regression (LR), and the other is the black-box machine learning model, which is a support vector machine (SVM). The newly suggested model shows robust estimation capabilities and outperforms the other two models in terms of R2 (coefficient of determination) and RMSE (root mean absolute error) measurements.

Effects of Small Deviations in Fiber Orientation on Compressive Characteristics of Plain Concrete Cylinders Confined with FRP Laminates.

The effectiveness of concrete confinement by fiber-reinforced polymer (FRP) materials is highly influenced by the orientation of fibers in the FRP laminates. In general, acceptable deviation limit from the intended direction is given as 5° in most design guidelines, without solid bases and reasoning. In this paper, a numerical study using finite element modeling was conducted to assess the effects of small deviations in fiber orientation from the hoop direction on compressive behavior of concrete cylinders confined with FRP. Different fiber angles of 0°, 2°, 5°, 8°, 10° and 15° with respect to hoop direction, unconfined concrete compressive strengths of 20, 35 and 50 MPa, FRP thicknesses of 0.2, 0.5 and 1.0 mm and FRP moduli of elasticity of 50 and 200 GPa were considered. The results showed that total dissipated energy (Et), ultimate axial strain (εcu') and compressive strength (fcu') exhibited the most reduction with deviation angle. For 5° deviation in fiber orientation, the average reduction in fcu', εcu' and Et were 2.4%, 2.8% and 4.5%, respectively. Furthermore, the calculated allowable limit of deviation in fiber orientation for a 2.5% reduction in fcu', εcu' and Et were 6°, 3° and 2°, respectively, with a 95% confidence.

Effect of Carbon Black and Hybrid Steel-Polypropylene Fiber on the Mechanical and Self-Sensing Characteristics of Concrete Considering Different Coarse Aggregates' Sizes.

The effect of combining filler (carbon black) and fibrous materials (steel fiber and polypropylene fiber) with various sizes of coarse particles on the post-cracking behavior of conductive concrete was investigated in this study. Steel fibers (SF) and carbon black (CB) were added as monophasic, diphasic, and triphasic materials in the concrete to enhance the conductive properties of reinforced concrete. Polypropylene fiber (PP) was also added to steel fiber and carbon to improve the post-cracking behavior of concrete beams. This research mainly focused on the effects of macro fibers on toughness parameters and energy absorption capacity, as well as enhancing the self-sensing of multiple cracks and post-cracking behavior. Fractional changes in resistance and crack opening displacement (COD-FCR) and the relationship of load-deflection-FCR with different coarse aggregates of (5-10 mm and 15-20 mm) sizes were investigated, and the law of resistance signal changes with single and multiple cracking through load-time-FCR curves was explored. Results indicated that the smaller size coarse aggregates (5-10 mm) showed higher compressive strength: up to 8.3% and 14.83% with diphasic (SF + CB), respectively. The flexural strength of PC-10 increased 22.60 and 51.2%, respectively, with and without fibers, compared to PC-20. The diphasic and triphasic conductive material with the smaller size of aggregates (5-10 mm) increased the FCR values up to 38.95% and 42.21%, respectively, as compared to those of greater size coarse aggregates (15-20 mm). The hybrid uses of fibrous and filler materials improved post-cracking behavior as well as the self-sensing ability of reinforced concrete.

Computation of High-Performance Concrete Compressive Strength Using Standalone and Ensembled Machine Learning Techniques.

The current trend in modern research revolves around novel techniques that can predict the characteristics of materials without consuming time, effort, and experimental costs. The adaptation of machine learning techniques to compute the various properties of materials is gaining more attention. This study aims to use both standalone and ensemble machine learning techniques to forecast the 28-day compressive strength of high-performance concrete. One standalone technique (support vector regression (SVR)) and two ensemble techniques (AdaBoost and random forest) were applied for this purpose. To validate the performance of each technique, coefficient of determination (R2), statistical, and k-fold cross-validation checks were used. Additionally, the contribution of input parameters towards the prediction of results was determined by applying sensitivity analysis. It was proven that all the techniques employed showed improved performance in predicting the outcomes. The random forest model was the most accurate, with an R2 value of 0.93, compared to the support vector regression and AdaBoost models, with R2 values of 0.83 and 0.90, respectively. In addition, statistical and k-fold cross-validation checks validated the random forest model as the best performer based on lower error values. However, the prediction performance of the support vector regression and AdaBoost models was also within an acceptable range. This shows that novel machine learning techniques can be used to predict the mechanical properties of high-performance concrete.

Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms.

The innovation of geopolymer concrete (GPC) plays a vital role not only in reducing the environmental threat but also as an exceptional material for sustainable development. The application of supervised machine learning (ML) algorithms to forecast the mechanical properties of concrete also has a significant role in developing the innovative environment in the field of civil engineering. This study was based on the use of the artificial neural network (ANN), boosting, and AdaBoost ML approaches, based on the python coding to predict the compressive strength (CS) of high calcium fly-ash-based GPC. The performance comparison of both the employed techniques in terms of prediction reveals that the ensemble ML approaches, AdaBoost, and boosting were more effective than the individual ML technique (ANN). The boosting indicates the highest value of R2 equals 0.96, and AdaBoost gives 0.93, while the ANN model was less accurate, indicating the coefficient of determination value equals 0.87. The lesser values of the errors, MAE, MSE, and RMSE of the boosting technique give 1.69 MPa, 4.16 MPa, and 2.04 MPa, respectively, indicating the high accuracy of the boosting algorithm. However, the statistical check of the errors (MAE, MSE, RMSE) and k-fold cross-validation method confirms the high precision of the boosting technique. In addition, the sensitivity analysis was also introduced to evaluate the contribution level of the input parameters towards the prediction of CS of GPC. The better accuracy can be achieved by incorporating other ensemble ML techniques such as AdaBoost, bagging, and gradient boosting.

Application of Advanced Machine Learning Approaches to Predict the Compressive Strength of Concrete Containing Supplementary Cementitious Materials.

The casting and testing specimens for determining the mechanical properties of concrete is a time-consuming activity. This study employed supervised machine learning techniques, bagging, AdaBoost, gene expression programming, and decision tree to estimate the compressive strength of concrete containing supplementary cementitious materials (fly ash and blast furnace slag). The performance of the models was compared and assessed using the coefficient of determination (R2), mean absolute error, mean square error, and root mean square error. The performance of the model was further validated using the k-fold cross-validation approach. Compared to the other employed approaches, the bagging model was more effective in predicting results, with an R2 value of 0.92. A sensitivity analysis was also prepared to determine the level of contribution of each parameter utilized to run the models. The use of machine learning (ML) techniques to predict the mechanical properties of concrete will be beneficial to the field of civil engineering because it will save time, effort, and resources. The proposed techniques are efficient to forecast the strength properties of concrete containing supplementary cementitious materials (SCM) and pave the way towards the intelligent design of concrete elements and structures.

A Comparative Study for the Prediction of the Compressive Strength of Self-Compacting Concrete Modified with Fly Ash.

Artificial intelligence and machine learning are employed in creating functions for the prediction of self-compacting concrete (SCC) strength based on input variables proportion as cement replacement. SCC incorporating waste material has been used in learning approaches. Artificial neural network (ANN) support vector machine (SVM) and gene expression programming (GEP) consisting of 300 datasets have been utilized in the model to foresee the mechanical property of SCC. Data used in modeling consist of several input parameters such as cement, water-binder ratio, coarse aggregate, fine aggregate, and fly ash (FA) in combination with the superplasticizer. The best predictive models were selected based on the coefficient of determination (R2) results and model validation. Empirical relation with mathematical expression has been proposed using ANN, SVM, and GEP. The efficiency of the models is assessed by permutation features importance, statistical analysis, and comparison between regression models. The results reveal that the proposed machine learning models achieved adamant accuracy and has elucidated performance in the prediction aspect.

Comparative Study of Supervised Machine Learning Algorithms for Predicting the Compressive Strength of Concrete at High Temperature.

High temperature severely affects the nature of the ingredients used to produce concrete, which in turn reduces the strength properties of the concrete. It is a difficult and time-consuming task to achieve the desired compressive strength of concrete. However, the application of supervised machine learning (ML) approaches makes it possible to initially predict the targeted result with high accuracy. This study presents the use of a decision tree (DT), an artificial neural network (ANN), bagging, and gradient boosting (GB) to forecast the compressive strength of concrete at high temperatures on the basis of 207 data points. Python coding in Anaconda navigator software was used to run the selected models. The software requires information regarding both the input variables and the output parameter. A total of nine input parameters (water, cement, coarse aggregate, fine aggregate, fly ash, superplasticizers, silica fume, nano silica, and temperature) were incorporated as the input, while one variable (compressive strength) was selected as the output. The performance of the employed ML algorithms was evaluated with regards to statistical indicators, including the coefficient correlation (R2), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). Individual models using DT and ANN gave R2 equal to 0.83 and 0.82, respectively, while the use of the ensemble algorithm and gradient boosting gave R2 of 0.90 and 0.88, respectively. This indicates a strong correlation between the actual and predicted outcomes. The k-fold cross-validation, coefficient correlation (R2), and lesser errors (MAE, MSE, and RMSE) showed better performance than the ensemble algorithms. Sensitivity analyses were also conducted in order to check the contribution of each input variable. It has been shown that the use of the ensemble machine learning algorithm would enhance the performance level of the model.

Analyzing the Compressive Strength of Ceramic Waste-Based Concrete Using Experiment and Artificial Neural Network (ANN) Approach.

In a fast-growing population of the world and regarding meeting consumer's requirements, solid waste landfills will continue receiving a substantial amount of waste. The utilization of solid waste materials in concrete has gained the attention of the researchers. Ceramic waste powder (CWP) is considered to be one of the most harmful wastes for the environment, which may cause water, soil, and air pollution. The aim of this study was comprised of two phases. Phase one was based on the characterization of CWP with respect to its composition, material testing (coarse aggregate, fine aggregate, cement,) and evaluation of concrete properties both in fresh and hardened states (slump, 28 days compressive strength, and dry density). Concrete mixes were prepared in order to evaluate the compressive strength (CS) of the control mix, with partial replacement of the cement with CWP of 10 and 20% by mass of cement and 60 prepared mixes. However, phase two was based on the application of the artificial neural network (ANN) and decision tree (DT) approaches, which were used to predict the CS of concrete. The linear coefficient correlation (R2) value from the ANN model indicates better performance of the model. Moreover, the statistical check and k-fold cross validation methods were also applied for the performance confirmation of the model. The mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were evaluated to confirm the model's precision.

An Experimental and Empirical Study on the Use of Waste Marble Powder in Construction Material.

Marble is currently a commonly used material in the building industry, and environmental degradation is an inevitable consequence of its use. Marble waste occurs during the exploitation of deposits using shooting technologies. The obtained elements most mainly often have an irregular geometry and small dimensions, which excludes their use in the stone industry. There is no systematic way of disposing of these massive mounds of waste, which results in the occurrence of landfills and environmental pollution. To mitigate this problem, an effort was made to incorporate waste marble powder into clay bricks. Different percentage proportions of marble powder were considered as a partial substitute for clay, i.e., 5-30%. A total of 105 samples were prepared in order to assess the performance of the prepared marble clay bricks, i.e., their water absorption, bulk density, apparent porosity, salt resistance, and compressive strength. The obtained bricks were 1.3-19.9% lighter than conventional bricks. The bricks with the addition of 5-20% of marble powder had an adequate compressive strength with regards to the values required by international standards. Their compressive strength and bulk density decreased, while their water absorption capacity and porosity improved with an increased content of marble powder. The obtained empirical equations showed good agreement with the experimental results. The use of waste marble powder in the construction industry not only lowers project costs, but also reduces the likelihood of soil erosion and water contamination. This can be seen to be a crucial factor for economic growth in agricultural production.

The Influence of CFRP Sheets on the Load-Bearing Capacity of the Glued Laminated Timber Beams under Bending Test.

Composite materials are increasingly used to strengthen existing structures or new load-bearing elements, also made of timber. In this paper, the effect of the number of layers of Carbon Fiber Reinforced Polymer (CFRP) on the load-bearing capacity and stiffness of Glued Laminated Timber beams was determined. Experimental research was performed on 32 elements-a series of eight unreinforced beams, and three series of eight reinforced beams: with one, three and five layers of laminate each. The beams with a cross-section of 38 mm × 80 mm and a length of 750 mm were subjected to the four-point bending test according to standard procedure. For each series, destructive force, deflection, mode of failure, and equivalent stiffness were determined. In addition, for the selected samples, X-ray computed tomography was performed before and after their destruction to define the quality of the interface between wood and composite. The results of the conducted tests and analyses showed that there was no clear relationship between the number of reinforcement layers and the load-bearing capacity of the beams and their stiffness. Unreinforced beams failed due to tension, while reinforced CFRP beams failed due to shear. Despite this, a higher energy of failure of composite-reinforced elements was demonstrated in relation to the reference beams.

Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste Material.

Structures located on the coast are subjected to the long-term influence of chloride ions, which cause the corrosion of steel reinforcements in concrete elements. This corrosion severely affects the performance of the elements and may shorten the lifespan of an entire structure. Even though experimental activities in laboratories might be a solution, they may also be problematic due to time and costs. Thus, the application of individual machine learning (ML) techniques has been investigated to predict surface chloride concentrations (Cc) in marine structures. For this purpose, the values of Cc in tidal, splash, and submerged zones were collected from an extensive literature survey and incorporated into the article. Gene expression programming (GEP), the decision tree (DT), and an artificial neural network (ANN) were used to predict the surface chloride concentrations, and the most accurate algorithm was then selected. The GEP model was the most accurate when compared to ANN and DT, which was confirmed by the high accuracy level of the K-fold cross-validation and linear correlation coefficient (R2), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) parameters. As is shown in the article, the proposed method is an effective and accurate way to predict the surface chloride concentration without the inconveniences of laboratory tests.