Synergizing machine learning and experimental analysis to predict post‐heating compressive strength in waste concrete

Commonly used concrete is made from a mixture of fine aggregate (sand), coarse aggregate (gravel), cement, and water. These constituent materials come from nature and have been processed and selected according to their needs. As time passes, the widespread use of concrete as a construction material can disrupt the balance of the surrounding environment, given the reduction in the ingredients of concrete available in nature. Therefore, we need an innovation that can be a choice in using concrete without destroying our natural resources, usually called Green Concrete or Eco Green Concrete. In other words, the level in this research is an appropriate technology for replacing building materials. The problem is how much influence the percentage of glass bottle powder, ceramic powder, and granite powder waste has in achieving the slump test value and the planned increase in compressive strength. Know the compressive strength of concrete using added Lokagrmic waste (glass bottle powder, ceramic powder waste, and granite powder waste).

The comparative analysis of predictive methodologies highlights the original contribution of this study in optimizing the prediction of Rate of Penetration (ROP) in mining drilling operations. The emphasis on employing advanced Artificial Neural Networks (ANN), fuzzy logic, and linear regression models provides new insights into enhancing predictive accuracy and operational efficiency in mining practices. This study aims to quantify the effects of three pivotal drilling parameters: compressive strength, rotational pressure, and thrust pressure on the rate of penetration, a critical performance metric in mining drilling operations. Additionally, the study seeks to develop and evaluate advanced predictive methodologies for predicting ROP. The effects of compressive strength, rotational pressure, and thrust pressure on the rate of penetration were investigated through a Design of Experiments (DOE) approach. Initially, the main effects and two-way interactions among these variables were identified using DOE. Subsequently, three predictive methodologies: linear regression, fuzzy logic, and artificial neural networks, were developed and evaluated to predict ROP based on the identified factors. The evaluation of predictive methodologies revealed that the ANN model demonstrated superior accuracy in predicting the ROP, achieving over 95 % accuracy. Additionally, the fuzzy logic model provided effective handling of nonlinearities in the data, while the linear regression model offered initial insights into the relationships between the variables. The application of advanced predictive methodologies: artificial neural networks, fuzzy logic, and linear regression to optimize the prediction of rate of penetration in mining drilling operations offers precise insights into drilling parameter interactions, enhancing operational efficiency and supporting informed decision making in mining practices.

ABSTRACTThis study presents a novel approach to optimize and predict the mechanical properties of 3D‐printed polylactic acid (PLA)/wood composites through artificial neural network (ANN) and fuzzy logic (FL) modeling. The research addresses the critical challenge of determining optimal process parameters in fused deposition modeling (FDM) of natural fiber composites. Using Taguchi's L27 orthogonal array, experiments were conducted with five key printing parameters: layer thickness (100–200–300 μm), printing speed (PS) (40–60–90 mm/s), raster angle (RA) (0°–45°–90°), infill density (ID) (30%–60%–90%), and nozzle temperature (NT) (190°C–200°C–210°C). Analysis revealed that RA and PS were the most influential parameters, contributing 41.86% and 40.92% to tensile and compressive strengths, respectively. The developed ANN model demonstrated exceptional prediction accuracy with R2 values of 99.94% for both tensile and compressive strengths, surpassing the FL model's performance (R2 = 97.16%). The development of these models is crucial for accurately predicting mechanical behavior, allowing for efficient process optimization without extensive physical testing. Both methods demonstrated high prediction accuracy. Validation tests revealed that maximum errors of 1.95% and 2.81% for ANN and FL, respectively. The findings contribute valuable insights for the development of high‐performance natural fiber composites and establish a foundation for future advanced manufacturing processes.

This study aimed to fabricate a Fuzzy Logic (FL) model based on dye, salt, and alkali concentrations to predict the color properties of pineapple leaf fiber (PALF) fabric dyed with reactive dyes. The nonlinear and interactive nature of these factors makes it challenging to make an exact model using mathematical or statistical methods. Additionally, artificial neural networks and neuro-fuzzy models require extensive trial data for parameter optimization, which is often difficult to obtain from dyeing industries. In this context, FL is an effective modeling tool, capable of handling nonlinear complex domains with minimal trial data. The test data confirmed the model established in this study, showing a mean absolute error (MAE) for all parameters within the acceptable range (<5%) and coefficients of determination (R²) exceeding 0.96. It is concluded that the FL model is efficient in the prediction of color properties of PALF fabric in nonlinear complex dyeing with high accuracy. Journal of Engineering Science 15(2), 2024, 13-27

In the present work, fuzzy logic (FL) has been used to model the performance of a batch reactor system and, hence, the conversion profile at varying operating conditions. The transient temperature vs. time data of exothermic reaction was taken from open literature [1] for modelling with FL. The FL model with properly chosen fuzzy sets, type of membership function and rule base relate time with temperature very well in the reactor under experimental condition. The simulated result through FL model was compared with experimental findings, mathematical model and artificial neural network (ANN) model. The FL model predictions were found to be in very good agreement with experimental findings with average absolute error less than 1%.

This paper presents the effect of recycled coarse aggregate (RCA) of 50% and 100% by wt. on compressive strength and elastic modulus of concrete at elevated temperatures of 600 and 800 °C. The residual compressive strengths of above recycled aggregate concretes after exposure to elevated temperatures are also evaluated and compared to those measured during heating. The effect of polypropylene (PP) fibers on residual compressive strength and cracking behavior of above recycled aggregate concretes after exposure to elevated temperatures is also evaluated in this study. Results show that the loss of compressive strength of recycled aggregate concretes at 600 and 800 °C is slightly higher (about 10%) than its counterpart control concrete containing natural coarse aggregates. Concrete containing 100% RCA exhibited about 50% loss of its ambient temperature compressive strength at 800 °C, which is about 25% less in concrete containing 50% RCA. The residual compressive strength, which is measured after cooling of heated specimens, of both recycled aggregate concretes and control concrete is higher at both elevated temperatures. The measured elastic modulus of both recycled aggregate concretes show no significant reduction compared to their counterpart control concrete at both elevated temperatures. A strong correlation between elastic modulus and square root of compressive strength of recycled aggregate concretes is observed at elevated temperatures. The model proposed in Eurocode to predict the elevated temperature compressive strength and elastic modulus agrees well with the measured values for recycled aggregate concretes. The addition of PP fibers reduced the residual compressive strength of concrete containing 100% RCA at both temperatures with significant reduction at 800 °C. However, mixed results are obtained in the case of concrete containing 50% RCA. The cracking patterns of concrete containing RCA and those containing PP fibers also correlated well with the observed residual compressive strength results.

The control and disposal of solid waste pose significant global challenges, particularly in the management of waste granite powder (WGP), a by-product of granite processing industries. Addressing this issue, the present study investigates the potential of WGP as a partial substitute for fine aggregate in concrete, with replacement levels up to 50%. The research emphasizes the need for sustainable construction materials and explores the viability of using industrial waste to reduce environmental impact and resource depletion. Novel aspects of this study include the comprehensive evaluation of the physical and chemical characteristics of fine aggregate and WGP through X-ray diffraction (XRD) and X-ray fluorescence (XRF) analyses. The study also examines the fresh and mechanical properties of concrete, such as workability, compressive strength, flexural strength, ultrasonic pulse velocity (UPV), and modulus of elasticity to determine the optimum WGP substitution level. The findings reveal that mechanical strength improves with WGP replacement levels of up to 40%, highlighting the potential of WGP in enhancing concrete performance. Furthermore, correlations between different mechanical properties are analyzed, providing a deeper understanding of the behavior of WGP-blended concrete. In addition to technical evaluations, a detailed cost analysis is conducted to assess the economic feasibility of using WGP in concrete production. The results indicate that incorporating WGP not only offers environmental benefits by reducing waste but also provides a cost-effective alternative to traditional fine aggregate. Thus, substituting sand with WGP in concrete emerges as a sustainable solution, delivering comparable or superior mechanical properties while contributing to environmental conservation and cost reduction.

RETRACTED: The impact of GGBS and ferrous on the flow of electrical current and compressive strength of concrete

Supplementary cementitious materials have been proven to be effective partial cement replacements in concrete to reduce greenhouse gas emissions from the use of ordinary Portland cement. In this study, artificial neural network was used to arrive at a predictive model to assess their effects in the compressive strength of concrete. Collection of 991 datasets from published literatures was done for the development of the best network model with acceptable root mean square error for both training and testing datasets. The supplementary cementitious materials were ranked accordingly using the improved stepwise method and network simulation. From the results, ground granulated blast-furnace slag with 15% cement replacement and silica fume with 30% cement replacement contributed to the highest increase in compressive strength.

In this study, a fuzzy logic model was constituted by using the Fuzzy Logic (FL) method, which is one of the traditional artificial intelligence (AI) methods, in order to estimate the shear strength of reinforced concrete (RC) beams with limited ductility. In this model, beam width(bw), beam height(h), characteristic concrete compressive strength(fck), transverse reinforcement diameter(T), the number of arms bearing the shear force of the transverse reinforcement(n) and transverse reinforcement spacing(s) were taken into account as variable parameters. The model developed by using the problem data containing the solutions of shear force strength of 2640 beams with different cross-section properties were tested with 480 beam solutions different from these data. In the tests of the developed FL model, maximum percentage error, minimum percentage error, average percentage error and correlation coefficient values were obtained as 3.604, -0.091, 1.514 and R2=0.999678. By applying the fuzzy inverse logic method (FIL), which was recently developed by the author of this study, on the FL model, which is seen to have been developed quite sensitively from the test results, a total of 521 designs were obtained for 15 different RC beams with limited ductility subjected to shear. In order to check the accuracy of these designs, after shear strengths were obtained by conventional computations for these designs, % error and correlation coefficients were computed between the obtained strength values and the shear force values taken into account for the design. The promising results show that the FIL method can be used in the design of RC beams under shear force and even in other scientific studies such as design, optimization and control.

This study aims to investigate the influence of pozzolanic materials and waste products on the strength properties of self-compacting concrete (SCC). Specifically, the research uses calcined kaolin clay (CKC) and waste marble powder (WMP), as supplementary materials. The study examines various blending systems, including binary, and ternary mixtures. Test samples were prepared by manipulating the weights of cement components, incorporating CKC, and WMP at different proportions. Fresh properties, such as L-Box, segregation resistance, V-funnel resistance, and slump flow diameter, were evaluated. Hardened properties were assessed at three intervals: 7, 28, and 56 days. The optimal binary mixture demonstrated potential as a substitute for CKC, and WMP improving fresh results and enhancing compressive strength. Ternary blends exhibited higher compressive and tensile strengths. The results indicated that binary blended mixes with 10 % WMP showed enhanced compressive strengths compared to other combinations. Furthermore, the binary blend with 10 % WMP displayed superior compressive strengths at all ages compared to other combinations. Additionally, the ternary blends showcased higher compressive and tensile strengths values, reaching 61,8 MPa, and 4,49 MPa, respectively. The durability performance of the binary and ternary blends SCC is examined in terms of water absorption. In addition, the study successfully met its objectives by lowering the requirement for cement, lowering CO2 emissions, and improving the environmental impact of (SCC). These findings provide valuable insights for the construction industry, promoting the utilization of alternative materials in producing high-performance self-compacting concrete

Impact of thermal loads on silica fume-modified lightweight concrete: Machine learning approach to assess compressive strength evolution

Objective: Attempt is made to estimate the compressive strength of Reactive Powder Concrete (RPC) by developing Artificial Neural Network model. Methods/Analysis: RPC is a complex composite material made using a combination of constituent materials viz. fine quartz, silica fume and cement to form a cementitious matrix. Mix design for RPC is more complicated as it excludes the coarse aggregates and a low water/cement ratio is maintained. The mix proportioning methods applicable to normal concrete cannot be applied readily to RPC. The complexity in behavior of concrete with special constituents makes the mix design complicated. Artificial neural network (ANN) techniques can capture complex relations among input/output variables in a given system and this method has been implemented in Reactive Powder Concrete mix proportion design, for predicting its strength. Findings: This paper presents the development and application of ANN for predicting the strength of RPC using data related to 112 mix proportions and the results of the model are checked experimentally. Compressive strength of concrete is chosen as a function of the 'Water/Cement' ratio (w/c), 'Silica Fume/Cement' ratio (sf/c), and 'Quartz Sand/Cement' ratio (qs/c). The ANN model developed is tested for the 12 mix proportions randomly selected from experimental data for which the experimental compressive strengths were available. The compressive strength given by the model when compared with the experimental values showed an average error of only 3.99 %. Novelty/Improvement: The model developed has coefficient of determination R² equal to 0.9066 which indicates a significant enough correlation.

This article reviews the physical, chemical and microstructural properties of palm oil clinker (POC) and oil palm shell (OPS) by-products of palm oil. They are considerably used as lightweight aggregate to produce lightweight concrete so as to conserve the virgin resources and to reduce environmental contamination, whereby sustainability will be achieved. This paper is devoted to explaining the compressive strength behavior of concrete incorporating POC and OPS as lightweight aggregate. It is demonstrated that POC of size below 4.75 mm can be used as a partial fine aggregate replacement. Coarse POC sized 9–4.75 mm can be used as coarse aggregate substitution. POC powder (POCP) showed an improvement in compressive strength of concrete when used as filler. POCP treated at 850 °C showed a distinct increase in compressive strength when added as 30% by weight of cement. Previous studies have investigated the possibility of using OPS as the coarse aggregate replacement in concrete after following certain treatments. However, they have also documented a significant drop in compressive strength of concrete due to the smooth texture surface of the convex and concave of shells, hence weakening the bond between aggregate and mortar. Consequently, the compressive strength of concrete is reduced. On the contrary, coarse POC showed a compressive strength development when used as OPS substitution. Future studies should focus on OPS treatments to remove purities and develop bond strength in concrete. Future investigations should consider a broader usage of POC and OPS as lightweight aggregate in other applications like mortar, tiles, bricks and blocks. All in all, the usage of oil palm by-products as lightweight aggregate has recorded an accepted compressive strength for lightweight concrete.

Impact on mechanical properties of cement sand mortar containing waste granite powder