RSM Approach Research Articles

Heat transfer enhancement in cylindrical heat pipes with MgO-Al2O3 hybrid nanofluids in water-ethylene glycol mixture: An RSM approach

Heat pipes are passive devices crucial for thermal management in various applications. However, conventional water-based fluids can limit their heat transfer capacity, especially in cold environments where freeze protection is necessary. This study investigates the potential of MgO-Al2O3 hybrid nanofluids to enhance heat transfer performance in cylindrical mesh heat pipes while addressing these limitations. The research demonstrates significant improvements in thermal performance compared to a water-ethylene glycol mixture. The MgO-Al2O3 hybrid nanofluid reduces thermal resistance by enhancing surface wettability in the evaporator section. Additionally, the formation of a nanofluid coating on the evaporator surface leads to a higher heat transfer coefficient. Furthermore, RSM successfully models the relationship between nanoparticle concentration, power input, and key thermal responses (thermal resistance and heat transfer coefficient). These findings highlight the effectiveness of MgO-Al2O3 hybrid nanofluids for augmenting heat transfer in heat pipes and provide valuable RSM models for predicting thermal behavior within the investigated range.

RGO@SnO2/ZnO nanocomposite as a highly reactive heterogeneous catalyst toward biodiesel synthesis by electrolysis procedure: Central composite design optimization

This paper highlights the incorporation of catalyst choice, feedstock type, and production technique for biodiesel production, thereby addressing existing gaps in the current research. In this sense, the rGO@SnO2/ZnO nanocomposite as a novel heterogeneous catalyst was prepared and employed to generate biodiesel from waste frying oil (WFO) by electrolysis approach for the first time. The structural attributes of rGO@SnO2/ZnO nanocatalyst were evaluated by several analyses. According to these analyses, rGO@SnO2/ZnO nanocomposite has a specific area of 61.428 g/m2 and appropriate functional groups. Additionally, a CCD-based RSM approach was employed for achieving the highest biodiesel yield in optimal conditions (MeOH/WFO molar proportion=12:1, reaction time= 40 min, voltage=40 V, and catalyst concentration= 3.5 wt%) was 96.47 %. Likewise, the yield of biodiesel decreased from 96.58 % to 88.36 % after seven reuse cycles, which reveals the substantial stability of rGO@SnO2/ZnO nanocomposite in the transesterification procedure. Moreover, the thermodynamic behavior of biodiesel synthesis indicated that the transesterification employing rGO@SnO2/ZnO nanocomposite is endothermic. The activation energy and Arrhenius factor for the transesterification of WFO to biodiesel utilizing rGO@SnO2/ZnO nanocatalysts were determined to be 51.59 kJ/mol and 6.67×105 min−1, respectively. Due to the high biodiesel yield and remarkable reusability, rGO@SnO2/ZnO nanocomposite is strongly recommended for the transesterification procedure.

The Optimization of Avocado-Seed-Starch-Based Degradable Plastic Synthesis with a Polylactic Acid (PLA) Blend Using Response Surface Methodology (RSM).

This research improves the strength of plastic using avocado seed starch and PLA. The effect of blending avocado seed starch and PLA was optimized using the RSM approach by using two variables: water absorption and biodegradability. Mixing them using RSM gave the best result: 1.8 g of starch and 3 g of PLA. Degradable plastic has a tensile strength of 10.1 MPa, elongation at a break of 85.8%, and a Young's modulus of 190 MPa. Infrared spectroscopy showed that the plastic had a -OH bond at 3273.20 cm-1, 3502.73 cm-1, and 3647.39 cm-1, a CH2 bond at 2953.52 cm-1, 2945.30 cm-1, and 2902.87 cm-1, a C=C bond at 1631.78 cm-1, and a C-O bond at 1741.72 cm-1. The plastic decomposed in the soil. It was organic and hydrophilic. Thermal tests demonstrated that the plastic can withstand heat well, losing weight at 356.86 °C to 413.64 °C, forming crystals and plastic melts at 159.10 °C-the same as PLA. In the melt flow test, the sample melted before measurement, and was therefore not measurable-process conditions affected it. A water absorption of 5.763% and biodegradation rate of 37.988% were found when the samples were decomposed for 12 days. The starch and PLA fused in the morphology analysis to form a smooth surface. The RSM value was close to 1. The RSM gave the best process parameters.

Multiobjective Optimization on Grave Properties of Mixed Transformer Oil Using RSM and NSGA-II Approach

Multiobjective Optimization on Grave Properties of Mixed Transformer Oil Using RSM and NSGA-II Approach

Identification of influential parameters and conditions in heavy metals adsorption onto Cal-LDH-PC using optimization approaches of RSM and Taguchi

Adsorption process plays an important role in the remediation of heavy metals (HMs) from wastewater. A laboratory trial was conducted to investigate effective parameters for improving the bio-adsorption removal of HMs. SEM, EDX, BET, and FTIR techniques were applied to characterize the calcined layer double hydroxide (Cal-LDH), pectin (PC), and Cal-LDH-PC composite prepared from Licorice pomace. The adsorption of zinc (Zn) cadmium, nickel (Ni) and lead (Pb) onto the most efficient sorbent was investigated using RSM methodology with operational factors such as concentration, reaction time, sorbent dose, and pH. The results related to FTIR showed that Cal-LDH-PC had the highest number of functional groups. Based on the SEM results Cal-LDH had a low surface area (9.36 m2 g-1) and a small pore size (9.22 nm). After the modification process (Cal-LDH-PC), the values of surface area and pore size increased by 13-fold (120 m2 g-1) and 1.5-fold (18 nm), respectively. Cal-LDH had high adsorption performance, more cavities, stability, various functional groups, and excessive carbon and oxygen content, which make it efficient and powerful in removing HMs from wastewater. The optimal condition for achieving the removal efficiency (RE%) values of metals was determined to be 80.79 mg L−1, 100 min, 0.167 g L−1, and 9 for concentration, reaction time, sorbent dose, and pH, respectively. Maximum adsorption capacity and RE (%) were 300 mg g−1 and 99% for Zn. According to the results concentration had a major impact on RE% (except for Ni), while for Ni, adsorbent dose had the most significant impact. The present study introduced Cal-LDH-PC prepared from Licorice pomace as a capable, useful and economical sorbent for HMs removal from polluted environments. Taguchi's statistical method is distinguished as an economic method with easier interpretation, while the RSM approach is more accurate, and it can also check the interaction of parameters.

Desirability analysis of sustainable concrete containing fly ash cenosphere as fine aggregate replacement using RSM approach

Desirability analysis of sustainable concrete containing fly ash cenosphere as fine aggregate replacement using RSM approach

Sustainable Phosphate Recovery as Hydroxyapatite from the Secondary Treated Industrial b-Effluents: Statistical RSM Approach

Sustainable Phosphate Recovery as Hydroxyapatite from the Secondary Treated Industrial b-Effluents: Statistical RSM Approach

Sustainable energy enhancement strategy from Chlorella vulgaris microalgae biomass resource

ABSTRACT Growing demand for renewable and sustainable energy sources has prompted research into bioethanol production as a viable alternative to hydrocarbon fuel for automobile engines. Based on their high carbohydrate content, Chlorella vulgaris microalgae were chosen for this study as a feasible biomass for bioethanol synthesis. After conducting microwave-based acid hydrolysis with varying acid concentrations of sulfuric acid (H2SO4) for 1–15 min, this study found that 3% H2SO4 for 5 min yielded the highest yield of reducing sugar (6.77 g/L). In this work, the RSM approach of central composite design (CCD) was utilized for modeling and optimization of ethanol fermentation and the MATLAB Simulink approach was employed for the simulation of ethanol fermentation. This study compared the effects of using Saccharomyces cerevisiae yeast for fermentation at different fermentation times (12 to 48 h), temperatures (28 to 32°C), and size of inoculum (0.5–1.5 g/L). Based on the actual and predicted results, the best conditions for fermentation were 36 h of time, 30°C of temperature, and 1.5 g/L of inoculum size. This gave the maximum ethanol concentration of 3.31 g/L. Furthermore, the RSM method provides minimum error and maximum R2 value results for ethanol production compared to MATLAB simulation prediction (MSP). In addition, residue biomass from biofuel production is evaluated for its suitability for a further form of biofuel production. This research explores the opportunities for zero-waste biomass utilization in the development of biofuels.

Optimization of design and fuel parameters of a DI CI engine through desirability function and RSM for lower emissions and clean environment

In the present investigation an attempt was made to control the NOx and smoke emission of a DI CI engine by simultaneously varying design and fuel factors of the engine. Four design factors and four fuel factors with three levels were chosen and test matrix were designed as per L18 orthogonal array. Experiments were conducted with different combinations of chosen design and fuel factors as per the designed test matrix and the responses (NOx, smoke and brake specific fuel consumption (BSFC)) were recorded for 18trials. Significance and interaction of the tested factors were obtained through analysis of variance technique. Desirability function through RSM approach was employed to investigate the optimum combination of tested factor levels for lower NOx, smoke and BSFC. At optimum level of factors both NOx and smoke emissions of the engine was reduced without any increase in its BSFC. This investigation reveals that combination of fuel and design factors have the ability to reduce the NOx and smoke simultaneously without any compromise on engine performance.

Application of response surface methodology and neural networks in pyramid solar still for seawater desalination: An optimization and prediction strategy

<p>Potable water is essential in various aspects of daily life. Converting brackish water to drinkable water using traditional methods is costly and has environmental impacts. Solar energy is preferred over fossil fuels and other energy sources due to its cost and environmental benefits. Solar stills are increasingly popular due to the growing need for drinkable water, but their performance requires improvement. The study examines the pyramid solar still (PSS) productivity using different operating parameters, such as solar intensity (350-950 W/m2), water inlet temperature (30-50°C), water depth (4-8 cm), and insulation thickness (0.05-0.15m). The response surface technique (RSM) was used to examine the performance of the still under different operating conditions. The RSM approach optimized the process for maximum output and reduced testing time and effort. To verify the optimum response derived from RSM, the artificial neural networks (ANN) model was implemented. The comparative studies of the ANN and RSM models demonstrates a strong correlation with the outcomes achieved in maximizing the productivity of PSS. It found that the ideal values for solar intensity, water intake temperature, water depth, and insulation thickness are 950 W/m2, 50°C, 4 cm, and 0.15 m, respectively. These parameters contribute to the production of 2.585 kg/m2 of distillate.</p>

Parametric study of WEDM of titanium grade 12 using RSM and desirability approach

The present experimental study aims to scrutinize the effect of different process parameters on the material removal rate (MRR) and surface roughness (SR) of titanium grade 12 alloy during wire electro-discharge machining (WEDM) using response surface methodology. Four parameters (pulse-on time, pulse-off time, wire feed and gap voltage) and three levels of each selected variable are considered to conduct the experimental work. Depending on experimental results, a mathematical model is generated for both MRR and SR. An analysis of variance (Anova) study is performed to find significant process parameters. The Anova results show that the developed models for both MRR and SR are significant, and pulse-on time is found to be the most significant parameter. Additionally, the desirability approach is used to scrutinize the single-objective and multi-objective criteria of response variables. The desirability functions for all of the cases are found to be 1. The maximum MRR is observed to be 12.4845 mm3/s, while the minimum value of SR is found to be 1.4911 μm. For multi-objective optimization, the maximum value of MRR and the minimum value of SR are obtained as 12.0942 mm3/min and 1.7167 μm, respectively. Finally, the surface morphology of the machined surfaces is examined using scanning electron microscopy micrographs.

Investigation on the influence of FSP parameters on TIG welded dissimilar aluminum joints using RSM and desirability function approach

The present study aimed to explore the cumulative influence of friction stir processing (FSP) parameters, viz., tool spindle speed, traverse speed, and tool tilt angle, on the ultimate tensile strength (TS), ultimate flexural strength (FS), microhardness (MH), and wear rate (WR) of tungsten inert gas (TIG) welded dissimilar AA6061-T6 and AA7075-T6 alloy joints. A face-cantered central composite design (FCCCD) of response surface methodology (RSM) was adopted to design the experiments. Analysis of variance (ANOVA) was employed to identify the significant factors and interaction effects. Multi-response optimization was performed using the desirability function approach to identify parameters that maximize TS, FS, and MH and minimize WR. A confirmation study under optimal conditions were also carried out. FSP significantly improved the TIG joint properties by producing more homogeneous and refined grains (average grain size of 7.75 µm) without any weld defects. The TS, FS, and MH of TIG welds have increased by 66.87%, 61.95%, and 69.01%, respectively, while the WR decreased by 37.87% after FSP. The fractography revealed that TIG welds lead to a brittle failure mode, and the FSP + TIG welds showed a ductile failure mode. The tool spindle speed was the most influential factor affecting joint properties. With increased spindle speed, the TS, FS, and MH of the joint increased, while the WR decreased. At a spindle speed of 1300 rpm, a traverse speed of 50.75 mm/min, and a tilt angle of 1.76°, the optimum TS of 271.89 MPa, the FS of 298.03 MPa, the MH of 122.23 HV, and the WR of 77.48 µm were observed.

Optimization of performance and emission characteristics of liquid fuel fired porous medium burner using RSM and desirability approach

ABSTRACT The porous medium combustion (PMC) is an emerging area in liquid fuel combustion, which has the ability to reduce emission and increase the fuel economy. Various operational parameters will affect the performance of liquid fuel-fired Porous Medium Burner (PMB). So, this present work focuses on finding the effect of operational parameters on the performance of PMB and to optimize it. This study was conducted in a double-layered porous burner with self-aspirated pressurized stove. Three input factors were selected, namely, fuel pressure (bar), throttle angle (°), and type of burner (Conventional burner (CB), PMB). The three output responses selected are thermal efficiency (ηth), CO (ppm), and NOX (ppm) emissions. The inscribed central composite design (ICCD) was used to design the experimental run. The response surface methodology (RSM) with desirability approach was used to optimize the multi-objective responses. The statistical analysis with ANOVA confirmed the significance of all the three input variables on the output responses. The regression model was developed with quadratic fit and it well predicts the burner performance and emission with R2 value close to 1. The multi-objective optimum input settings are found by desirability approach, i.e. fuel pressure = 1.60 bar, throttle angle = 161.3°, and burner type = PMB. The corresponding optimized responses are found as ηth = 58.39%, CO = 201. 49 ppm, and NOX = 6.43 ppm. The above optimum settings and responses are confirmed with experimental confirmation test, which is in the satisfactory level.

Parametric analysis of wastewater electrolysis for green hydrogen production: A combined RSM, genetic algorithm, and particle swarm optimization approach

The production of green hydrogen from wastewater presents a significant opportunity to address environmental challenges associated with wastewater treatment and fulfill the increasing demand for renewable and sustainable energy sources. This study aimed to determine the optimal operating parameters for maximizing hydrogen production through wastewater electrolysis. To design the experimental runs, a Box-Behnken design (BBD) with an L17 array was implemented, while Response Surface Methodology (RSM) in conjunction with Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) was employed to develop predictive models and optimize the operating parameters. The operating parameters considered were the catalyst amount (g), electrode voltage (V), and electrolysis time (min), and the response variable was the oxyhydrogen (HHO) gas generation rate (L/min). The comparative analysis shows that the optimized parameters obtained through RSM surpassed those obtained through GA and PSO, with a catalyst amount of 99.42 g, an electrode voltage of 22.9 V, and an electrolysis time of 23.17 min. Consequently, the HHO generation rate reached a maximum value of 12.42 L/min. Furthermore, the experimental validation indicated a close agreement between the model's predicted results and the actual experimental outcomes. This study shows the effectiveness of combining RSM, GA, and PSO for accurate prediction and optimization of operating parameters in wastewater electrolysis for green hydrogen production. The identified optimal conditions contribute to enhanced efficiency and increased hydrogen yield, thereby promoting the advancement of sustainable energy systems.

Anaerobic co-digestion of human excreta, food leftovers and kitchen residue: 1 ternary mixture design, synergistic effects and RSM approach

Anaerobic digestion of multiple substrates can generate more biogas while remaining stable, if positive synergistic effects are achieved. The type of co-digested substrates and the mixing ratio used, are the most important variables as each substrate has unique set of characteristics. Optimizing the volume ratios by testing various substrate mixing ratios is a popular method for determining the best-performing ratio of substrate mixture. The ternary mixture design has reportedly been found to quicken the process of testing different mixing ratios with high accuracy without running several experiments. Therefore, a ternary mixture design and a response surface approach are used in this work to ascertain the relationship between substrate mix and responses (biogas yield, methane yield, and synergy). The findings of the experiment revealed that R9 comprising 78.8 % human excreta, 11.8 % food leftovers and 9.4 % kitchen residue, had the highest methane production of 764.79 mLCH4/gVS and a synergistic index of 3.26. Additionally, the 3D response surface plots from the response surface model showed important and shared interactions between Human Excreta, (HE), Food Leftovers (FLO), and Kitchen Residue (KR). HE and KR had a similar positive synergistic effect on biogas yield, methane yield, and synergy, which was not the case for FLO. The response surface plots showed that the predicted responses (methane yield, biogas yield and synergy) increased with increasing HE and KR fractions and decreased with increasing FLO fractions in the substrate mixtures.

Modeling and optimization of transesterification of Jatropha oil to fatty acid methyl ester: application of response surface methodology (CCD) and Taguchi orthogonal method.

The study effectively optimized the transesterification process of Jatropha oil to fatty acid methyl ester using response surface methodology (CCD) and Taguchi orthogonal method, leading to enhanced efficiency and product quality. The optimization of five process parameters was conducted to predict the biodiesel yield (%) from the transesterification of Jatropha oil. The procedure was made easier with the use of a nanocatalyst made from calcium oxide obtained from snail shells using the hydrothermal technique. The RSM approach yielded an optimal FAME of 94.10% under specific conditions: a methanol to oil ratio of 5 : 1, catalyst weight of 1.5 w/w, reaction temperature of 50 °C, reaction duration of 45 minutes, and an agitation speed of 250 rpm across 32 experimental trials. On the other hand, the Taguchi method predicted a higher FAME yield of 86.36% using specific operational parameters. These parameters included a methanol to oil ratio of 4 : 1, catalyst weight of 0.5 w/w, reaction temperature of 60 °C, reaction duration of 25 minutes, and an agitation speed of 200 rpm. These parameters were determined through 16 experimental trials. The RSM technique yielded impressive results with a determined coefficient of determination (R2) of 0.9943, adjusted R2 of 0.9838, predicted R2 of 0.8470, and a coefficient of variance (CV) of 0.65. On the other hand, the Taguchi method had coefficients of 0.8994, 0.7483, and 1.95. The FAME yield of RSM was slightly higher, but the Taguchi method was much more cost-efficient. The analysis of variance (ANOVA) results showed that the methanol to oil ratio had the highest influence on the yield, accounting for 49.61% of the variation. This highlights the significant impact of this factor on the overall process. The study highlights the significance of utilizing advanced techniques such as TOA and RSM, which are known for their effectiveness. The study aims to enhance the yield and efficiency of the transesterification process, thereby increasing the overall production of fatty acid methyl ester from Jatropha oil. This innovative approach efficiently generates biodiesel from renewable resources, like Jatropha oil, in a manner that is both environmentally friendly and maximizes the effectiveness of the process parameters.

Ultrasound irradiation-assisted biodiesel synthesis from waste oils employing a retrievable and strong CoFe2O4/GO/SrO nanocatalyst

A novel heterogeneous CoFe2O4/GO/SrO nanocatalyst was synthesized using ultrasonic irradiation, and employed for synthesizing biodiesel from waste edible oil (WEO). To this end, a 2-step esterification-transesterification reaction utilizing ultrasound was applied. The surface attributes of CoFe2O4/GO/SrO was specified by XRD, FTIR, FESEM, EDX/Map, BET, DLS, CO2-TPD, and VSM analyses. CO2-TPD analysis indicated that the CoFe2O4/GO/SrO nanocatalyst has favorable catalytic activity for transesterification. CCD-based RSM approach was employed to examine the influence of parameters and ascertain optimal conditions under ultrasonic irradiation (24 KHz, 200 W, 70 % duty cycles and 60 % amplitude). Also, the utmost biodiesel yield (98.63 %) was achieved using CoFe2O4/GO/SrO under optimum conditions (i.e., time = 53.76 min, temperature = about 69 °C, CH3OH/oil proportion = 16.3:1, and nanocatalyst dosage = 5 wt%), which is the highest biodiesel performance ever attained using WEO. However, the highest biodiesel yield under optimal conditions by magnetic-stirrer at 600 rpm was 72.9 %, which is much lower than utilizing ultrasonic irradiation. Further, the stability investigation indicated that the CoFe2O4/GO/SrO nanocatalyst has a yield of over 90 % after five reuse stages, which reveals its remarkable stability. Besides, the kinetics of biodiesel production displayed that the reaction between methanol and WEO utilizing CoFe2O4/GO/SrO nanocatalyst is endothermic and the reaction rate enhances with temperature. On account of its high biodiesel yield, favorable catalytic activity, short reaction time, and remarkable stability, the CoFe2O4/GO/SrO nanocatalyst is strongly recommended for biodiesel generation from WEO in the presence of ultrasonic irradiation for industrial applications.

Optimization of syngas production from co-gasification of palm oil decanter cake and alum sludge: An RSM approach with char characterization

The study explores co-gasification of palm oil decanter cake and alum sludge, investigating the correlation between input variables and syngas production. Operating variables, including temperature (700–900 °C), air flow rate (10–30 mL/min), and particle size (0.25–2 mm), were optimized to maximize syngas production using air as the gasification agent in a fixed bed horizontal tube furnace reactor. Response Surface Methodology with the Box-Behnken design was used employed for optimization. Fourier Transformed Infra-Red (FTIR) and Field Emission Scanning Electron Microscopic (FESEM) analyses were used to analyze the char residue. The results showed that temperature and particle size have positive effects, while air flow rate has a negative effect on the syngas yield. The optimal CO + H2 composition of 39.48 vol% was achieved at 900 °C, 10 mL/min air flow rate, and 2 mm particle size. FTIR analysis confirmed the absence of C─Cl bonds and the emergence of Si─O bonds in the optimized char residue, distinguishing it from the raw sample. FESEM analysis revealed a rich porous structure in the optimized char residue, with the presence of calcium carbonate (CaCO3) and aluminosilicates. These findings provide valuable insights for sustainable energy production from biomass wastes.

Numerical simulation of thermosolutal natural convection of power-law non-Newtonian fluids in a parallelogram with sensitivity analysis by response surface methodology

Thermosolutal natural convection originates in a fluid when the density changes due to the presence of two distinct components with varying rates of diffusion. This convection is driven by buoyancy resulting from concurrent temperature and concentration gradients. This study focuses on the thermosolutal free convection flow within a parallelogrammic enclosure. The functioning fluid under consideration is non-Newtonian and formulated by the viscosity model (power-law). The top and bottom walls of the chamber are adiabatic and are assumed to be impermeable. The temperature and concentration on the left side are maintained at a high level, while the conditions on the right side are cold and low. The controlling parameters for the present case include Rayleigh number Lewis number (Le = 5, 10), Prandtl number (Pr = 6.2), buoyancy ratio (N = 0.8, −0.8) along with power-law index (n = 0.6, 1, 1.4). The results obtained from this numerical study are validated with existing results and indicate the correctness of the code. The output of the study is shown in terms of velocity and temperature profiles, streamlines, isotherms, and iso-concentrations, the average rate of heat and mass transmission in terms of the average Nusselt number () and the average Sherwood number (). The correlation equation derived from the RSM approach demonstrates the relationship between the output responses and the input parameters. It concludes that n negatively affects both heat and mass transfer, while Ra affects positively. The findings of this study could be helpful for understanding of thermosolutal natural convection behavior of non-Newtonian (power-law) fluid in an enclosure and therefore accelerate the industrial application of such fluid in the relevant field, such as HVAC (heating, ventilation, and air conditioning) system.

Study on the Mechanical Properties of Polyurethane-Cement Mortar Containing Nanosilica: RSM and Machine Learning Approach

Polymer-modified cement mortar has been increasingly used as a runway/road pavement repair material due to its improved bending strength, bonding strength, and wear resistance. The flexural strength of polyurethane–cement mortar (PUCM) is critical in achieving a desirable maintenance effect. This study aims to evaluate and optimize the flexural strength of PUCM involving nano silica (NS) using a central composite design/response surface methodology (CCD/RSM) to design and establish statistical models. The PU binder and NS were utilized as input parameters to evaluate the responses, such as compressive and flexural strength. Moreover, machine learning (ML) algorithms including artificial neural networks (ANN) and Gaussian regression process (GPR) were used. The PUCM mixtures were prepared by adding a PU binder at 0%, 10%, 15%, and 25% by weight of cement. At the same time, NS was incorporated into the mortar mixes at 0 to 3% (interval of 1%) by cement weight. The results showed that the simultaneous effect of PU binder at the optimal content and NS improved the performance of PUCM. Adding NS to the mortar mixture mitigated some of the strength lost due to the PU binder, which remarkably reduces the strength properties at a high content. The optimized PUCM can be obtained by partly adding 3.5% PU binder and 2.93% NS particles by the weight of cement. The performance of the machine learning algorithms was tested using performance indicators such as the determination of coefficient (R2), mean absolute error (MAE), mean-square error (MSE), and root-mean-square error (RMSE). The GPR algorithm outperformed the ANN with higher R2 and lower MAE values in the training and testing phases. The GPR can predict flexural strength with 90% accuracy, while ANN can predict it with 75% accuracy.