Response Surface Methodology Approach Research Articles

Genetic neuro-computing model for insights on membrane performance in oily wastewater treatment: An integrated experimental approach

In this study, response surface methodology (RSM) and artificial neural network-based genetic algorithm (ANN-GA) were utilized to predict two crucial output parameters of membrane performance, namely separation efficiency and oil flux, derived from experimental investigations. The central composite design (CCD) screening approach of RSM was employed to evaluate the influence of important process input parameters, such as oil concentration (ranging from 50 to 10,000 ppm), feed flow rate (ranging from 150 to 300 mL/min), and pH of the feed (ranging from 4 to 10), as well as their synergistic effects on the output variables. The constructed RSM model and ANN-GA were effectively employed to estimate the optimum conditions for maximizing the output variables. Statistical analysis using the determination coefficient (R2) and standard error of prediction (SEP), along with analysis of variance (ANOVA) and the t-test, demonstrated the accurate description of the membrane performance process by both models. For the oil flux, the RSM model showed an estimated R2 of 0.9916 and SEP of 3.54%, while the ANN model exhibited an R2 of 0.9933 and SEP of 3.31%. In terms of separation efficiency, the RSM model yielded R2 = 0.9929 and SEP = 1.31%, whereas the ANN model achieved R2 = 0.9961 and SEP = 0.99%. Remarkably, the ANN-GA approach revealed the best optimum conditions for both responses. Furthermore, the sensitivity analysis of the developed ANN model indicated the order of significance of the variables as follows: oil concentration > feed pH > feed flow rate. These findings substantiate the efficacy of the proposed approach, making it viable for implementation in diverse industries to facilitate sustainable monitoring and management practices.

A co-precipitation synthesized BiOI/(BiO)2CO3 nanocatalyst: An experimental design and mechanism study towards photodegradation of sulfasalazine

BackgroundIncreased antibiotic consumption residues a large amount of antibiotics in the bacterial communities and ecosystems, leading to bacterial persistence against them. Thus, in recent decades, an urgent need has been to introduce/develop novel catalysts/adsorbents/methods to diminish the pollution extent of the aquatic environment by various organic pollutants like antibiotics. MethodsBiOI/(BiO)2CO3 was synthesized by adding ammonium iodide to the aqueous suspension of (BiO)2CO3 (BOC) under hydrothermal conditions. The individual BiOI and (BiO)2CO3 and their p-n heterojunction system were characterized by some identification techniques like UV–vis diffuse reflectance spectroscopy (DRS) and electrochemical impedance spectroscopy (EIS). Significant findingsThe direct band gap energies of 1.99, 3.54, and 2.42 eV were obtained for BiOI, (BiO)2CO3, and BiOI/(BiO)2CO3 samples from the Tauc plots. Both CVs and EIS results confirmed better charge transfer in the coupled catalyst. pHpzc for BiOI, (BiO)2CO3 and BiOI/(BiO)2CO3 was 6.3, 10.1, and 6.5. The response surface methodology (RSM) approach was used to construct a design model to investigate the interaction effects of the most influencing variables on the boosted catalytic effect of the coupled catalyst toward sulfasalazine (SSZ) as a model antibiotic pollutant. The model goodness was confirmed based on model F-value=20.59 > F0.05, 14, 13 = 2.55 and lake of fit (LOF) F-value = 0.364 < F0.05, 10, 3 = 8.73, as well as by adequate regression coefficient (R2) of 0.9705, adjusted R2 (0.9699), and predicted R2 (0.9575) values. RSM optimal run included pH 6.0, catalyst dose: 0.55 g/L, irradiation time: 50 min, and SSZ concentration of 6 ppm, which resulted in a 95.3 % photodegradation efficiency. The relative role of photoinduced holes> photoinduced electrons > hydroxyl radicals> superoxide radicals was obtained in the photodegradation efficiency by the results obtained in the presence of some scavenging species. Accordingly, the photodegradation pathway was suggested. We believe simple preparation of the BiOI/(BiO)2CO3 photocatalyst via a co-precipitation anion-exchanged consisted procedure by adding iodide anion to the aqueous suspension of (BiO)2CO3 is an advantage of this work.

Optimization of Humidification-Dehumidification solar desalination Unit: Comparative analysis

Water is essential for life on Earth. By turning saline water into drinkable water, desalination technology may help solve water scarcity. The present work uses artificial neural networks and the response surface approach to discuss freshwater production through a humidification-dehumidification solar-powered desalination unit with a pneumatic sprayer. The compressed air flow rate, air pressure, and time on productivity desalinated by the proposed system are investigated. The designed artificial neural networks model indicated that responses are close to the observed findings. It is shown that the generated models can be utilized to predict productivity and accumulated productivity within the investigation area. The optimum parameters for maximum accumulated productivity are 150 L/min compressed air flow rate, 7 bar air pressure, and 16o'clock to achieve the maximum accumulated freshwater productivity of 19.4 L/day. The comparative results reveal higher precision in the artificial neural networks model than in the response surface methodology approach.

Optimization and Mathematical Modelling of Surface Roughness Criteria and Material Removal Rate when Milling C45 Steel using RSM and Desirability Approach

This work consists of studying the workability of C45 steel in face milling by using coated carbides (GC4040). The objective is to investigate the evolution of surface roughness (Ra, Ry, and Rz) and Material Removal Rate (MRR) according to cutting speed, feed rate, and depth of cut. A full-factorial design (43)was adopted in order to analyse the obtained experimental results via bothAnalysis of Variance (ANOVA) and Response Surface Methodology (RSM)design. The levels of cutting speed were as follows: Vc1=57 m/min; Vc2=111m/min; Vc3=222 m/min and Vc4=440 m/min. The ranges of feed rate werefz1=0.024 mm/tooth; fz2=0.048 mm/tooth; fz3=0.096 mm/tooth and fz4=0.192mm/tooth. As for the depth of cut levels, they included ap1=0.2 mm; ap2=0.4mm; ap3=0.6 mm, and ap4=0.8 mm. To determine mathematical models tomake predictions, a statistical analysis of the results by using RSM was appliedto obtain the main effects and interactions plot of the answer. Furthermore, amulti-objective optimization procedure for minimizing Ra and maximizing themetal removed rate using the desirability approach was also implemented.Therefore, the developed models can be effectively used to predict the surfaceroughness criteria and the material removal rate in machining C45 steel. Theresults indicated that feed rate is a significant factor affecting surfaceroughness (Ra: 52.37%, Ry: 80.97%, and Rz: 54.96%), followed by cuttingspeed (Ra: 37.88%, Ry: 12.90%, and Rz: 24.43%). Meanwhile, cutting speedand feed rate are the most significant parameters on the MRR with a contribution of 29.5% followed by the depth of cut with 11.62%.

The coupled WO3-AgBr nanocatalyst, part I: Experimental design, kinetics and mechanism studies of the boosted photocatalytic activity towards metronidazole in an aqueous solution

The boosted photocatalytic activity of the coupled AgBr-WO3 nanocatalyst was observed towards metronidazole (MNZ) in an aqueous solution, and to study the simultaneous interaction effects between the influencing variables, experimental design was performed via the response surface methodology approach (RSM). The optimized run included MNZ solution pH: 9, catalyst dosage: 1 g/L, irradiation time: 45 min, and CMNZ: 10 mg/L. The goodness of the model was proven by greater model F-value than F0.05, 14, 15 = 2.42, and smaller lake of fit F-value than F0.05, 10, 5 = 4.74 and also by regression coefficient values of R2: 0.9994, Adjusted R2: 0.9988, Predicted R2: 0.9977. Based on the results obtained in the scavenging agent study, the following trend was suggested for the relative importance of the main four reactive species in MNZ photodegradation: Photoinduced h+> Hydroxyl radicals > Photoinduced e-> Superoxide radicals. The Z-scheme pathway well illustrates the mechanism pathway. The photodegradation kinetics obeyed the pseudo-first-order Hinshelwood model with a rate constant of 0.014 min−1 (t1/2 = 49.5 min). The photodegraded solutions' chemical oxygen demand (COD) confirmed the MNZ mineralization. Based on the COD results, a rate constant of about 0.018 min−1 (t1/2 = 38.5 min) was obtained. Reusing experiments confirmed the excellent stability of the binary catalyst for at least four reusing runs.

Optimization of colloidal nano-silica based cementitious mortar composites using RSM and ANN approaches

Sustainable development of infrastructure requires the efficient and optimized utilization of nano-silica in concrete applications. Thus, current study aims to explore how the dosages of colloidal nano-silica (CNS) and its surface area affect the mechanical performance of cementitious mortar composites. To assess the compressive strength with aging (7, 28 and 56 days), CNS with different surface areas was used as cement substitutes at three different dosages levels. Additionally, to optimize nano-silica dosages and evaluate the outcomes of the experiment, statistical modelling based on Response Surface Methodology (RSM) and machine learning-based Artificial Neural Network (ANN) were applied. In comparison to the control and all other mixtures, the compressive strength was improved (51.5 MPa, 70.2 MPa, and 73.2 MPa) at 7, 28, and 56 days, respectively, by the CNS with higher surface area (CNS500) at their lower dosages (3%). However, at medium (5%) and high dosages (10%), CNS with a lower surface area (CNS80) resulted in better compressive strength (71.9 MPa, 87 MPa, and 90 MPa) at 7, 28, and 56 days, respectively, comparatively to control as well as all other mixtures. These findings were supported by both the RSM and ANN models, with the ANN model outperforming the RSM model in terms of performance. The ANN model was trained and validated using 70% and 30% of the data, respectively. For the validation data of ANN model, the Coefficient of Determination (R), the Mean Absolute Error (MAE), and the Root Mean Square Error (RMSE) were revealed as 0.925, 2.263 and 2.974 MPa, respectively. Whereas, for the quadratic RSM models, these values were determined as 0.86, 4.485, and 5.45 MPa, respectively. The results of statistical models validated the experimental results, thus showing that the developed RSM and ANN can be used as reliable prediction model to optimize CNS use in producing stronger and more sustainable concrete.

Technical and economic analysis of multi-energy complementary systems for net-zero energy consumption combining wind, solar, hydrogen, geothermal, and storage energy

An integrated renewable energy supply system is designed and proposed to effectively address high building energy consumption in Zhengzhou, China. This system effectively provides cold, heat, and electricity by incorporating various clean energy sources such as wind, solar, hydrogen, and geothermal energy. Technical and economic analyses are conducted to optimize the integration of these renewable sources. Technical and economic analyses are conducted to optimize the integration of these renewable sources. Rigorous system modeling and dynamic simulation using TRNSYS software evaluate the seamless integration and optimal functioning of the PV/T subsystem within the CCHP system. The interaction between Photovoltaic/Thermal (PV/T) and borehole heat exchanger (BHE) coupling is investigated, analyzing their impact on individual system performance. Furthermore, key indicators, including overall electricity consumption (OEC), life cycle cost (LCC), heat pump coefficient of performance (COPHP), and system coefficient of performance (COPSYS) are analyzed. The robust response surface methodology (RSM) and Box-Behnken experimental design approach are employed to show remarkable agreement between predicted and simulated values, with a maximum deviation of only 1.45%. The optimal configuration consists of a PV/T area of 132 m2, 20 wind turbines, 12 alkaline fuel cells, and 17 borehole heat exchangers, resulting in highly favorable outcomes: an OEC of −35648.72 kW∙h/year, an LCC of $209113.85, a COPSYS of 2.91, and a COPHP of 3.82. Moreover, detailed assessments of each subsystem's performance enhances our understanding of the system's overall operation, affirming the feasibility of the proposed integrated energy supply system for buildings.

Prediction of concrete residual compressive strength under elevated temperatures: Response surface methodology (RSM) approach

Exposure of concrete to elevated temperatures causes irreversible damage to the concrete structure and poses a serious threat to its service life. Due to the importance of concrete fire performance, extensive research has been conducted to investigate its behavior under different conditions of elevated temperatures. The properties of concrete are significantly affected by various factors, including heating temperatures, heating durations, and cooling methods. Among these factors, the residual compressive strength of concrete is considered the most crucial characteristic after exposure to elevated temperatures. This paper aims to develop mathematical models for analyzing and predicting the relative residual compressive strength of concrete at high temperatures. Three independent factors were identified in this study: heating temperatures, heating duration, and cooling method. Two groups of datasets on the relative residual compressive strength of concrete under elevated temperatures were reviewed and collected from previous studies, serving as the benchmark dataset and validation dataset, respectively. Response Surface Methodology (RSM) was employed to analyze the datasets. The results of various statistical parameters, such as the coefficient of determination, sum of squares, F-value, and P-value, indicate the significance of the predicted model for estimating concrete's relative residual compressive strength under elevated temperatures. The RSM analysis reveals that heating temperatures have the most significant effect on the relative residual compressive strength of concrete. In summary, the RSM model shows a strong correlation with the validation datasets, with a coefficient of determination (R2) of 0.7869.

Design, Formulation, and Evaluation of Risperidone Mucoadhesive Buccal Patches

Objectives: To construct and optimize Risperidone (RIS) mucoadhesive buccal films for systemic distribution as an alternate route. To make buccal patches of Risperidone utilizing natural polymers such sodium alginate (SA), Hydroxypropyl methylcellulose (HPMC), Na CMC, and Carbopol 934 (CP 934). Method: Solvent casting created Risperidone buccal patches. The optimization study used a software-based response surface methodology approach with 23 factorial designs to evaluate 8 formulations of Risperidone mucoadhesive buccal patches to determine the significant effect of selected independent variables on the dependent variable. To assess patch appearance, thickness, weight homogeneity, folding durability, medication content, surface pH, swelling index, and FTIR. Invitro dissolution, ex-vivo permeation, residence time, and stability tests. Results: FTIR and DSC showed that Risperidone was entirely entrapped in polymer carrier bonds with no chemical interaction. Drug distribution was uniform in buccal patches at 90.14± 0.07 and 98.75± 0.80. Conclusion: Buccal patch medicine release and penetration depended on polymer type. Hydrophilic polymers boosted buccal patch drug release. F6 was the best of F1–F8. Formulation F6 had 82.03 ±0.82% in-vitro drug release and 75.21 ± 0.42% ex-vivo permeability after 7 hours. Stability tests did not modify appearance, surface pH, content homogeneity, in-vitro residence length, medication release, or ex-vivo penetration.

Structural, optimization of and mechanistic insights into a new thiosemicarbazone derivative as a highly sensitive and selective chemosensor for Hg2+ recognition using DFT, COSMO-RS, RSM, and molecular dynamics simulation approaches

A new thiosemicarbazone derivative, N-(2-hydroxyphenyl)-2-[1-(pyridin-4-yl)ethylidene]hydrazinecarbothioamide (HPEH), has been synthesized, characterized, and further developed as a highly selective and sensitive colorimetric chemosensor for Hg2+ recognition in environmental water samples. Structural conformers of HPEH were successfully identified using a combination of the potential energy surface (PES) and time-dependent density functional theory (TD-DFT) methods. The synthesized HPEH was successfully characterized further and analyzed based on its harmonic vibrational frequencies, NMR spectra, and electronic transitions using the DFT approach. Sigma profiles were generated using the COSMO-RS approach to identify a compatible medium for HPEH to act as a chemosensor. The conditions for the highly sensitive and selective detection of Hg2+ by HPEH were successfully optimized using the statistical response surface methodology approach. The optimum sensing of HPEH occurred in an 8:2 v/v DMSO/pH 7.8 solution at a 20:60 μM HPEH/Hg2+ concentration and after a reaction time of 18 min, with statistically significant independent variables (p < 0.05) for all parameters. Under optimal conditions, the lowest Hg2+ concentration detected by HPEH was 3.56 µM, indicating that HPEH can serve as an alternative and comparable probe for the detection of Hg2+ in aqueous systems. Using the optimized results, the interaction between HPEH and Hg2+ in the chemosensor system was successfully modeled, and the model was subsequently used with the TD-DFT, non-covalent interaction-reduced density gradient (NCI-RDG), and molecular dynamics approaches to gain mechanistic insights into the interaction. The results showed that the newly synthesized HPEH, in addition to being cost-effective, could serve as a suitable alternative and comparable chemosensor for Hg2+ recognition in water samples, with the advantages of being efficient, portable, and eco-friendly, and offering rapid analysis without the need of specialized training.

Response surface methodology and desirability approach to investigate and optimize the performance of a CO2 geothermal thermosyphon

Geothermal thermosyphons (GTs) are increasingly used in many heating and cooling geothermal applications, owing to their high heat transfer performance. In this paper a combined response surface methodology and multi-objective desirability method is proposed for the investigation and optimization of the thermal performance of a geothermal thermosyphon. The filling ratio, temperature, and flow rate of the heat transfer fluid are selected as the designing parameters, and heat transfer rate and effectiveness are adopted as response parameters (objective functions). First, a dedicated experimental GT test bench filled with carbon dioxide (CO2) was built and subjected to different test conditions defined by RSM. A multi-level design of experiment-based response surface methodology (RSM) was used to establish corresponding models between the input parameters and responses. Various diagnostic tests were used to evaluate the quality and validity of the best-fit models, which explain respectively 98.9 and 99.2% of the output result's variability. Further, a surface response analysis of the effect of each input parameter on the responses was performed and a desirability function-based model was employed to determine the optimal combination of factors that would maximize the desired responses. The results revealed that the parameter-setting obtained using the proposed procedure satisfies the requirements of each response, with a desirability of 0.98.

Evolutionary Optimizing Process Parameters in the Induction Hardening of Rack Bar by Response Surface Methodology and Desirability Function Approach under Industrial Conditions.

Conditions of industrial production introduce additional complexities while attempting to solve optimization problems of material technology processes. The complexity of the physics of such processes and the uncertainties arising from the natural variability of material parameters and the occurrence of disturbances make modeling based on first principles and modern computational methods difficult and even impossible. In particular, this applies to designing material processes considering their quality criteria. This paper shows the optimization of the rack bar induction hardening operation using the response surface methodology approach and the desirability function. The industrial conditions impose additional constraints on time, cost and implementation of experimental plans, so constructing empirical models is more complicated than in laboratory conditions. The empirical models of nine system responses were identified and used to construct a desirability function using expert knowledge to describe the quality requirements of the hardening operation. An analysis of the hypersurface of the desirability function is presented, and the impossibility of using classical gradient algorithms during optimization is empirically established. An evolutionary strategy in the form of a floating-point encoded genetic algorithm was used, which exhibits a non-zero probability of obtaining a global extremum and is a gradient-free method. Confirmation experiments show the improvement of the process quality using introduced measures.

Optimum Yield of Empty Fruit Bunches Cellulose Nanofibers by Deep Eutectic Solvent and Ultrasonication

AbstractCellulose nanofibers (CNFs) are extensively utilized as affordable, renewable materials. The conventional technique for making CNFs is time‐consuming, requires hazardous toxic chemicals, and consumes enormous amounts of energy. CNFs from empty fruit bunches (EFB) were produced via deep eutectic solvent (DES) and ultrasonication. The DES treatment conditions were optimized using the central composite design (CCD) approach of response surface methodology (RSM). Analysis of variance (ANOVA) revealed that the reaction time, DES molar ratio, and temperature were all significant variables. The experimental results closely correspond to the theoretical model of CNFs yield. X‐ray diffraction (XRD) studies demonstrated that the crystallinity index of the CNFs increased significantly after sonication. It could be stated that DES treatment and ultrasonication were effective ways to successfully generate CNFs from EFB. This study may serve as foundation for high‐yield, industrial‐scale synthesis of nanocellulose using DES treatment.

Techno-economic assessment of sugarcane bagasse pith-based briquette production and performance analysis of briquette feed gasifier-engine system

Utilizing agriculture co-products and agricultural residues directly leads to Energy, Economic, and Environmental sustainability. Sugar production industries produce a considerable amount of sugarcane bagasse (SB) as a co-product, whereas SB is used in paper-mill sectors, which have a large amount of waste as sugarcane bagasse pith (SBP). In this view, the novelty of the present study aims to ensure the economic viability of the SBP briquette production plant, after that, briquette-based producer gas (PG) generation and application to compression ignition (CI) engine for diesel substitution. The economic analysis includes the Net Present Value (NPV) and Profitability Index (PI) for the feasibility check. And gasifier-engine analysis includes the effect of gasification equivalence ratio (GER), engine compression ratio (CR), and load on engine brake thermal efficiency (BTE), diesel saving, Sound, Exhaust gas temperature (EGT), and emissions (CO, HC, CO2, NOx). Further, operating variables were optimized with the desirability approach of Response surface methodology (RSM). In the result, NPV and PI values were found to be Rs 49,64,379.5 (≈0.06 million USD) and 1.98, respectively. However, the economic feasibility of the plant is sensitive to capital cost, briquette market price, and discount percentages. Regarding gasifier-engine performance, the maximum diesel substitution was found to be 66.15% at dual fuel (DF) mode engine run. RSM-based optimization result showed the optimum operating setting of 0.10 GER, 16 CR, and 9.93 kg load at 1500 rpm with a composite desirability of 0.798. Accordingly, at optimal input parameters, the magnitudes of engine performance as BTE, Sound, CO, HC, CO2, and NOx were found to be 27.18%, 91.21 db, 0.10%vol., 53.19 ppm, 2.33%vol., and 8.43 ppm respectively. Thus, the higher value of the economic index and substantial amount of diesel fuel saving through the gasifier-engine system ensures the economic feasibility of briquetting and power generation technology.

The Optimization of a Segmented Cladding Fiber via the Response Surface Methodology Approach for a Large Mode Area

In this work, we have proposed and optimized a segmented cladding fiber (SCF) with a large mode area (LMA) consisting of a uniform core and a double cladding. The outer cladding of the SCF consisted of a periodic alternation of high- and low-refractive-index segments, while the inner cladding consisted of a resonant layer of rods surrounded by high-refractive-index rings. The three geometrical parameters chosen as design variables were the (a) doped rod refractive index differences, (b) refractive index differences of rings, and (c) ring thickness. Using the Box–Behnken approach, we selected thirteen different design cases and modeled them numerically using the finite element method (FEM). In order to optimize the features of the proposed fiber, such as the effective mode area (EMA), we applied response surface methodology (RSM). The EMA of the optimal SCF was significantly improved and markedly enlarged to about 706 µm2 at a wavelength of 1.550 µm. Different properties of the optimized double-cladding octo-wing SCF (DC-OW-SCF), such as confinement losses in the core mode and the first higher-order mode, were studied. The DC-OW-SCF offers the advantages of feasibility in fabrication using the powder-in-tube (PIT) method and provides the possibility of utilization in compact amplifier devices and high-power fiber lasers.

Optimization of QuEChERS Extraction for Determination of Carotenoids, Polyphenols, and Sterols in Orange Juice Using Design of Experiments and Response Surface Methodology.

Several compounds with different physical properties are present in foods, biological components, and environmental samples, and there are cases in which these must be analyzed simultaneously. However, it is difficult to extract compounds with different physical properties from the same sample using a single method. In the present study, we examined the optimal conditions for the QuEChERS extraction of several kinds of compounds from orange juice using design of experiments (DoE) and response surface methodology (RSM) to determine the optimal ratio of organic solvent to sodium chloride. We determined the optimal extraction conditions, which were within the design space, using 100% tetrahydrofuran (THF) as the extraction organic solvent and NaCl:MgSO4 = 75:25 as the salt. The developed LC/MS/MS method using QuEChERS extraction achieved specific detection and precise quantification. Finally, we measured the polyphenols, sterols, and carotenoids in citrus juice using the optimized QuEChERS extraction method before LC/MS/MS analysis. Most of the analytes were quantifiable in orange juice. The optimized method achieved ease of operation, the extraction of analytes from food samples in a short time (within 30 min), minimization of analytical residues, and reliability. The DoE and RSM approach may contribute to better optimization of the extraction conditions for the lowest number of experiments.

Optimization of common rail direct injection diesel engine performance with Melia dubia methyl ester peppermint oil blend using response surface methodology approach and investigation of hydrogen and hydroxy influence

In this study, an experimental investigation was carried out to evaluate the impact of compression ratio, exhaust gas recirculation, and the start of injection on the performance and emission of single-cylinder VCR CRDI engine fueled with Melia dubia biodiesel and peppermint oil blends. Response surface methodology (RSM) was used to evaluate the effects of these multiple factors and their interactions with response variables like brake thermal efficiency (BTE), carbon monoxide (CO), oxides of nitrogen (NOx), hydrocarbon (HC), and smoke. Model analysis was done to validate the regression model developed for all responses by using Analysis of variance (ANOVA). Compression ratios 17.5, 19.5, and 21.5, exhaust gas recirculation of 10, 15, and 20%, and 19, 21, and 23 °CA were selected for the start of injection in this study. High desirability of 0.979 was obtained at the optimum operating parameters, viz. 19.5 of compression ratio, 23 °CAbTDC of the start of injection with 15% EGR where the values of BTE, CO, HC, NOx, and smoke were found to be 30.66%, 2.66 g/kWh, 0.076 g/kWh, 7.36 g/kWh, and 40 HSU respectively. Further, hydrogen and hydroxy (simulated) gas were inducted to improve the biofuel blend's performance, and their influence was investigated. A significant improvement in performance and reduction in emissions were observed with the usage of hydrogen gases. Researchers and organizations seeking to enhance engine performance and reduce harmful environmental emissions can benefit from this study.

Machine Learning Alternatives to Response Surface Models

In the Design of Experiments, we seek to relate response variables to explanatory factors. Response Surface methodology (RSM) approximates the relation between output variables and a polynomial transform of the explanatory variables using a linear model. Some researchers have tried to adjust other types of models, mainly nonlinear and nonparametric. We present a large panel of Machine Learning approaches that may be good alternatives to the classical RSM approximation. The state of the art of such approaches is given, including classification and regression trees, ensemble methods, support vector machines, neural networks and also direct multi-output approaches. We survey the subject and illustrate the use of ten such approaches using simulations and a real use case. In our simulations, the underlying model is linear in the explanatory factors for one response and nonlinear for the others. We focus on the advantages and disadvantages of the different approaches and show how their hyperparameters may be tuned. Our simulations show that even when the underlying relation between the response and the explanatory variables is linear, the RSM approach is outperformed by the direct neural network multivariate model, for any sample size (&lt;50) and much more for very small samples (15 or 20). When the underlying relation is nonlinear, the RSM approach is outperformed by most of the machine learning approaches for small samples (n ≤ 30).

Optimizing the Flexural Behavior of Bamboo Reinforced Concrete Beams Containing Cassava Peel Ash using Response Surface Methodology

The growing concern to reduce global warming has necessitated the use of more eco-friendly materials in construction. The study is focused on the utilization of cassava peel ash as supplementary cementitious material and bamboo as reinforcement in concrete beams. The response surface methodology approach was explored to determine the effect of simultaneously varying the cassava peel ash content, bamboo size, beam length, and beam depth on the flexural strength and strain of beams. An analysis of variance was carried out on experimentally obtained results to determine the accuracy of the obtained models and the contributions made by the linear interaction and quadratic terms on flexural strength and flexural strain. The coefficient of determination obtained for RSM models showed a good correlation between all predicted and experimentally obtained results. The optimum conditions obtained for bamboo-reinforced concrete containing cassava peel ash were 3% cassava peel ash, 16 mm bamboo diameter, 500 mm beam length, and 150 mm beam depth. The predicted flexural strengths were 11.85, 14.34, and 14.95 N/mm2 and flexural strains of 0.64, 0.67, and 0.91 for 28 days, 56 days, and 90 days, respectively. To validate the model prediction, a laboratory experiment was conducted using the optimum mix design proportion. From the results obtained, it was observed that the experimental results were close to those predicted by the models. These models can be efficiently used for simulating the flexural behavior of bamboo-reinforced concrete beams. Doi: 10.28991/CEJ-2023-09-08-011 Full Text: PDF

Modelling the effects of mixing ratio and temperature on the thermal conductivity of GNP-Alumina hybrid nanofluids: A comparison of ANN, RSM, and linear regression methods

This research aimed to evaluate and compare the efficacy of three distinct methods for forecasting the thermal conductivity of GNP-Alumina hybrid nanofluids. The methods under consideration were artificial neural network (ANN), response surface methodology (RSM), and linear regression (LR). The predictive performance of the ANN model was investigated in relation to the number of neurons in the hidden layer. The findings revealed that the optimal number of neurons was 7, which produced the best performance with an overall mean square error (MSE) of 1.08E-06. The correlation coefficient was also high at 0.99799. The RSM approach involved testing linear, quadratic, cubic, and quartic models, with the quadratic model showing the highest predicted R2 (0.9721) values, indicating that it provided the best fit to the data. Finally, the LR model was developed using a backward elimination approach, with temperature and volume fraction being the significant variables in the final model. Overall, the ANN model produced the most accurate predictions, followed by the RSM and LR models. These findings suggest that the ANN and RSM techniques can be effective tools for forecasting the thermal conductivity of nanofluids, and highlight the importance of selecting appropriate model parameters for optimal performance.