Multivariate Response Surface Methodology Research Articles

Optimization of supercritical fluid extraction of bioactive compounds from Ammodaucus leucotrichus fruits by using multivariate response surface methodology

This study explored supercritical fluid extraction (SFE) of bioactive molecules from Ammodaucus leucotrichus seeds, a little-known source of potent bioactive compounds. Response surface methodology assessed extraction parameters (pressure, temperature, and ethanol co-solvent) and their effects on global yield, total phenolic compound (TPC), total carbohydrate content (TCC), and anti-Alzheimer activity. Optimization via a Box-Behnken design identified the optimal conditions: 15 % ethanol, 300 bar, and 70 °C. Chemical profiling using GC-MS and UHPLC-q-tof-MS/MS detected over 41 metabolites. In addition, a biorefinery sequential extraction process was performed to obtain extracts with high neuroprotective potential. The SFE extracts exhibited modest AChE inhibition. Notably, sequential SFE and PLE extractions yielded extracts with enhanced antioxidant activity compared to separate processes. In conclusion, Ammodaucus leucotrichus presents a promising natural source of secondary metabolites. Its potential health benefits warrant further exploration, emphasizing the need for continued research.

Solving a Typical Small Sample Size MRSM Dataset Problem Using a Flexible Hybrid Ensemble Approach for Credibility

Multiresponse surface methodology often involves small data analytics which, statistically, have regression modelling credibility problems. This is worsened by dataset, model selection and solution methodology uncertainties. It is difficult for solution methodologies which select and use single best models per response at simultaneous optimisation to effectively deal with these problems. This paper exploited the fact that model selection criteria choose differently, in a flexible hybrid ensemble system, to generate several solutions for integration and comparison. Mean square prediction error, with bias-variance-covariance decomposition values, was computed and analysed at simultaneous optimisation. Results suggest that the credibility of the final solution is enhanced when working with multiple models, solution methodologies and results. However, the results do not show any significance of small sample size correction to model selection criteria and analysis of bias-variance-covariance decompositions at simultaneous optimisation does not encourage dependence on theoretical optimality for best results.

ENHANCING MULTI RESPONSE SURFACE METHODOLOGY THROUGH INTEGRATING PRINCIPAL COMPONENT ANALYSIS (PCA) FOR COMPLEX PARAMETER DESIGN OPTIMIZATION

The optimization of parameters to achieve desired performance outcomes presents significant challenges due to high dimensionality, collinearity among variables, and data noise. Traditional optimization methods, such as Response Surface Methodology (RSM), often face limitations when tackling these complexities. Additionally, the lack of efficient techniques for identifying and prioritizing influential parameters further exacerbates the difficulties in the optimization process. To address these intertwined issues, we propose an enhanced optimization methodology that integrates Principal Component Analysis (PCA) with Multi- Response Surface Methodology (MRSM). This integration aims to reduce dimensionality and highlight the most significant parameters, facilitating a more effective optimization process. We evaluated the effectiveness of the PCA-MRSM approach using a simulated dataset. Our findings indicate that the PCA-MRSM technique significantly outperforms traditional MRSM, leading to improved optimization outcomes and reduced variability. The analysis of response surface plots reveals a curved relationship between the principal components and the response variable, suggesting intricate interactions among the components. The results highlight the potential of the PCA-MRSM approach for optimizing complex systems characterized by multiple responses and correlated input variables. By effectively addressing the challenges of high dimensionality and collinearity, this methodology paves the way for more robust and insightful optimization techniques in intricate contexts.

Use of customized 3-dimensional printed mandibular prostheses with a dental implant pressure-reducing device in mandibular body defect: A finite element study performing multiresponse surface methodology

Background/purposeSegmental body defects of the mandible result in the complete loss of the affected region. In our previous study, we investigated the clinical applicability of a customized mandible prosthesis (CMP) with a pressure-reducing device (PRD) in an animal study. In this study, we further incorporated dental implants into the CMP and explored the use of dental implant PRD (iPRD) designs. Materials and methodsBy employing a finite element analysis approach, we created 4 types of CMP: CMP, CMP with iPRD, CMP-PRD, and CMP-PRD with iPRD. We developed 2 parameters for the iPRD: cone length (CL) in the upper part and spring pitch (SP) in the lower part. Using the response surface methodology (RSM), we determined the most suitable structural assignment for the iPRD. ResultsOur results indicate that CMP-PRD had the highest von Mises stress value for the entire assembly (1076.26 MPa). For retentive screws and abutments, CMP with iPRD had the highest von Mises stress value (319.97 and 452.78 MPa, respectively). CMP-PRD had the highest principal stress (131.66 MPa) in the anterior mandible. The iPRD reduced principal stress in both the anterior and posterior mandible. Using the RSM, we generated 25 groups for comparison to achieve the most favorable results for the iPRD and we might suggest the CL to 12 mm and the SP to 0.4 mm in the further clinical trials. ConclusionUse of the PRD and iPRD in CMP may resolve the challenges associated with CMP, thereby promoting its usage in clinical practice.

Multiresponse surface methodology for hyperparameter tuning to optimize multiple performance measures of statistical and machine learning algorithms

AbstractHyperparameter tuning is an important task in machine learning for controlling model complexity and improving prediction performance. Most methods in the literature can only be used to tune hyperparameters to optimize a single performance measure. In practice, participants may want to optimize multiple measures of the model; however, optimizing one measure may worsen another. Therefore, a hyperparameter tuning method is proposed using the multiresponse surface methodology to solve the tradeoff problem between multiple measures. A search algorithm that requires fewer tuning runs is developed to find the optimal hyperparameter settings systematically based on the preferences of participants for multiple measures of the model. An example using the random forest algorithm is provided to demonstrate the application of the proposed method to improve the prediction performance of the model on unbalanced data.

Multivariate response surface methodology assisted modified QuEChERS method for the rapid determination of 39 pesticides and metabolites in medlar

A modified QuEChERS method coupled with high performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS) was established for residue analysis of 39 pollutants (34 commonly used multi-class pesticides and 5 metabolites) in medlar matrices (fresh, dried, and medlar juice). Samples were extracted using water with 0.1 % formic acid: acetonitrile (5: 10, v/v). The phase-out salts and five different cleanup sorbents (including N-propyl ethylenediamine (PSA), octadecyl silane bonded silica gel (C18), graphitized carbon black (GCB), Carbon nanofiber (C-Fiber) and MWCNTs) were investigated to improve the purification efficiency. The Box-Behnken Design (BBD) study was employed for an optimal solution of the volume of extraction solvent, phase-out salt, and the purification sorbents for the analytical method. The average recoveries of the target analytes in the three medlar matrices ranged from 70 % to 119 % with relative standard deviations (RSDs) of 1.0 %−19.9 %. Screening of market samples (fresh and dried medlars) collected from the major producing regions in China showed that 15 pesticides and metabolites were detected in the samples at concentrations of 0.01–2.22 mg/kg, and none of which exceeded the maximum residue limits (MRLs) set in China. The results showed that the risk of food safety by consumption of medlar products caused by the use of pesticides was low. The validated method could be used for rapid and accurate screening of multi-class multi-pesticide residues in Medlar for food safety.

Life cycle assessment multi-objective optimization for eco-efficient biodiesel production using waste cooking oil

In recent decades, fossil fuel consumption has increased exponentially despite limited resources, high cost, excessive air pollution and environmental degradation. This has contributed to an increasing recognition of biodiesel as an alternative combustible. This combustible is produced by a process of chemical transesterification. The study investigates modelling and optimal conditions for biodiesel production. It is based on five input process parameters that cause the greater environmental impact when employing used cooking oil. These input parameters are the methanol to oil molar ratio, catalyst dose, reaction temperature, reaction time and stirred speed. Biodiesel yield, high heating value and energy consumption also were considered to be output process variables, whereas global warming, acidification, human toxicity, terrestrial ecotoxicity and fresh water aquatic ecotoxicity were considered to be environmental impacts of the process. The effect on the environment of various input process parameters is often determined by life cycle assessment. Current paper provides a novel optimization of biodiesel production from waste cooking oil using multi-response surface methodology and life cycle assessment. It improves a new optimal sustainability production of biodiesel by combining the input process parameters, while minimizing the environmental impacts of the process. Four different optimization scenarios were proposed. The first scenario is one with a higher yield and higher heating value, but requires less catalyst and a lower methanol to oil molar ratio, as well as the power necessary for the chemical process. The second scenario attempts to minimize the environmental impact of the process on global warming, acidification, human toxicity, terrestrial ecotoxicity and fresh water aquatic ecotoxicity, while minimizing the methanol to oil molar ratio and the catalyst dose. In addition to considering the input process parameters and environmental impacts in the second scenario, the third scenario minimizes the power that the chemical process requires. Finally, the fourth scenario considered the same input process parameters and environmental impact as the third scenario in an effort to minimize the reaction time of the process. This fourth scenario was the one of least environmental impact in the production of biodiesel (global warming = 0.351768 kg CO2 eq.; human toxicity = 0.103402 kg 1.4-BD eq. and fresh water aquatic ecotoxicity = 0.027826 kg 1.4-BD eq.), in an efficient way ((η = 0.91374) while the calorific value of biodiesel obtained was high 42.466742 MJ/kg). The results enabled one to conclude that it is possible to optimize the chemical process in biodiesel production for a high yield and high heating value of that the biofuel, as well as a lower environmental impact.

Optimization of formulation and process conditions of chestnut-based functional beverage using response surface methodology.

Response surface methodology was used to optimize the chestnut beverage production under the effect of the independent variables including dilution rate (x 1 ), dilution temperature (x 2 ), pasteurization time (x 3 ) and pasteurization temperature (x 4 ). The experiments were based on a central composite design with linear and quadratic models employed to study the combined effects of four independent variables. The responses were selected with functional properties such as antioxidative attributes and total phenolic content. The optimal conditions (x 1 , x 2 , x 3 and x 4 ) determined for development of chestnut based functional beverage were a dilution rate of 25.19g/100 mL, a dilution temperature of 37.562°C, a pasteurization time of 24.996min. and a pasteurization temperature of 84.433°C. After comparing the predicted and experimental results, the multi-response surface methodology was more stable with a good correlation for a functional chestnut beverage.

Biosorption of Cu(II) ions as a method for the effective use of activated carbon from grape stalk waste: RMS optimization and kinetic studies

ABSTRACT This study was undertaken to examine the effect of such biosorption factors as initial Cu(II) concentration, biosorbent dosage, reaction temperature, contact time and mixing speed on the efficiency of removal Cu(II) ions from wastewater using activated carbon from grape stalk waste. In this case, Response Surface Methodology (RSM) was used in conjunction with a Box–Behnken design of experiments to predict the final Cu(II) concentration (CFin ), while considering the previously mentioned biosorption factors. In an attempt to obtain the maximum removal of final Cu(II) concentration, while minimizing energy consumption, the Multi-Response Surface Methodology (MRS) was used. Three possible optimizations were proposed for the maximum elimination of final Cu(II) in this case. The maximum (100 mg/L), minimum (2 mg/L) and intermediate (51 mg/L) values of the study were used for the initial Cu(II) concentration. The optimal values that were reached were 92.21% when the initial copper concentration was 51 mg/L and the activated carbon dose, temperature, mixing speed and reaction time, were, respectively, 0.895 g/L, 20.036°C, 105.313 rpm and 30.181 s. Also, in regard to thermodynamic studies, the experimental equilibrium data provided a good fit using the Freundlich model, whereas the kinetic data were efficiently by the pseudo-second order. These results support the use of grape stalk waste in the production of activated carbon for the removal of Cu(II) ions from water. This could help to improve the economics of treating wastewater.

Multi response surface optimization, Pareto analysis and kinetics study of microalgal post-treatment systems

ABSTRACT High concentrations of nutrients are observed in the effluent of different wastewater treatment plants, while additional costs of post-treatment systems and low-value sludge are the main reasons for releasing such effluents. The present study aims to introduce an increased procedure for simultaneous nutrient recovery and biomass production using an algae-based post-treatment technique. The procedure has been utilized by two well-known strains (Scenedesmus dimorphus and Chlorella vulgaris) cultivated in different N/P ratios (16, 62, and 108) and trace metals (0, 50%, and 100%) in a synthetic meat processing wastewater as a model to investigate effects of the factors on microalgal cultivation and nutrient removal. Pareto statistical analysis and Multi Response Surface methodology were applied to determine the priority of factors and their optimum values, respectively. The unbalanced N/P ratio and lack of trace metals were introduced as two main reasons for the significant decrease of about 60% and 120% in nutrient removal and biomass production. The optimized procedure resulted in significant increases in the removal efficiencies where 90%, 83%, and 65% were achieved for ammonium, nitrate, and phosphate, respectively. Moreover, a 72% increase in biomass production was reported in the optimal points. The results of the Pareto analysis highlighted the significant superiority (about two times) of the trace metals in removal efficiencies. Finally, experimental data has also been modelled by Verhulst logistic model that successfully described the microalgae growth. This procedure showed promising results of microalgal systems to supersede the conventional post-treatment systems.

Simultaneous on-line preconcentration and determination of toxic elements in rice and rice-based products by SPE–ICP–MS: Multiple response optimization

Simultaneous preconcentration of five toxic elements (Cd, Hg, Mn, Pb, and Sb) was carried out using a hyphenated system by on-line coupling of flow injection (FI), solid phase extraction (SPE) and inductively coupled plasma mass spectrometry (ICP–MS). The analytes were simultaneously preconcentrated on a microcolumn filled with oxidized multiwalled carbon nanotubes (ox-MWCNTs). During the method development, SPE conditions were optimized using a chemometric approach with experimental design and desirability function by multi-response surface methodology. An enrichment factor of 104 was obtained when 50 mL of sample were passed through the microcolumn. After optimizing the FI–SPE–ICP–MS system, detection limits were calculated varying from 0.8 ng L−1 for Mn to 0.09 μg L−1 for Hg. The relative standard deviations (RSD) for all elements were < 5%. For checking accuracy two standard reference materials NIST1568b (Rice Flour) and NIST 1643f (Trace Elements in Water) were analyzed and results were in good agreement with certified values. The proposed method was successfully applied to the determination of Cd, Hg, Mn, Pb and Sb in real samples of rice and rice-based products. The concentration of the analytes spanned in the range (ng g−1): Cd, 0.18–23.5; Hg, <4.6-6.0; Mn, <0.04–744; Pb, <0.16–462 and Sb, 5.9–47.

Multiresponse Optimization of Mechanical Behaviour of Calotropis gigantea/Nano-Silicon-Based Hybrid Nanocomposites under Cryogenic Environment

The utilization of natural fibre-based biodegradable polymers has expanded in the present circumstances since natural fibres are relatively inexpensive, recyclable, lighter, nonflammable, and harmless. However, hydrophilic nature is the most serious issue. To address this issue, the current study was applied to enhance the material characteristics of hybrid composites strengthened by CGF and nanosilica powder. To accomplish the mentioned goal, RSM calculated and optimized the following processing parameters using the BBD arrangement at various CGF fibre thickness (gsm), weight percent of nanosilica powder (wt. percent), and cryogenic treatment period (min). To prevent hydrophilic nature, the fibres were pretreated for four hours with a 5% alkaline solution. Deterioration models were created to analyze the material characteristics, and the optimal progression variables were determined. Based on the multiresponse surface methodology, the governable process variables for nano-silica- and CGF-based hybrid nanocomposites should be set at 3% silica, 300 gsm of CGF, and 30 minutes of cryogenic treatment. The tension, bending, and impact property correlation coefficient values ([Formula: see text]) are 0.95, 0.94, and 0.95, respectively. The above-mentioned combinations provide better water absorption and mechanical strength.

Jackknifing then model averaging: investigating the improvements to fitness to data and prediction accuracy of two-input under-fitted and just-fitted response models

The possibility of improving the fitness to data and prediction accuracy of models in a multi-response surface methodology environment of under and just-fitted ordinary least squares response models by jackknifing then combining the resultant partial estimates and the pseudo-values using arithmetic averaging or criterion-based frequentist model averaging was investigated. Jackknifing is known to reduce parametric and model bias. Model averaging is known to reduce model bidirectional bias and variance. A typical multi-response surface methodology dataset and resultant validation dataset were used as example. Results suggest that it is possible to obtain better fitness to data and prediction accuracy by jackknifing a just-fitted response model of interest and combining the resultant partial estimates using arithmetic averaging. The combining of pseudo-values using arithmetic averaging or criterion-based frequentist model averaging gave mixed results. The actual jackknife model estimators gave good performance with under-fitted models.

Experimental investigation of machining nimonic-80A alloy on wire EDM using response surface methodology

This paper aims to optimize the wire electric discharge machining (WEDM) parameters using multi response surface methodology. Experiments were performed on Nimonic 80A alloy to improve the response variables, namely material removal rate (MRR) and Kerf width (Kw). SEM analysis was carried out on the different samples obtained using different levels of input input parameters, namely, peak current, gap voltage, duty cycle and wire speed to evaluate the quality of machined surface. The influence of these parameters on MRR and Kw were determined using ANOVA. The analysis results revealed that the peak current is the main factor affecting MRR and Kw. The optimized WEDM parameters obtained using multi response function of RSM technique for machining of Nimonic 80A alloy are peak current (57A), gap voltage (90 V), duty cycle (75 µs), and wire speed (7 mm/min) of wire electrode. The characterization results show that high discharge energy results in deep craters with micro craters at low energy levels on the machined surface of the specimen. The results obtained using the proposed methodology would provide sufficient data for enhancing the machining of Nimonic 80A alloy on WEDM.

Decolorization of Reactive Black B from wastewater by electro-coagulation: optimization using multivariate RSM and ANN

Abstract The present study is aimed to model and optimize the electrocoagulation (EC) process with five important parameters for the decolorization of Reactive Black B (RBB) from simulated wastewater. A multivariate approach, response surface methodology (RSM) together with central composite design (CCD) is used to optimize process parameters such as pH (5–9), electrode gap (0.5–2.5 cm), current density (2.08–10.41 mA/cm2), process time (10–30 min), and initial dye concentration (100–500 mg/l). The predicted percentage decolorization of dye is obtained as 97.21% at optimized conditions: pH (6.8), gapping (1.3 cm), current density (8.32 mA/cm2), time (23 min), and initial dye concentration (200 mg/L), which is very close to experimental percent decolorization (98.41%). The statistical analysis of variance (ANOVA) is performed to evaluate the quadratic model (RSM), and shows good fit of experimental data with coefficient of determination R2 &gt;0.93. An Artificial Neural Network (ANN) is also used to predict the percentage decolorization and gives overall 94.96% which shows performance accuracy between the predicted and actual value of decolorization. The additional considerations of operating cost and current efficiency are also taken care to show the efficacy of EC process with mathematical tool. The sludge characteristics are determined by FE-SEM/EDX.

Optimization of Vegetable Oil-Based Biodiesels by Multi-Response Surface Methodology (MRS) using Desirability Functions

Environmental concerns associated with petroleum resources have propelled the development of sustainable and renewable alternatives to petroleum based products. Vegetable oil is one amongst the foremost abundant bio-based feedstocks. The interest in using vegetable oils and low molecular weight alcohols by direct transesterification have shown great potential as alternatives to petroleum-based diesel, and the production of bio-based diesel continues to increase. Utilization of multi-response surface methodology (MRS) for the most effective combination effect or response from the uses of input to output variables to optimize the yield and higher heating values (HHV) of biodiesels was investigated. In this work, utilizing variety of non-edible vegetable oils like castor (Ricinus communis L), jatropha (Jatropha curcas), and neem (Azadirachta indica) seeds and several process variables or inputs, including mixing time, mixing speed, process temperature and catalyst dosage to formulate high quality renewable fuels were further explored. The outputs were yield, viscosity, higher heating value, density and turbidity. The proposed optimization scenarios for biodiesel using the statistical (MRS) models was aimed to optimize the processes to achieved high conversion and higher heating values, while reducing the reaction time, turbidity, density, and viscosity in the samples. The results showed catalyst dosage as the most important variable for all the three samples. For maximum yield of 100%, the molar ratio of 6.25, catalyst of 0.75 wt.%, reaction speed of 499.99 rpm, reaction time of 19.88 min and temperature of 24.50 oC were found as optimal conditions; while the molar ratio of 5.60, catalyst of 1.01 wt.%, the reaction speed of 499.5 rpm, reaction time of 20.00 min and temperature of 35.50 oC were optimal conditions for maximum biodiesel yield.

Microencapsulation of Meyerozyma guilliermondii by spray drying using sodium alginate and soy protein isolate as wall materials: a biocontrol formulation for anthracnose disease of mango

ABSTRACT In the present work, the microencapsulation conditions by spray drying of the biocontrol agent Meyerozyma guilliermondii using the multi-response surface methodology (MRSM) were optimised. The concentration of sodium alginate and soy protein isolate, encapsulating agents, and the dryer inlet air temperature were evaluated on the percentage of yeast viability, release rate, and percentage of mycelial growth inhibition of Colletotrichum gloeosporioides isolated from mango. The optimum conditions obtained by MRSM were 0.06% sodium alginate (w/v), 3.8% soy protein isolate (w/v), and dryer inlet air temperature of 113°C. The validation of the optimal conditions allowed to obtain values of 97.8 ± 1.53% viability, the release rate of 0.124 ± 0.04 Log CFU g·h−1 and 86.4 ± 1.1% of mycelial growth inhibition. A hydratable powder formulation was produced with the microencapsulated biocontrol agent, which is considered an effective, integrated, and eco-friendly alternative to manage the control of anthracnose disease caused by C. gloeosporioides on mango fruit.

Adsorptive of Nickel in Wastewater by Olive Stone Waste: Optimization through Multi-Response Surface Methodology Using Desirability Functions

Pollution from industrial wastewater has the greatest impact on the environment due to the wide variety of wastes and materials that water can contain. These include heavy metals. Some of the technologies that are used to remove heavy metals from industrial effluents are inadequate, because they cannot reduce their concentration of the former to below the discharge limits. Biosorption technology has demonstrated its potential in recent years as an alternative for this type of application. This paper examines the biosorption process for the removal of nickel ions that are present in wastewater using olive stone waste as the biosorbent. Kinetic studies were conducted to investigate the biosorbent dosage, pH of the solution, and stirring speed. These are input variables that are frequently used to determine the efficiency of the adsorption process. This paper describes an effort to identify regression models, in which the biosorption process variables are related to the process output (i.e., the removal efficiency). It uses the Response Surface Method (RSM) and it is based on Box Benken Design experiments (BBD), in which olive stones serves as the biosorbent. Several scenarios of biosorption were proposed and demonstrated by use of the Multi-Response Surface (MRS) and desirability functions. The optimum conditions that were necessary to remove nickel when the dosage of biosorbent was the minimum (0.553 g/L) were determined to be a stirring speed of 199.234 rpm and a pH of 6.369. The maximum removal of nickel under optimized conditions was 61.73%. Therefore, the olive stone waste that was investigated has the potential to provide an inexpensive biosorbent material for use in recovering the water that the nickel has contaminated. The experimental results agree closely with what the regression models have provided. This confirms the use of MRS since this technique and enables satisfactory predictions with use of the least possible amount of experimental data.

High Density Supercritical Carbon Dioxide for the Extraction of Pesticide Residues in Onion with Multivariate Response Surface Methodology.

The excessive use of pesticides is a serious health problem due to their toxicity and bioaccumulation through the food chain. Due to the complexity of foods, the analysis of pesticides is challenging often giving large matrix effects and co-extracted compounds. To overcome this problem, a selective and “green” supercritical fluid extraction method was developed, using neat carbon dioxide as a solvent at pressures of up to 800 bars. A Box–Behnken response surface experimental design was used, with the independent variables of density (0.70−1.0 g mL−1), temperature (40−70 °C), and volume (10−40 mL) of solvent, and the dependent variable of extracted amount of pesticides. The optimum extraction condition was found at the use of 29 mL of supercritical CO2 at 0.90 g mL−1 and 53 °C (corresponding to 372 bars of pressure). It was observed that increasing the density of CO2 significantly increased the extraction recovery of endrin and 2,4′-dichlorodiphenyldichloroethane. Matrix-matched calibration curves showed satisfactory linearity (R2 ≥ 0.994), and LODs ranged from 0.2 to 2.0 ng g−1. Precision was lower than 11% and recoveries between 80%–103%. Thus, the developed method could efficiently be used for trace analysis of pesticides in complex food matrices without the use of organic solvents.

Optimization of content of components over activated carbon catalyst on CO2 reforming of methane using multi-response surface methodology

To accurately and efficiently optimize the component content of the catalyst is one important strategy to fabricate robust catalysts. By multi-response surface methodology (RSM), this study chose promising metal components (Co, Ce, and W) supported over activated carbon as a catalyst to investigate the catalytic activity of CO2–CH4 reforming. First, the center point of the center-complex design (CCD) based on RSM was determined by single-factor experiment, Co, W and Ce were loaded with 10.1 wt%, 9.7 wt%, and 9.2 wt%, respectively. Then, the three-factor and five-level CCD was exhibited. Four well-matched quadratic regression models (R2 is close to 1) were developed to gain a better understanding of the effects of the individual component content and their interactions on CH4 conversion, CO2 conversion, H2 yield, and CO yield. The results showed that W content was the most important negative parameter affecting the conversion of CH4 and CO2, while the Co and Ce content played a significant positive role in the catalyst performance. The interactive effects of all different component content imposed a significant effect on the CO2 conversion and CO yield. At last, the content optimization suggested that the optimal catalytic activity was achieved at the content of Co, W, and Ce of 10.6 wt%, 6.5 wt%, and 8.6 wt%, respectively, which was validated by a mean error of less than 2.2%.