Modeling the CO2 separation capability of poly(4

Scientific Reports volume 13, Article number: 8812 (2023) Cite this article

152 Accesses

Metrics details

Membranes are a potential technology to reduce energy consumption as well as environmental challenges considering the separation processes. A new class of this technology, namely mixed matrix membrane (MMM) can be fabricated by dispersing solid substances in a polymeric medium. In this way, the poly(4-methyl-1-pentene)-based MMMs have attracted great attention to capturing carbon dioxide (CO2), which is an environmental pollutant with a greenhouse effect. The CO2 permeability in different MMMs constituted of poly(4-methyl-1-pentene) (PMP) and nanoparticles was comprehensively analyzed from the experimental point of view. In addition, a straightforward mathematical model is necessary to compute the CO2 permeability before constructing the related PMP-based separation process. Hence, the current study employs multilayer perceptron artificial neural networks (MLP-ANN) to relate the CO2 permeability in PMP/nanoparticle MMMs to the membrane composition (additive type and dose) and pressure. Accordingly, the effect of these independent variables on CO2 permeability in PMP-based membranes is explored using multiple linear regression analysis. It was figured out that the CO2 permeability has a direct relationship with all independent variables, while the nanoparticle dose is the strongest one. The MLP-ANN structural features have efficiently demonstrated an appealing potential to achieve the highest accurate prediction for CO2 permeability. A two-layer MLP-ANN with the 3-8-1 topology trained by the Bayesian regulation algorithm is identified as the best model for the considered problem. This model simulates 112 experimentally measured CO2 permeability in PMP/ZnO, PMP/Al2O3, PMP/TiO2, and PMP/TiO2-NT with an excellent absolute average relative deviation (AARD) of lower than 5.5%, mean absolute error (MAE) of 6.87 and correlation coefficient (R) of higher than 0.99470. It was found that the mixed matrix membrane constituted of PMP and TiO2-NT (functionalized nanotube with titanium dioxide) is the best medium for CO2 separation.

Recently, the capture and sequestration of CO2 (carbon dioxide)1,2 as a practical tool against global warming and climate change have received significant interest. According to the literature, the CO2 concentration in the atmosphere since the pre-industrial era till now has dramatically increased from 280 to 420 ppm, while its maximum allowable value is 350 ppm3,4. On the other hand, it has been estimated that the CO2 concentration in the atmosphere will reach 570 ppm by the current rising level at the end of 21 century5. On this ground, several agreements are established to reduce CO2 emissions by 2050 by focusing on deploying carbon capture and storage (CCS) strategies6. To this end, different technologies, such as absorption7, adsorption8,9, cryogenic10, and membranes11 have been proposed. However, absorption as the most mature technology owns some serious drawbacks, including corrosion of equipment12, environmental side-effects13, and cost14. Cryogenic as another mature technology consumes high energy15. Moreover, introducing a water-stable adsorbent with high selectivity and loading capacity as well as proper heat of adsorption and reasonable cost for the large-scale application is still a serious challenge7,16,17. Hence, membrane technology regarding being environmentally friendly, efficient, flexible, cost, maturity, and simple is considered one of the interesting strategies for gas separation18 and pollution monitoring19. CO2 capture and sequestration not only is crucial for post-combustion applications related to flue gas for CO2/N2 separation but also is required for pre-combustion processes for developing renewable sources of energy, including biogas upgrading20 and natural gas sweetening for CO2/CH4 separation21. The recovered carbon dioxide is also possible to use as feedstock to synthesize value-added chemicals22.

Routinely, membranes are developed in natural or synthetic ways23, and the last one is categorized as organic and inorganic24. To improve the gas separation performance of conventional membranes the focus is concentrated on polymeric media25. To this end, different polymers, including siloxanes26, poly acetylenes27, polyimides28, polysulfone29, and basic silicon polymers30 are employed for different separation purposes. However, polymeric membranes still have some concerns related to their permeability31, selectivity32, and stability at high pressures33. Accordingly, nanocomposite membranes are fabricated by adding starch34, ceramic35, metal–organic framework36, carbon nanotube37, and nanoparticle38,39,40, to the membrane body.

On these grounds, Ahn et al. added silica nano samples as fillers to the polysulfone membrane to boost the performance of the developed mixed matrix membrane41. They reported inclusion of nano silica samples into the polymer structure improves the permeability. Also, Pechaf et al. applied polyimide membrane and zeolite as the MMM and assessed the permeability of He, CH4, CO2, N2, and O242. They claimed the fabricated membrane increases the permeability of CO2 and CH4, while some reduction was observed for N2 and O2 permeability. Further, Ismail et al. synthesized a mixed matrix membrane using poly-ether-sulfone and Matrimid 5218 by employing Zeolite 4A43. The study showed adding the zeolite can improve the permeability of the membrane.

Recently, machine learning (ML) models due to their flexibility, robustness, precision, and adaptability have received significant interest in a broad range of applications from engineering to medicine44,45,46,47. Pattern design, model recognition, fault detection, data mining, and function estimation are some of the main applications of ML48,49. Recently, artificial neural network (ANN)50, adaptive neuro-fuzzy inference system (ANFIS)51, support vector machine (SVM)52, and genetic programming (GP)53 have been used in the field of membrane technology. On these grounds, Rezakazemi et al. employed the ANFIS model for molecular separation in microporous membranes54. In another study, Vural et al. employed ANFIS topology for estimating the performance of a proton exchange membrane fuel cell55. In addition, Zhao et al. employed the ANN paradigm to predict the interfacial interactions and fouling in a membrane bioreactor56. They declared that the radial basis function has excellent ability to predict interfacial interactions. Further, Gasós et al. trusted on the artificial neural networks to create the maps of membrane-based CO2 separation technology18. Additionally, Kazemian et al. employed the benefits of SVM and genetic algorithm (GA) methodology to develop an algorithm for the membrane helices in amino acid sequences57.

Despite conducting many experiments on measuring CO2 permeability in pure poly(4-methyl-1-pentane) (PMP) and PMP-containing mixed membranes, no correlation has already been suggested in this field. Since permeability is a crucial factor in efficient CO2 separation by the PMP-based membranes, a reliable model is also required for its estimation. Hence, this study applies the MLP-ANN to correlate CO2 permeability in pure PMP and PMP/nanoparticle mixed matrix membranes to the filler type, nanoparticle dose, and pressure. Also, the performed relevancy analysis by the MLR (i.e., multiple linear regression) clarifies the effect of these variables on the potential level of CO2 permeability. To the best of the authors’ knowledge, this is the first attempt to predict CO2 permeability in PMP-containing membranes from some easily and always available parameters. Also, the designed MLP-ANN can help engineers fabricate a PMP-based membrane and adjust the working pressure to achieve maximum CO2 separation in various industries including gas processing, petroleum, petrochemical, as well as biogas upgrading.

As already discussed, permeability is one of the key specifications of membrane technology for gas separation, which is often experimentally measured. On the other hand, several other studies have investigated the impact of employing different nanoparticles to improve the performance of polymetric membranes to this end. Accordingly, this study has developed a robust theoretical topology to estimate the CO2 permeability in the pure PMP and PMP/nanoparticle mixed matrix membranes, which to the best of the authors’ knowledge is the first one in this area. In this way, the nanoparticle types, their weight percentage (wt%) in the fabricated membrane, and operating pressure are the independent variables to estimate the CO2 permeability in a specific membrane. Table 1 presents the main statistical features of the gathered experimental data from the literature58,59,60,61.

It is noteworthy that the literature has added up to 40 wt% of four nanoparticles (i.e., TiO2, ZnO, Al2O3, and TiO2-NT) to the PMP structure to fabricate different mixed matrix membranes. Also, 112 CO2 permeability tests have been conducted in a pressure range of 2–25 bar. The CO2 permeability of 18.01-570.90 barrer was reported in the literature for the pure PMP and PMP/ZnO, PMP/Al2O3, PMP/TiO2, and PMP/TiO2-NT mixed matrix membranes58,59,60,61.

Since this study includes both qualitative (additive type) and quantitative (nanoparticle dose and pressure) independent variables, it is also necessary to represent the earlier quantitatively. Table 2 introduces the numerical codes used in this regard.

Histograms of all independent (additive type, nanoparticle dose, and pressure) and dependent (CO2 permeability) variables are depicted in Fig. 1.

Histogram of the involved variables (additive type, nanoparticle dose, and pressure) in the modeling of CO2 permeability in PMP-nanoparticle membranes58,59,60,61.

Artificial neural networks (ANNs) as a biologically inspired computational approach is a non-linear topology, which has a high capacity for data processing in the engineering area62. Actually, the ANNs are a reduced set of concepts derived from biological neural systems based on the simulation of data processing of the human brain and nervous systems63. The ANNs have already proved a robust potential for statistical analysis in the area without a broad range of experimental values regarding their flexibility and capability62,63. In the way of deriving an ANN paradigm, it is required to specify the main independent variables that affect the output of the process. It is worth noting that the ANNs have the potential to correlate the dependent variables with the independent ones with any degree of complexity64. To this end, providing a proper dataset is necessary to design a black box for the estimation of dependent factors considering defined criteria62. Accordingly, the obtained approach develops a signal among the input and output factors, which specifies the details in different layers related to neuron interactions.

Up to date, several ANN approaches have been developed, including multi-layer perceptron (MLP-ANN)65, radial basis function (RBF-ANN)66, cascade feedforward (CFF-ANN)67, general regression (GR-ANN)68, which the MLP-ANN is the most commonly used one. Generally, the MLP-ANN is an online learning supervised procedure that employs partial fit order together with tunable synaptic weights69. On these grounds, this topology was applied in this work to estimate the permeability of CH4 and N2 in PMPs. Routinely, an MLP-ANN is developed by defining three main layers, including the input layer, the hidden layer, and the output one. In this way, the input layer is derived from the raw independent (input) values after some data processing, which has already proven their high impact on the process. Then, the outcome of this layer is introduced to the hidden layer to employ statistical analysis and mathematical treatment on the data. Afterward, the outcomes of this layer are transferred to the output layer that specifies the main results of the model. It should be considered that the major mathematical processing employed on the neurons is determined by Eq. (1)70:

here \(b\) specifies the bias of the model, which indicates the activation thresholds for input values (\(x_{r}\)), and \(\omega_{jr}\) is the weight coefficients of the model. Also, the net output of neurons (\(O_{j}\)) is received by a transfer function (\(tf\)) to calculate the neuron's output70. In this work, the hyperbolic tangent sigmoid (Eq. 2) and logarithmic sigmoid (Eq. 3), which are among the most popular transfer functions, have been incorporated in the hidden and output layers, respectively63,68:

Figure 2a,b show the general shapes of the hyperbolic tangent sigmoid and logarithmic sigmoid transfer functions, respectively. This figure indicates that the earlier provides a value between − 1 and + 1, while the latter produces a value ranging from 0 to + 1.

The hyperbolic tangent sigmoid (a) and logarithm sigmoid (b) transfer functions.

To this end, it is necessary to normalize both the independent (IV) and dependent variables (DV) into the [0 1] range using Eqs. (4) and (5), respectively.

NoD designates the number of datasets. X1, X2, and X3 indicate the normalized value of the additive type, nanoparticle dose, and pressure. Moreover, Y stands for the normalized CO2 permeability.

It is often mandatory to measure the deviation between experimental and predicted values of the dependent variable using statistical criteria. This study applies correlation coefficient (R), coefficient of determination (R2), summation of absolute error (SAE), mean absolute error (MAE), absolute average relative deviation (AARD), and mean squared error (MSE). Accordingly, Eqs. (6) to (11) present the formula of R, R2, SAE, MAE, AARD, and MSE, correspondingly71.

The above equations need experimental (\(DV^{\exp }\)) and calculated (\(DV^{cal}\)) dependent variables as well as the average value of the \(DV^{\exp }\). Equation (12) calculates this average value, i.e., \(\overline{{DV^{\exp } }}\).

This section introduces the results of relevancy analysis by MLR, MLP-ANN development, and statistical and graphical investigations of the proposed model.

Before constructing the MLP-ANN to estimate the CO2 permeability in PMP/nanoparticle membranes, the relevancy between dependent and dependent variables must be explored. The MLR is a well-known method in this field72. Equation (13) is a simple MLR model that correlates the normalized CO2 permeability (\(Y^{cal}\)) to the normalized values of the independent variables based on 112 experimental datasets.

The positive sign of the X1, X2, and X3 coefficients suggests the direct dependency of CO2 permeability on the involved independent variables. Also, the coefficient magnitude shows the strength of the relationship between the dependent and independent variables. As Fig. 3 illustrates the CO2 permeability in PMP/nanoparticle membranes has the strongest dependency on the nanoparticle dose and the weakest dependency on the additive type.

Relevancy between CO2 permeability in MMMs and additive type, nanoparticle dose, and pressure.

The observed AARD = 88.24%, R2 = 0.40145, and SAE = 7634.84 barrer between experimental CO2 permeabilities and MLR predictions show that the considered problem is mainly governed by a nonlinear model.

The accuracy of indices is calculated after de-normalizing the MLR prediction for the normalized CO2 permeability using Eq. (14).

The general topology of the MLP-ANN to relate the CO2 permeability in PMP/nanoparticle MMMs has been shown in Fig. 4.

The MLP-ANN structure to simulate CO2 permeability in PMP/nanoparticle MMMs.

This stage constructs 90 MLP-ANN approaches with different numbers of hidden neurons. Indeed, these MLP-ANN models may have one to nine neurons in their hidden layers. In addition, the MLP-ANN with a specific number of hidden neurons is trained and tested 10 different times.

Figure 5 shows the results of ranking the 90 constructed MLP-ANN models. Generally, the MLP-ANN accuracy increases (rank decreases) by increasing the number of hidden neurons. This observation is related to the increasing MLP-ANN size as well as the number of their weights and biases. The figure indicates that the second-developed MLP-ANN with eight hidden neurons (rank = 1) is the best model for estimating the CO2 permeability in PMP/nanoparticle MMMs. In addition, the 9th-built MLP-ANN with only one hidden layer is the lowest accurate model (rank = 90) for the considered task.

Overall ranking of the 90 constructed MLP-ANNs with 1–9 hidden neurons (10 models per each hidden neuron).

The best MLP-ANN is applied to accomplish all subsequent analyses and the remaining 89 models are ignored.

Figure 6 presents the general shape of the MLP-ANN approach constructed to estimate the CO2 permeability in MMMs. It can be seen that the MLP-ANN has only one hidden layer with eight neurons, i.e., 3-8-1 topology. The hyperbolic tangent sigmoid and logarithmic sigmoid transfer functions can also be seen in the hidden and output layers. It should be noted that the modeling phase of the CO2 permeability in both PMP and PMP/nanoparticle membranes is done in the MATLAB environment (Version: 2019a)73.

Topology of the best MLP-ANN73 for predicting CO2 permeability in PMP/nanoparticle membranes.

Table 3 reports the achieved accuracy of the proposed MLP-ANN in the training and testing stages. This table also shows the accuracy of the built MLP-ANN model for predicting the CO2 permeability of the overall datasets. Five statistical criteria (i.e., R, MAE, AARD, MSE, and SAE) have been used in this regard. All these accuracies are acceptable enough from the modeling point of view.

The cross-plot which graphically inspects the linear correlation between experimental and predicted values of a dependent variable is a practical method to evaluate the reliability of data-driven models. Figure 7a–c illustrate the linear correlation between experimental CO2 permeabilities and their associated calculated values by the MLP-ANN approach. Since both training and testing datasets are mainly located around the diagonal lines, the MLP-ANN reliability is approved by the visual inspection. Moreover, the closeness of the correlation coefficients of the training, testing, and all datasets to R ~ 1 (i.e., 0.99658, 0.98433, and 0.99477) is another indication of the MLP-ANN model.

Linear correlations between experimental and calculated CO2 permeability in MMMs; training (a), testing (b), and overall database (c).

The actual and predicted CO2 permeabilities in the pure PMP membranes and PMP/nanoparticles MMMs in the training, as well as testing stages are depicted in Fig. 8. This analysis justifies the outstanding performance of the MLP-ANN to model both training and testing datasets. In addition, the MLP-ANN accuracy for predicting the training (MAE = 5.28, AARD = 5.20%, MSE = 100.54, and SAE = 501.84) and testing group (MAE = 15.76, AARD = 6.88%, MSE = 444.52, and SAE = 267.84) is approved by the statistical investigation. In addition, the overall values of the MAE, AARD, MSE, and SAE are 6.87, 5.46%, 152.75, and 769.68, correspondingly.

Compatibility between experimen6tal and calculated CO2 permeability in MMMs.

Figure 9 explains the effect of alumina concentration on CO2 permeability in the PMP/Al2O3 membrane from the modeling and experimental point of view. The outstanding agreement between actual and estimated CO2 permeabilities in the PMP/Al2O3 MMMs can be easily found in this figure. The MLP-ANN also accurately learns the increasing effect of the filler dose on CO2 separation by the membrane-based process. Increasing the CO2 permeability in membranes by increasing the filler dose was also previously forecasted by the MLR relevancy investigation.

The effect of additive dose on the CO2 permeability in PMP/Al2O3 membranes (pressure = 10 bar).

The literature has related this permeability improvement to the alumina-polymer interactions and pore volume increment due to the Al2O3 presence within the polymer chain61.

The effect of working pressure on CO2 separation by the PMP/ZnO membranes with five nanoparticle concentration levels (2.5, 5, 8, 10, and 15 wt%) has been presented in Fig. 10. This figure displays both laboratory-measured CO2 permeabilities and their related MLP-ANN predictions. An excellent agreement between the experimental and modeling permeability-pressure profiles is easily observable through this investigation. The MLP-ANN also correctly identifies the pressure as well as the filler effect on CO2 permeability in PMP/ZnO mixed matrix membranes.

The effect of pressure on the CO2 permeability in PMP/ZnO membranes with different additive dosages.

As expected, the CO2 permeability in the mixed matrix membranes rises by increasing the working pressure. This observation is in a direct relationship with the driving force improvement due to the pressure enhancement.

The effect of filler type (ZnO, Al2O3, TiO2, and TiO2-NT) on the CO2 separation ability of PMP-based membranes in the same working pressure is illustrated in Fig. 11. It can be seen that different fillers represent various roles in CO2-MMM interaction. Indeed, the PMP/TiO2 and PMP-TiO2-NT provide the CO2 molecule with minimum and maximum permeabilities within the membrane structure. The literature justified the higher CO2 permeability in PMP-TiO2-NT to the free volume expansion and porosity increase due to the functionalized nanoparticle presence in the membrane body60.

The effect of additive type on the CO2 permeability in PMP/nanoparticle membranes.

This study uses a two-step methodology, i.e., multiple linear regression and multilayer perceptron artificial neural networks to simulate carbon dioxide permeability in mixed matrix membranes. The carbon dioxide permeability in pure poly(4-methyl-1-pentene) and PMP/nanoparticle membranes (i.e., PMP/ZnO, PMP/Al2O3, PMP/TiO2, and PMP/TiO2-NT) has been studied based on 112 experimental datasets collected from the literature. The multiple linear regression method applies to anticipate the dependency of the carbon dioxide permeability on the membrane composition (additive type and dose) and pressure. This method shows that the carbon dioxide permeability is directly related to all independent variables and it has the strongest correlation with the nanoparticle dose in membrane structure. The MLP-ANN is then utilized to construct a non-linear approach to estimate the carbon dioxide permeability as a function of additive type, nanoparticle dose, and pressure. This MLP-ANN with the 3-8-1 topology predicted 112 experimental carbon dioxide permeabilities in the involved MMMs with excellent accuracy (i.e., R = 0.99477, MAE = 6.87, AARD = 5.46%, MSE = 152.75, and SAE = 769.68). The modeling results clarify that the PMP/TiO2-NT has a better carbon dioxide separation than the PMP/ZnO, PMP/Al2O3, and PMP/TiO2 mixed matrix membranes. Finally, the obtained results in this work demonstrated the excellent potential of the ANN for estimating the separation factors of mixed matrix membranes for carbon capture and sequestration applications.

All the literature datasets analyzed in this study are available at a reasonable request from the corresponding author (S.A. Abdollahi).

Wennersten, R., Sun, Q. & Li, H. The future potential for Carbon Capture and Storage in climate change mitigation—An overview from perspectives of technology, economy and risk. J. Clean. Prod. 103, 724–736 (2015).

Article CAS Google Scholar

Du, L., Lu, T. & Li, B. CO2 capture and sequestration in porous media with SiO2 aerogel nanoparticle-stabilized foams. Fuel 324, 124661 (2022).

Article CAS Google Scholar

Karimi, M. et al. CO2 capture in chemically and thermally modified activated carbons using breakthrough measurements: experimental and modeling study. Ind. Eng. Chem. Res. 57, 11154–11166 (2018).

Article CAS Google Scholar

Karimi, M. et al. MIL-160 (Al) as a candidate for biogas upgrading and CO2 capture by adsorption processes. Ind. Eng. Chem. Res. 62, 5216–5229 (2023).

Article CAS Google Scholar

Change, I. C. Impacts, Adaptation, and Vulnerability. Working Group II Contribution to the IPCC Sixth Assessment Report of the Intergovernmental Panel on Climate Change; Pötner, H. O., Roberts, DC, Tignor, M., Poloczanska, ES, Mintenbeck, K., Ale, A., Eds (2022).

Lu, J., Chen, H. & Cai, X. From global to national scenarios: Exploring carbon emissions to 2050. Energy Strateg. Rev. 41, 100860 (2022).

Article Google Scholar

Yu, C.-H., Huang, C.-H. & Tan, C.-S. A review of CO2 capture by absorption and adsorption. Aerosol Air Qual. Res. 12, 745–769 (2012).

Article CAS Google Scholar

Karimi, M., Shirzad, M., Silva, J. A. C. & Rodrigues, A. E. Carbon dioxide separation and capture by adsorption: A review. Environ. Chem. Lett. https://doi.org/10.1007/s10311-023-01589-z (2023).

Article Google Scholar

Xi, M. et al. Predicted a honeycomb metallic BiC and a direct semiconducting Bi2C monolayer as excellent CO2 adsorbents. Chin. Chem. Lett. 33, 2595–2599 (2022).

Article CAS Google Scholar

Xu, G. et al. A novel CO2 cryogenic liquefaction and separation system. Energy 42, 522–529 (2012).

Article CAS Google Scholar

Rafiq, S. et al. Surface tuning of silica by deep eutectic solvent to synthesize biomass derived based membranes for gas separation to enhance the circular bioeconomy. Fuel 310, 122355 (2022).

Article Google Scholar

Zhao, B. et al. Study on corrosion in CO2 chemical absorption process using amine solution. Energy Procedia 4, 93–100 (2011).

Article ADS CAS Google Scholar

Lamy-Mendes, A. et al. Amine modification of silica aerogels/xerogels for removal of relevant environmental pollutants. Molecules 24, 3701 (2019).

Article CAS PubMed PubMed Central Google Scholar

Lu, W., Bosch, M., Yuan, D. & Zhou, H. Cost-effective synthesis of amine-tethered porous materials for carbon capture. Chemsuschem 8, 433–438 (2015).

Article CAS PubMed Google Scholar

Song, C. et al. Reducing the energy consumption of membrane-cryogenic hybrid CO2 capture by process optimization. Energy 124, 29–39 (2017).

Article CAS Google Scholar

Karimi, M., Shirzad, M., Silva, J. A. C. & Rodrigues, A. E. Biomass/biochar carbon materials for CO2 capture and sequestration by cyclic adsorption processes: A review and prospects for future directions. J. CO2 Util. 57, 101890 (2022).

Article CAS Google Scholar

Siegelman, R. L., Milner, P. J., Kim, E. J., Weston, S. C. & Long, J. R. Challenges and opportunities for adsorption-based CO2 capture from natural gas combined cycle emissions. Energy Environ. Sci. 12, 2161–2173 (2019).

Article CAS PubMed PubMed Central Google Scholar

Gasós, A., Becattini, V., Brunetti, A., Barbieri, G. & Mazzotti, M. Process performance maps for membrane-based CO2 separation using artificial neural networks. Int. J. Greenh. Gas Control 122, 103812 (2023).

Article Google Scholar

Lin, X. et al. Membrane inlet mass spectrometry method (REOX/MIMS) to measure 15N-nitrate in isotope-enrichment experiments. Ecol. Indic. 126, 107639 (2021).

Article CAS Google Scholar

Miltner, M., Makaruk, A. & Harasek, M. Review on available biogas upgrading technologies and innovations towards advanced solutions. J. Clean. Prod. 161, 1329–1337 (2017).

Article CAS Google Scholar

Uddin, M. W. & Hägg, M.-B. Effect of monoethylene glycol and triethylene glycol contamination on CO2/CH4 separation of a facilitated transport membrane for natural gas sweetening. J. Memb. Sci. 423, 150–158 (2012).

Article Google Scholar

Zhao, C., Xi, M., Huo, J., He, C. & Fu, L. Computational design of BC3N2 based single atom catalyst for dramatic activation of inert CO2 and CH4 gasses into CH3COOH with ultralow CH4 dissociation barrier. Chin. Chem. Lett. 34, 107213 (2023).

Article CAS Google Scholar

Ahmad, A. et al. Recent trends and challenges with the synthesis of membranes: Industrial opportunities towards environmental remediation. Chemosphere 306, 135634. https://doi.org/10.1016/j.chemosphere.2022.135634 (2022).

Article ADS CAS PubMed Google Scholar

Yeo, Z. Y., Chai, S.-P., Zhu, P. W. & Mohamed, A. R. An overview: synthesis of thin films/membranes of metal organic frameworks and its gas separation performances. RSC Adv. 4, 54322–54334 (2014).

Article ADS CAS Google Scholar

Dong, G., Li, H. & Chen, V. Challenges and opportunities for mixed-matrix membranes for gas separation. J. Mater. Chem. A 1, 4610–4630 (2013).

Article CAS Google Scholar

Jee, K. Y. & Lee, Y. T. Preparation and characterization of siloxane composite membranes for n-butanol concentration from ABE solution by pervaporation. J. Memb. Sci. 456, 1–10 (2014).

Article CAS Google Scholar

Budd, P. M. & McKeown, N. B. Highly permeable polymers for gas separation membranes. Polym. Chem. 1, 63–68 (2010).

Article CAS Google Scholar

Chen, X. Y., Hoang, V.-T., Rodrigue, D. & Kaliaguine, S. Optimization of continuous phase in amino-functionalized metal–organic framework (MIL-53) based co-polyimide mixed matrix membranes for CO2/CH4 separation. RSC Adv. 3, 24266–24279 (2013).

Article ADS CAS Google Scholar

Pereira, V. R. et al. Preparation and performance studies of polysulfone-sulfated nano-titania (S-TiO2) nanofiltration membranes for dye removal. RSC Adv. 5, 53874–53885 (2015).

Article ADS CAS Google Scholar

Bhadra, P. et al. Selective transportation of charged ZnO nanoparticles and microorganism dialysis through silicon nanoporous membranes. J. Memb. Sci. 503, 16–24 (2016).

Article CAS Google Scholar

Suleman, M. S., Lau, K. K. & Yeong, Y. F. Plasticization and swelling in polymeric membranes in CO2 removal from natural gas. Chem. Eng. Technol. 39, 1604–1616 (2016).

Article CAS Google Scholar

Clarizia, G., Algieri, C. & Drioli, E. Filler-polymer combination: A route to modify gas transport properties of a polymeric membrane. Polymer (Guildf). 45, 5671–5681 (2004).

Article CAS Google Scholar

Ali, A., Mubashir, M., Abdulrahman, A. & Phelan, P. E. Ultra-permeable intercalated metal-induced microporous polymer nano-dots rooted smart membrane for environmental remediation. Chemosphere 306, 135482 (2022).

Article ADS CAS PubMed Google Scholar

Yang, G. C. C. & Tsai, C.-M. Effects of starch addition on characteristics of tubular porous ceramic membrane substrates. Desalination 233, 129–136 (2008).

Article CAS Google Scholar

Maguire-Boyle, S. J. et al. Superhydrophilic functionalization of microfiltration ceramic membranes enables separation of hydrocarbons from frac and produced water. Sci. Rep. 7, 12267 (2017).

Article ADS PubMed PubMed Central Google Scholar

Lee, J.-Y., Tang, C. Y. & Huo, F. Fabrication of porous matrix membrane (PMM) using metal-organic framework as green template for water treatment. Sci. Rep. 4, 1–5 (2014).

CAS Google Scholar

Ismail, A. F., Goh, P. S., Sanip, S. M. & Aziz, M. Transport and separation properties of carbon nanotube-mixed matrix membrane. Sep. Purif. Technol. 70, 12–26 (2009).

Article CAS Google Scholar

Talukder, M. E. et al. Ag nanoparticles immobilized sulfonated polyethersulfone/polyethersulfone electrospun nanofiber membrane for the removal of heavy metals. Sci. Rep. 12, 5814 (2022).

Article ADS CAS PubMed PubMed Central Google Scholar

Xue, B. et al. An AuNPs/mesoporous NiO/nickel foam nanocomposite as a miniaturized electrode for heavy metal detection in groundwater. Engineering. https://doi.org/10.1016/j.eng.2022.06.005 (2022).

Article Google Scholar

Wang, Z. et al. Enhanced denitrification performance of Alcaligenes sp TB by Pd stimulating to produce membrane adaptation mechanism coupled with nanoscale zero-valent iron. Sci. Total Environ. 708, 135063 (2020).

Article ADS CAS PubMed Google Scholar

Ahn, J., Chung, W.-J., Pinnau, I. & Guiver, M. D. Polysulfone/silica nanoparticle mixed-matrix membranes for gas separation. J. Memb. Sci. 314, 123–133 (2008).

Article CAS Google Scholar

Pechar, T. W., Tsapatsis, M., Marand, E. & Davis, R. Preparation and characterization of a glassy fluorinated polyimide zeolite-mixed matrix membrane. Desalination 146, 3–9 (2002).

Article CAS Google Scholar

Ismail, A. F., Rahim, R. A. & Rahman, W. Characterization of polyethersulfone/Matrimid® 5218 miscible blend mixed matrix membranes for O2/N2 gas separation. Sep. Purif. Technol. 63, 200–206 (2008).

Article CAS Google Scholar

Tang, F., Niu, B., Zong, G., Zhao, X. & Xu, N. Periodic event-triggered adaptive tracking control design for nonlinear discrete-time systems via reinforcement learning. Neural Netw. 154, 43–55 (2022).

Article PubMed Google Scholar

Si, Z., Yang, M., Yu, Y. & Ding, T. Photovoltaic power forecast based on satellite images considering effects of solar position. Appl. Energy 302, 117514 (2021).

Article Google Scholar

Guedes, I. A. et al. New machine learning and physics-based scoring functions for drug discovery. Sci. Rep. 11, 1–19 (2021).

Article MathSciNet Google Scholar

Cheng, F., Liang, H., Niu, B., Zhao, N. & Zhao, X. Adaptive neural self-triggered bipartite secure control for nonlinear MASs subject to DoS attacks. Inf. Sci. (Ny) 631, 256–270 (2023).

Article Google Scholar

Bansal, M., Goyal, A. & Choudhary, A. A comparative analysis of K-Nearest Neighbour, Genetic, Support Vector Machine, Decision Tree, and Long Short Term Memory algorithms in machine learning. Decis. Anal. J. 3, 100071 (2022).

Article Google Scholar

Li, Z., Wang, J., Huang, J. & Ding, M. Development and research of triangle-filter convolution neural network for fuel reloading optimization of block-type HTGRs. Appl. Soft Comput. https://doi.org/10.1016/j.asoc.2023.110126 (2023).

Article PubMed Google Scholar

Dragoi, E.-N. & Vasseghian, Y. Modeling of mass transfer in vacuum membrane distillation process for radioactive wastewater treatment using artificial neural networks. Toxin Rev. 40, 1526–1535 (2021).

Article CAS Google Scholar

Rezakazemi, M., Dashti, A., Asghari, M. & Shirazian, S. H2-selective mixed matrix membranes modeling using ANFIS, PSO-ANFIS, GA-ANFIS. Int. J. Hydrogen Energy 42, 15211–15225 (2017).

Article CAS Google Scholar

Karimi, M., Hosin Alibak, A., Seyed Alizadeh, S. M., Sharif, M. & Vaferi, B. Intelligent modeling for considering the effect of bio-source type and appearance shape on the biomass heat capacity. Meas. J. Int. Meas. Confed. 189, 110529 (2022).

Article Google Scholar

Chamani, H. et al. CFD-based genetic programming model for liquid entry pressure estimation of hydrophobic membranes. Desalination 476, 114231 (2020).

Article CAS Google Scholar

Rezakazemi, M., Mosavi, A. & Shirazian, S. ANFIS pattern for molecular membranes separation optimization. J. Mol. Liq. 274, 470–476 (2019).

Article CAS Google Scholar

Vural, Y., Ingham, D. B. & Pourkashanian, M. Performance prediction of a proton exchange membrane fuel cell using the ANFIS model. Int. J. Hydrogen Energy 34, 9181–9187 (2009).

Article CAS Google Scholar

Zhao, Z. et al. Prediction of interfacial interactions related with membrane fouling in a membrane bioreactor based on radial basis function artificial neural network (ANN). Bioresour. Technol. 282, 262–268 (2019).

Article CAS PubMed Google Scholar

Kazemian, H. B., White, K. & Palmer-Brown, D. Applications of evolutionary SVM to prediction of membrane alpha-helices. Expert Syst. Appl. 40, 3412–3420 (2013).

Article Google Scholar

Saeedi Dehaghani, A. H. & Pirouzfar, V. Preparation of high-performance membranes derived from poly (4-methyl-1-pentene)/zinc oxide particles. Chem. Eng. Technol. 40, 1693–1701 (2017).

Article CAS Google Scholar

Alihosseini, A., Zergani, D. & Saeedi Dehaghani, A. H. Optimization of parameters affecting separation of gas mixture of O2, N2, CO2 and CH4 by PMP membrane modified with TiO2, ZnO and Al2O3 nanoparticles. Polyolefins J. 7, 13–24 (2019).

Google Scholar

Saeedi Dehaghani, A. H., Pirouzfar, V. & Alihosseini, A. Novel nanocomposite membranes-derived poly (4-methyl-1-pentene)/functionalized titanium dioxide to improve the gases transport properties and separation performance. Polym. Bull. 77, 6467–6489 (2020).

Article CAS Google Scholar

Nematollahi, M. H., Dehaghani, A. H. S., Pirouzfar, V. & Akhondi, E. Mixed matrix membranes comprising PMP polymer with dispersed alumina nanoparticle fillers to separate CO2/N2. Macromol. Res. 24, 782–792 (2016).

Article CAS Google Scholar

Guidotti, R. et al. A survey of methods for explaining black box models. ACM Comput. Surv. 51, 1–42 (2018).

Article Google Scholar

Leperi, K. T., Yancy-Caballero, D., Snurr, R. Q. & You, F. 110th anniversary: surrogate models based on artificial neural networks to simulate and optimize pressure swing adsorption cycles for CO2 capture. Ind. Eng. Chem. Res. 58, 18241–18252 (2019).

Article CAS Google Scholar

Waqas, S. et al. SVM and ANN modelling approach for the optimization of membrane permeability of a membrane rotating biological contactor for wastewater treatment. Membranes (Basel). 12, 821 (2022).

Article CAS PubMed PubMed Central Google Scholar

Ke, K.-C. & Huang, M.-S. Quality prediction for injection molding by using a multilayer perceptron neural network. Polymers (Basel). 12, 1812 (2020).

Article CAS PubMed Central Google Scholar

Pu, L., Li, Y., Gao, P., Zhang, H. & Hu, J. A photosynthetic rate prediction model using improved RBF neural network. Sci. Rep. 12, 9563 (2022).

Article ADS CAS PubMed Central Google Scholar

Ren, K., Jiao, Z., Wu, X.-L. & Han, H.-G. Multivariable identification of membrane fouling based on compacted cascade neural network. Chin. J. Chem. Eng. 53, 37–45 (2023).

Article Google Scholar

Fulcher, J. A. A comparative review of commercial ANN simulators. Comput. Stand. interfaces 16, 241–251 (1994).

Article Google Scholar

Curteanu, S. & Cartwright, H. Neural networks applied in chemistry. I. Determination of the optimal topology of multilayer perceptron neural networks. J. Chemom. 25, 527–549 (2011).

Article CAS Google Scholar

Díez, J.-L., Masip-Moret, V., Santafé-Moros, A. & Gozálvez-Zafrilla, J. M. Comparison of artificial intelligence control strategies for a peristaltically pumped low-pressure driven membrane process. Membranes (Basel). 12, 883 (2022).

Article PubMed PubMed Central Google Scholar

Abdollahzadeh, M. et al. Estimating the density of deep eutectic solvents applying supervised machine learning techniques. Sci. Rep. 12, 1–16 (2022).

Article Google Scholar

Wang, J. et al. Prediction of CO2 solubility in deep eutectic solvents using random forest model based on COSMO-RS-derived descriptors. Green Chem. Eng. 2, 431–440 (2021).

Article Google Scholar

MATLAB and Artificial Neural Networks Toolbox (Release 2019a), The MathWorks, Inc., Natick, Massachusetts, United States. (2019).

Download references

Faculty of Mechanical Engineering, University of Tabriz, Tabriz, Iran

Seyyed Amirreza Abdollahi & Seyyed Faramarz Ranjbar

You can also search for this author in PubMed Google Scholar

You can also search for this author in PubMed Google Scholar

S.A.A.: preparing the original draft, collecting the literature data, data curation, model construction, formal analysis. S.F.R.: preparing the original draft, relevancy analysis, conceptualization, final approval, supervision.

Correspondence to Seyyed Amirreza Abdollahi.

The authors declare no competing interests.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and Permissions

Abdollahi, S.A., Ranjbar, S.F. Modeling the CO2 separation capability of poly(4-methyl-1-pentane) membrane modified with different nanoparticles by artificial neural networks. Sci Rep 13, 8812 (2023). https://doi.org/10.1038/s41598-023-36071-x

Download citation

Received: 22 March 2023

Accepted: 29 May 2023

Published: 31 May 2023

DOI: https://doi.org/10.1038/s41598-023-36071-x

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.