Influence of machine learning membership functions and degree of membership function on each input parameter for simulation of reactors

To understand impact of input and output parameters during optimization and degree of complexity, in the current study we numerically designed a bubble column reactor with a single sparger in the middle of the reactor. After that, some input and output parameters were selected in the post-processing of the numerical method, and then the machine learning observation started to investigate the level of complexity and impact of each input on output parameters. The adaptive neuro-fuzzy inference system (ANFIS) method was exploited as a machine learning approach to analyze the gas-liquid flow in the reactor. The ANFIS method was used as a machine learning approach to simulate the flow of a 3D (three-dimensional) bubble column reactor. This model was also used to analyze the influence of input and output parameters together. More specifically, by analyzing the degree of membership functions as a function of each input, the level of complexity of gas fraction was investigated as a function of computing nodes (X, Y, and Z directions). The results showed that a higher number of membership functions results in a better understanding of the process and higher model accuracy and prediction capability. X and Y computing nodes have a similar impact on the gas fraction, while Z computing points (height of reactor) have a uniform distribution of membership function across the column. Four membership functions (MFs) in each input parameter are insufficient to predict the gas fraction in the 3D bubble column reactor. However, by adding two membership functions, all features of gas fraction in the 3D reactor can be captured by the machine learning algorithm. Indeed, the degree of MFs was considered as a function of each input parameter and the effective parameter was found based on the impact of MFs on the output.

High performance ozone based advanced oxidation processes catalyzed with novel argon plasma treated iron oxyhydroxide hydrate for phenazopyridine degradation

The present study has focused on the degradation of phenazopyridine (PhP) as an emerging contaminant through catalytic ozonation by novel plasma treated natural limonite (FeOOH·xH₂O, NL) under argon atmosphere (PTL/Ar). The physical and chemical characteristics of samples were evaluated with different analyses. The obtained results demonstrated higher surface area for PTL/Ar and negligible change in crystal structure, compared to NL. It was found that the synergistic effect between ozone and PTL/Ar nanocatalyst was led to highest PhP degradation efficiency. The kinetic study confirmed the pseudo-first-order reaction for the PhP degradation processes included adsorption, peroxone and ozonation, catalytic ozonation with NL and PTL/Ar. Long term application (6 cycles) confirmed the high stability of the PTL/Ar. Moreover, different organic and inorganic salts as well as the dissolved ozone concentration demonstrated the predominant role of hydroxyl radicals and superoxide radicals in PhP degradation by catalytic Ozonation using PTL/Ar. The main produced intermediates during PhP oxidation by PTL/Ar catalytic ozonation were identified using LC–(+ESI)–MS technique. Finally, the negligible iron leaching, higher mineralization rate, lower electrical energy consumption and excellent catalytic activity of PTL/Ar samples demonstrate the superior application of non-thermal plasma for treatment of NL.

Experimental and thermodynamic modeling decitabine anti cancer drug solubility in supercritical carbon dioxide

Design and development of efficient processes for continuous manufacturing of solid dosage oral formulations is of crucial importance for pharmaceutical industry in order to implement the Quality-by-Design paradigm. Supercritical solvent-based manufacturing can be utilized in pharmaceutical processing owing to its inherent operational advantages. However, in order to evaluate the possibility of supercritical processing for a particular medicine, solubility measurement needs to be carried out prior to process design. The current work reports a systematic solubility analysis on decitabine as an anti-cancer medicine. The solvent is supercritical carbon dioxide at different conditions (temperatures and pressures), while gravimetric technique is used to obtain the solubility data for decitabine. The results indicated that the solubility of decitabine varies between 2.84 × 10^–05 and 1.07 × 10^–03 mol fraction depending on the temperature and pressure. In the experiments, temperature and pressure varied between 308–338 K and 12–40 MPa, respectively. The solubility of decitabine was plotted against temperature and pressure, and it turned out that the solubility had direct relation with the pressure due to the effect of pressure on solvating power of solvent. The effect of temperature on solubility was shown to be dependent on the cross-over pressure. Below the cross-over pressure, there is a reverse relation between temperature and solubility, while a direct relation was observed above the cross-over pressure (16 MPa). Theoretical study was carried out to correlate the solubility data using several thermodynamic-based models. The fitting and model calibration indicated that the examined models were of linear nature and capable to predict the measured decitabine solubilities with the highest average absolute relative deviation percent (AARD %) of 8.9%.

Predicting Air Superficial Velocity of Two-Phase Reactors Using ANFIS and CFD

In predicting the turbulence property of gas (bubble) flow in the domain of continuous fluid and liquid, the integration of machine learning and computational fluid dynamics (CFD) methods reduces the overall computational time. This combination enables us to see the effective input parameters in the engineering process and the impact of operating conditions on final outputs, such as gas hold-up, heat and mass transfer, and the flow regime (uniform bubble distribution or nonuniform bubble properties). This paper uses the combination of machine learning and single-size calculation of the Eulerian method to estimate the gas flow distribution in the continuous liquid fluid. To present the machine-learning method besides the Eulerian method, an adaptive neuro-fuzzy inference system (ANFIS) is used to train the CFD finding and then estimate the flow based on the machine-learning method. The gas velocity and turbulent eddy dissipation rate are trained throughout the bubble column reactor (BCR) for each CFD node, and the artificial BCR is predicted by the ANFIS method. This smart reactor can represent the artificial CFD of the BCR, resulting in the reduction of expensive numerical simulations. The results showed that the number of inputs could significantly change this method's accuracy, representing the intelligence of method in the learning data set. Additionally, the membership function specifications can impact the accuracy, particularly, when the process is trained with different inputs. The turbulent eddy dissipation rate can also be predicted by the ANFIS method with a similar model pattern for air superficial gas velocity.

Controlled release evaluation of paracetamol loaded amine functionalized mesoporous silica KCC1 compared to microcrystalline cellulose based tablets

In the pharmaceutical manufacturing, drug release behavior development is remained as one of the main challenges to improve the drug effectiveness. Recently, more focus has been done on using mesoporous silica materials as drug carriers for prolonged and superior control of drug release in human body. In this study, release behavior of paracetamol is developed using drug-loaded KCC-1-NH2 mesoporous silica, based on direct compaction method for preparation of tablets. The purpose of this study is to investigate the utilizing of pure KCC-1 mesoporous silica (KCC-1) and amino functionalized KCC-1 (KCC-1-NH2) as drug carriers in oral solid dosage formulations compared to common excipient, microcrystalline cellulose (MCC), to improve the control of drug release rate by manipulating surface chemistry of the carrier. Different formulations of KCC-1 and KCC-NH2 are designed to investigate the effect of functionalized mesoporous silica as carrier on drug controlled-release rate. The results displayed the remarkable effect of KCC-1-NH2 on drug controlled-release in comparison with the formulation containing pure KCC-1 and formulation including MCC as reference materials. The pure KCC-1 and KCC-1-NH2 are characterized using different evaluation methods such as FTIR, SEM, TEM and N2 adsorption analysis.

Pressure and temperature predictions of Al2O3/water nanofluid flow in a porous pipe for different nanoparticles volume fractions: combination of CFD and ACOFIS

Artificial intelligence (AI) techniques have illustrated significant roles in finding general patterns of CFD (Computational fluid dynamics) results. This study is conducted to develop combination of the ant colony optimization (ACO) algorithm with the fuzzy inference system (ACOFIS) for learning the CFD results of a physical case study. This binary join of the ACOFIS and CFD was used for pressure and temperature predictions of Al₂O₃/water nanofluid flow in a heated porous pipe. The intelligence of ACOFIS is investigated for different input numbers and pheromone effects, as the ant colony tuning parameter. The results showed that the intelligence of the ACOFIS could be found for three inputs (x and y nodes coordinates and nanoparticles fraction) and the pheromone effect of 0.1. At the system intelligence, the ACOFIS could predict the pressure and temperature of the nanofluid on any values of the nanoparticles fraction between 0.5 and 2%. Comparing the ANFIS and the ACOFIS, it was shown that both methods could reach the same accuracy in predictions of the nanofluid pressure and temperature. The root mean square error (RMSE) of the ACOFIS (~ 1.3) was a little more than that of the ANFIS (~ 0.03), while the total process time of the ANFIS (~ 213 s) was a bit more than that of the ACOFIS (~ 198 s). The AI algorithms process time (less than 4 min) shows their ability in the reduction of CFD modeling calculations and expenses.

A molecular scale analysis of TEMPO-oxidation of native cellulose molecules

The native cellulose, through TEMPO (2,2,6,6-tetramethylpiperidine-1-oxyl radical)-mediated oxidation, can be converted into individual fibers. It has been observed that oxidized fibers disperse completely and individually in water. It is believed that electrostatic repulsive forces might be responsible for such observations. In order to study the TEMPO-oxidation of cellulose molecules, we used Density Functional Theory (DFT) calculations and Flory-Huggins theory combined with molecular dynamics (MD). The surface electrostatic potential in native cellulose and TEMPO-oxidized cellulose were calculated using DFT calculations. We found that TEMPO-oxidized cellulose accommodates a threefold screw conformation where the negatively charged (–COO–) functional groups are pointed away from the surface in all spatial directions. This spatial orientation causes that TEMPO-oxidized cellulose molecules repulse each other due to strong negatively charged surface. At the same time, the spatial orientation increases the hydrophilicity in TEMPO-oxidized cellulose molecules. These observations explain the improved dispersion in water and separability of TEMPO-oxidized cellulose molecules. We obtained large and positive Flory–Huggins interaction parameters for TEMPO-oxidized cellulose molecules indicating their higher dispersion once in water.

Evaluation of product of two sigmoidal membership functions (psigmf) as an ANFIS membership function for prediction of nanofluid temperature

A nanofluid containing water and nanoparticles made of copper (Cu) inside a cavity with square shape is simulated utilizing the computational fluid dynamics (CFD) approach. The nanoparticles made up 15% of the nanofluid. By performing the simulation, the CFD output is characterized by the coordinates in the x, y, nanofluid temperature, and velocity in the y-direction that these outputs are obtained for different physical time iterations. Moreover, the CFD outputs are examined by one of the artificial techniques, i.e. adaptive network-based fuzzy inference system (ANFIS). For this purpose, the data was clustered via grid partition clustering, and the type of membership functions (MFs) was chosen product of two sigmoidal membership functions (psigmf). After reaching 99.9% of intelligence in ANFIS, the nanofluid temperature is predicted for the entire data, which are included in the learning processes. The results showed that the method of ANFIS can predict the thermal properties in different physical times at different computing points without having a training background at those times. Additionally, this study shows that with three membership functions at each input, the model’s accuracy is higher than four functions.

Liquid temperature prediction in bubbly flow using ant colony optimization algorithm in the fuzzy inference system as a trainer

In the current research paper a novel hybrid model combining first-principle and artificial intelligence (AI) was developed for simulation of a chemical reactor. We study a 2-dimensional reactor with heating sources inside it by using computational fluid dynamics (CFD). The type of considered reactor is bubble column reactor (BCR) in which a two-phase system is created. Results from CFD were analyzed in two different stages. The first stage, which is the learning stage, takes advantage of the swarm intelligence of the ant colony. The second stage results from the first stage, and in this stage, the predictions are according to the previous stage. This stage is related to the fuzzy logic system, and the ant colony optimization learning framework is build-up this part of the model. Ants movements or swarm intelligence of ants lead to the optimization of physical, chemical, or any kind of processes in nature. From point to point optimization, we can access a kind of group optimization, meaning that a group of data is studied and optimized. In the current study, the swarm intelligence of ants was used to learn the data from CFD in different parts of the BCR. The learning was also used to map the input and output data and find out the complex connection between the parameters. The results from mapping the input and output data show the full learning framework. By using the AI framework, the learning process was transferred into the fuzzy logic process through membership function specifications; therefore, the fuzzy logic system could predict a group of data. The results from the swarm intelligence of ants and fuzzy logic suitably adapt to CFD results. Also, the ant colony optimization fuzzy inference system (ACOFIS) model is employed to predict the temperature distribution in the reactor based on the CFD results. The results indicated that instead of solving Navier–Stokes equations and complex solving procedures, the swarm intelligence could be used to predict a process. For better comparisons and assessment of the ACOFIS model, this model is compared with the genetic algorithm fuzzy inference system (GAFIS) and Particle swarm optimization fuzzy inference system (PSOFIS) method with regards to model accuracy, pattern recognition, and prediction capability. All models are at a similar level of accuracy and prediction ability, and the prediction time for all models is less than one second. The results show that the model’s accuracy with low computational learning time can be achieved with the high number of CIR (0.5) when the number of inputs ≥ 4. However, this finding is vice versa, when the number of inputs < 4. In this case, the CIR number should be 0.2 to achieve the best accuracy of the model. This finding could also highlight the importance of sensitivity analysis of tuning parameters to achieve an accurate model with a cost-effective computational run.

Computational Modeling of Transport in Porous Media Using an Adaptive Network-Based Fuzzy Inference System

This investigation is conducted to study the integration of the artificial intelligence (AI) method with computational fluid dynamics (CFD). The case study is hydrodynamic and heat-transfer analyses of water flow in a metal foam tube under a constant wall heat flux (i.e., 55 kW/m²). The adaptive network-based fuzzy inference system (ANFIS) is an AI method. A 3D CFD model is established in ANSYS-FLUENT software. The velocity of the fluid in the x-direction (Ux) is considered as an output of the ANFIS. The x, y, and z coordinates of the node's location are added to the ANFIS step-by-step to achieve the best intelligence. The number and type of membership functions (MFs) are changed in each step. The training process is done by the CFD results on the tube cross-sections at different lengths (i.e., z = 0.1, 0.2, 0.3, 0.4, 0.6, 0.7, 0.8, and 0.9), while all data (including z = 0.5) are selected for the testing process. The results showed that the ANFIS reaches the best intelligence with all three inputs, five MFs, and "gbellmf"-type MF. At this condition, the regression number is close to 1.

High-performance hybrid modeling chemical reactors using differential evolution based fuzzy inference system

Bubbly flow behavior simulation in two-phase chemical reactors such bubble column type reactors is widely employed for chemical industry purposes. The computational fluid dynamics (CFD) approach has been employed by engineers and researchers for modeling these types of chemical reactors. In spite of the CFD robustness for simulating transport phenomena and chemical reactions in these reactors, this approach has been known as expensive for modeling such turbulent complex flows. Artificial intelligence (AI) algorithm of the adaptive network-based fuzzy inference system (ANFIS) are largely understood and utilized for the CFD approach optimization. In this hybrid approach, the CFD findings are learned by AI algorithms like ANFIS to save computational time and expenses. Once the pattern of the CFD results have been captured by the AI model, this hybrid model can be then used for process simulation and optimization. As such, there is no need for further simulations of new conditions. The objective of this paper is to obviate the need for expensive CFD computations for two-phase flows in chemical reactors via coupling CFD data to an AI algorithm, i.e., differential evolution based fuzzy inference system (DEFIS). To do so, air velocity as the output and the values of the x, and y coordinates, water velocity, and time step as the inputs are inputted the AI model for learning the flow pattern. The effects of cross over as the DE parameter and also the number of inputs on the best intelligence are investigated. Indeed, DEFIS correlates the air velocity to the nodes coordinates, time, and liquid velocity and then after the CFD modeling could be replaced with the simple correlation. For the first time, a comparison is made between the ANFIS and the DEFIS performances in terms of the prediction capability of the gas (air) velocity. The results released that both ANFIS and DEFIS could accurately predict the CFD pattern. The prediction times of both methods were obtained to be equal. However, the learning time of the DEFIS was fourfold of ANFIS.

Characterization of Simultaneous Evolution of Size and Composition Distributions Using Generalized Aggregation Population Balance Equation

The application of multi-dimensional population balance equations (PBEs) for the simulation of granulation processes is recommended due to the multi-component system. Irrespective of the application area, numerical scheme selection for solving multi-dimensional PBEs is driven by the accuracy in (size) number density prediction alone. However, mixing the components, i.e., the particles (excipients and API) and the binding liquid, plays a crucial role in predicting the granule compositional distribution during the pharmaceutical granulation. A numerical scheme should, therefore, be able to predict this accurately. Here, we compare the cell average technique (CAT) and finite volume scheme (FVS) in terms of their accuracy and applicability in predicting the mixing state. To quantify the degree of mixing in the system, the sum-square χ2 parameter is studied to observe the deviation in the amount binder from its average. It has been illustrated that the accurate prediction of integral moments computed by the FVS leads to an inaccurate prediction of the χ2 parameter for a bicomponent population balance equation. Moreover, the cell average technique (CAT) predicts the moments with moderate accuracy; however, it computes the mixing of components χ2 parameter with higher precision than the finite volume scheme. The numerical testing is performed for some benchmarking kernels corresponding to which the analytical solutions are available in the literature. It will be also shown that both numerical methods equally well predict the average size of the particles formed in the system; however, the finite volume scheme takes less time to compute these results.

Computational modeling of drug separation from aqueous solutions using octanol organic solution in membranes

Continuous membrane separation of pharmaceuticals from an aqueous feed was studied theoretically by development of high-performance mechanistic model. The model was developed based on mass and momentum transfer to predict separation and removal of ibuprofen (IP) and its metabolite compound, i.e. 4-isobutylacetophenone (4-IBAP) from aqueous solution. The modeling study was carried out for a membrane contactor considering mass transport of solute from feed to organic solvent (octanol solution). The solute experiences different mass transfer resistances during the removal in membrane system which were all taken into account in the modeling. The model’s equations were solved using computational fluid dynamic technique, and the simulations were carried out to understand the effect of process parameters, flow pattern, and membrane properties on the removal of both solutes. The simulation results indicated that IP and 4-IBAP can be effectively removed from aqueous feed by adjusting the process parameters and flow pattern. More removal was obtained when the feed flows in the shell side of membrane system due to improving mass transfer. Also, feed flow rate was indicated to be the most affecting process parameter, and the highest solute removal was obtained at the lowest feed flow rate.

Modelling tyramine extraction from wastewater using a non-dispersive solvent extraction process

Wastewater effluent from alkaloid processing plants has the potential adverse environmental influences. Mathematical modelling and simulations were carried out using computational fluid dynamics of mass and momentum transfer in a hollow fibre membrane extractor. Conservation equations were derived for tyramine extraction in the membrane extractor and solved based on the finite element method. Model findings based on the computational fluid dynamics validated well with the experimental data. The results showed that increase in organic-phase flow rate, as well as the fibre length and its porosity, has a positive impact on the performance of the extractor, whereas the enhancement of aqueous-phase flow rate led to the reduction of tyramine extraction.

Functional input and membership characteristics in the accuracy of machine learning approach for estimation of multiphase flow

In the current study, Artificial Intelligence (AI) approach was used for the learning of a physical system. We applied four inputs and one output in the learning process of AI. In the learning process, the inputs are space locations of a BCR (bubble column reactor), which are x, y, and z coordinate as well as the amount of gas fraction in BCR. The liquid velocity is also considered as output. A variety of functions were used in learning, such as gbellmf and gaussmf functions, to examine which functions can give the best learning. At the end of the study, all of the results were compared to CFD (computational fluid dynamics). A three-dimensional (3D) BCR was used in this research, and we studied simulation by CFD as well as AI. The data from CFD in a 3D BCR was studied in the AI domain. In AI, we tuned for various parameters to achieve the best intelligence in the system. For instance, different inputs, different membership functions, different numbers of membership functions were used in the learning process. Moreover, the meshless prediction was used, meaning that some data in the BCR have not participated in the learning, and they were predicted in the prediction process, which gives us a special capability to compare the results with the CFD outcomes. The findings showed us that AI can predict the CFD results, and a great agreement was achieved between CFD computing nodes and AI elements. This novel methodology can suggest a meshless and multifunctional AI model to simulate the turbulence flow in the BCR. For further evaluation, the ANFIS method is compared with ACOFIS and PSOFIS methods with regards to model’s accuracy. The results show that ANFIS method contains higher accuracy and prediction capability compared with ACOFIS and PSOFIS methods.

gbell Learning function along with Fuzzy Mechanism in Prediction of Two-Phase Flow

The integration of the computational fluid dynamics (CFD) and the adaptive network-based fuzzy inference system, known as ANFIS, is investigated for simulating the hydrodynamic in a bubble column reactor. The Eulerian-Eulerian two-phase model is employed as the CFD approach. For the ANFIS technique, a sensitivity analysis is done by varying the number of inputs and the number of membership functions (MFs). The x and z coordinates of the fluid location, the air velocity, and the pressure are considered as the inputs of the ANFIS, while the air vorticity is the output. The results revealed that the ANFIS with all four inputs and the MFs of five achieved the highest intelligence with the regression number close to 1. More specifically, gbell function in the learning framework is used to train all local computing nodes from solving Navier-Stokes equations. In the decision or prediction part, the fuzzy mechanism is used for the prediction of extra nodes that solve, which Navier-Stokes equations did not solve. The results show that the gbell function enables us to fully train all numerical points and also store data set in the frame of mathematical equations. Besides, this function responds well with the number of inputs and MFs for accurate prediction of reactor hydrodynamics. Additionally, a high number of MFs and input parameters influence the accuracy of the method during prediction. In the current study, gbell MF was studied to investigate its accuracy in the prediction of the two-phase flow. Also, different numbers of MFs were considered to investigate the level of accuracy and capability of prediction. ANFIS clustering methods, grid partition and fuzzy C-mean (FCM) clustering, are compared to see the ability of the method in prediction. To compare the accuracy of the ANFIS method with FCM clustering, the data were compared to the gaussmf function. The results showed that the method has high accuracy and that it could predict the flow pattern.

Pattern recognition of the fluid flow in a 3D domain by combination of Lattice Boltzmann and ANFIS methods

Many numerical methods have been used to simulate the fluid flow pattern in different industrial devices. However, they are limited with modeling of complex geometries, numerical stability and expensive computational time for computing, and large hard drive. The evolution of artificial intelligence (AI) methods in learning large datasets with massive inputs and outputs of CFD results enables us to present completely artificial CFD results without existing numerical method problems. As AI methods can not feel barriers in numerical methods, they can be used as an assistance tool beside numerical methods to predict the process in complex geometries and unstable numerical regions within the short computational time. In this study, we use an adaptive neuro-fuzzy inference system (ANFIS) in the prediction of fluid flow pattern recognition in the 3D cavity. This prediction overview can reduce the computational time for visualization of fluid in the 3D domain. The method of ANFIS is used to predict the flow in the cavity and illustrates some artificial cavities for a different time. This method is also compared with the genetic algorithm fuzzy inference system (GAFIS) method for the assessment of numerical accuracy and prediction capability. The result shows that the ANFIS method is very successful in the estimation of flow compared with the GAFIS method. However, the GAFIS can provide faster training and prediction platform compared with the ANFIS method.