Development of a 3D Hybrid Intelligent‐Mechanistic Model for Simulation of Multiphase Chemical Reactors

Rezakazemi, Mashallah; Shirazian, Saeed

doi:10.1002/ceat.201800159

Cited by 14 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of combining CFD approach and soft computing can be used to capture the advantages of both methods and tackle the drawbacks associated with each method. The method has been recently used for modeling and simulation of multiphase chemical reactors and shown to be a promising approach [41,42,44,45]. This novel approach takes in the data generated by CFD in order to train artificial intelligent system, and once the system has been trained it can be used for prediction of the process without the need for implementation of CFD for the whole system.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

ANFIS pattern for molecular membranes separation optimization

Rezakazemi

Mosavi

Shirazian

2019

Journal of Molecular Liquids

Self Cite

120

View full text Add to dashboard Cite

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

ANFIS pattern for molecular membranes separation optimization

Rezakazemi

Mosavi

Shirazian

2019

Journal of Molecular Liquids

Self Cite

120

View full text Add to dashboard Cite

show abstract

“…The bubble column reactor can produce two-phase gas-liquid flows, and sometimes solid material is added to create chemical reactions as well [1][2][3]. Advantages such as simple shape, not having moving parts, and a high rate of heat and mass transfer have rendered the bubble column reactor an attractive choice for academia and industries [4][5][6][7]. Various industries use this type of bubble column reactor [8].…”

Section: Introductionmentioning

confidence: 99%

Fluid Velocity Prediction Inside Bubble Column Reactor Using ANFIS Algorithm Based on CFD Input Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

Since machine learning and smart methods can be used to study hydrodynamics in the bubble column reactor, it is possible to create highly intelligent bubble column reactors that have not been previously simulated and optimized them with computational fluid dynamics (CFD) methods. The previous studies considered the position of each node (in three directions) inside the bubble column reactor as the input in the artificial intelligence model. Machine learning methods have been used for processing big data related to the bubble column reactor. These big data are associated with the points inside the bubble column reactor, which represent the gas volume fraction and the fluid velocity in the x-direction. In this study, adaptive-network-based fuzzy inference system (ANFIS) was used to find out the relationship between the outputs of the bubble column reactor. The present study also intends to investigate the relationship between two outputs, namely the amount of gas in the bubble column reactor and the velocity of the fluid in the x-direction. Various parameters were investigated in this system, including the number of rules, the type of membership function, and the amount of input data. The mentioned parameters were regularly changed to find out the state where the system can achieve its intelligence. In this study, the best parameter that helped the system was the amount of data in the training process. The results showed that the lower the amount of data used in training, the better the prediction.

show abstract

“…In addition to this numerical model, machine learning techniques have been mixed with numerical or experimental data for predicting the multiphase flow. In about one decade, some researchers 23 , 24 have combined the CFD method with machine learning algorithms to predict the fluid flow, particularly multiphase flow and heat transfer problems 25 , 26 . They examined different tuning parameters to achieve the best accuracy of the model in predicting the flow 27 – 29 .…”

Section: Introductionmentioning

confidence: 99%

ANFIS grid partition framework with difference between two sigmoidal membership functions structure for validation of nanofluid flow

Pishnamazi

Babanezhad

Nakhjiri

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

In this study, a square cavity is modeled using Computational Fluid Dynamics (CFD) as well as artificial intelligence (AI) approach. In the square cavity, copper (Cu) nanoparticle is the nanofluid and the flow velocity characteristics in the x-direction and y-direction, and the fluid temperature inside the cavity at different times are considered as CFD outputs. CFD outputs have been assessed using one of the artificial intelligence algorithms, such as a combination of neural network and fuzzy logic (ANFIS). As in the ANFIS method, we have a non-dimension procedure in the learning step, and there is no issue in combining other characteristics of the flow and thermal distribution beside the x and y coordinates, we combine two coordinate parameters and one flow parameter. This ability of method can be considered as a meshless learning step that there is no instability of the numerical method or limitation of boundary conditions. The data were classified using the grid partition method and the MF (membership function) type was dsigmf (difference between two sigmoidal membership functions). By achieving the appropriate intelligence in the ANFIS method, output prediction was performed at the points of cavity which were not included in the learning process and were compared to the existing data (the results of the CFD method) and were validated by them. This new combination of CFD and the ANFIS method enables us to learn flow and temperature distribution throughout the domain thoroughly, and eventually predict the flow characteristics in short computational time. The results from AI in the ANFIS method were compared to the ant colony and fuzzy logic methods. The data from CFD results were inserted into the ant colony system for the training process, and we predicted the data in the fuzzy logic system. Then, we compare the data with the ANFIS method. The results indicate that the ANFIS method has a high potentiality compared to the ant colony method because the amount of R in the ANIFS system is higher than R in the ant colony method. In the ANFIS method, R is equal to 0.99, and in the ant colony method, R is equal to 0.91. This shows that the ant colony needs more time for both the prediction and training of the system. Also, comparing the pattern recognition in the two systems, we can obviously see that by using the ANFIS method, the predictions completely match the target points. But the other method cannot match the flow pattern and velocity distribution with the CFD method.

show abstract

Development of a 3D Hybrid Intelligent‐Mechanistic Model for Simulation of Multiphase Chemical Reactors

Cited by 14 publications

References 43 publications

ANFIS pattern for molecular membranes separation optimization

ANFIS pattern for molecular membranes separation optimization

Fluid Velocity Prediction Inside Bubble Column Reactor Using ANFIS Algorithm Based on CFD Input Data

ANFIS grid partition framework with difference between two sigmoidal membership functions structure for validation of nanofluid flow

Contact Info

Product

Resources

About