Genetic algorithm‐assisted artificial neural network for retrieval of a parameter in a third grade fluid flow through two parallel and heated plates

Abstract

Genetic algorithm (GA) has been used to determine important attributes of artificial neural network (ANN), such as number of neurons in different hidden layers and division of data for training, validation, and testing. The GA‐assisted ANN (GAAANN) model was used to retrieve third grade fluid (TGF) parameter (A) in a TGF flow problem. The TGF was allowed to flow through two parallel plates, which were subjected to uniform heat flux. The least square method (LSM) was used to solve the governing equations, for specified boundary conditions. In this way, temperature profiles for different values of A were computed by LSM, constituting the direct part of the problem. In the inverse part, the GAAANN model was fed with a temperature profile as input and the corresponding value of A was obtained as output. Four different GAAANN model were developed, and a detailed analysis was done in retrieving the value of A by different GAAANN models. Two very important and commonly used algorithms: Levenberg‐Marquardt (LM) and scaled conjugate gradient are explored for training of the neurons. The entire four GAAANN model were able to retrieve the value of A with different levels of accuracy.

Numerical study of thermal and solutal advancements in ZnO–SAE50 nanolubricant flow past a convergent/divergent channel with the effects of thermophoretic particle deposition

“…However, it was first developed to handle nonlinear least-squares issues. Mishra and Chaudhuri 31 examined the flow of third-grade fluid on heated plates using an ANN approach to explore their results. Shafiq et al 32 used the ANN technique to examine the Williamson fluid flow via a radiative surface.…”

Retrieval of parameters in micromixer with obstacle by cascade‐forward‐type artificial neural network: Comparison of four training algorithms under noisy data

“…As compared to any numerical/experimental approach, ANN offers the following advantages: (1) only correct pair of data (input-output) is required; that is, exact relation between the output and input is not needed, (2) a trained ANN model can give the result in much less time, that is, time taken to solve any similar problem is drastically less as compared to other means, (3) both the experimental and/or numerical data can be used to develop an ANN model, and (4) inverse problem can be solved easily. [7][8][9][10][11] Various advantages of the ANN approach make it a useful tool to solve scientific problems in different fields, like, manufacturing, 12,13 oil exploration, 14 biofuels, 15,16 solar, 17 lubrication, 18 automobile, 19 power plants, 20 and so on. Various thermal and fluid problems solved by employing ANN and various optimization tools are listed in Table 1.…”

“…), when interconnected. As compared to any numerical/experimental approach, ANN offers the following advantages: (1) only correct pair of data (input–output) is required; that is, exact relation between the output and input is not needed, (2) a trained ANN model can give the result in much less time, that is, time taken to solve any similar problem is drastically less as compared to other means, (3) both the experimental and/or numerical data can be used to develop an ANN model, and (4) inverse problem can be solved easily 7–11 …”

Clustering assisted artificial neural network for handling noisy big data: An application for estimation of parameter in combined mode conduction and radiation heat transfer

“…Such problems are called inverse problems, and they are ill-posed. [1][2][3][4][5][6] In inverse analysis, various optimization methods are used by different researchers. In such an approach, an objective function is defined by using the dependent variables obtained from guessed values of independent variables and known/desired dependent variables.…”

“…But there are situations like higher costs of measurements, disturbance of flow due to intrusion of measuring probe, inaccessible location of measurement, and so on when dependent variables are known and independent variables need to be computed. Such problems are called inverse problems, and they are ill‐posed 1–6 …”