Artificial Neural Network Based Prediction of Heat Transfer From Horizontal Tube Bundles Immersed in Gas–Solid Fluidized Bed of Large Particles

Abstract

Artificial neural network (ANN) modeling of heat transfer from horizontal tube bundles immersed in gas fluidized bed of large particles (mustard, raagi and bajara) was investigated. The effect of fluidizing gas velocity on the heat transfer coefficient in the immersed tube bundles in in-line and staggered arrangement is discussed. The parameters particle diameter, temperature difference between bed and immersed surface were used in the neural network (NN) modeling along with fluidizing velocity. The feed-forward network with back propagation structure implemented using Levenberg–Marquardt's learning rule in the NN approach. The predictions of the ANN were found to be in good agreement with the experiment's values, as well as the results achieved by the developed correlations.

The analyses of frictional losses and thermal stresses in a diesel engine piston coated with different thicknesses of thermal barrier films using co-simulation method

“…38 At this point, the ''connection weights'' that contain the knowledge, ''bias,'' and ''activation (transfer) function'' must be needed for the data transfer. [36][37][38][39][40][41][42] Additionally, an error criterion and a modification process of the weights according to the error based objective function must be determined with an appropriate learning method that is called as ''training.'' 39 Neural network toolbox of MATLAB (Mathworks Inc. Software) was utilized to create the universal ANN in this study.…”

“…In the related researches, it may be denoted that LM algorithm was preferred usually since it approximates the error of the network with a second order expression, trains networks of moderate size fast and also has memory reduction feature for use when training set is large. 41,42 For those reasons, LM algorithm was used in this study and imposed to MATLAB script by addition of the line of ''net.trainFcn = 'trainlm'.'' Schematic diagram of the generated ANN for this application was shown in Figure 6.…”

Heat Transfer Performance in a Superheater of an Industrial CFBC Using Fuzzy Logic-Based Methods

“…Alternative methods for the above time-consuming and expensive techniques of data handling is the use of artificial intelligence (AI) approach. One of their representatives are called the neurocomputing routines [ 40 , 41 , 42 , 43 ], but there are also other AI techniques of data handling, including fuzzy logic (FL) approach [ 15 , 44 , 45 , 46 ]. The first one is based on the use of artificial neural networks, as they have the abilities to reproduce a process from training samples.…”