A NEURAL NETWORK APPROACH FOR EVALUATION of SURFACE HEAT TRANSFER COEFFICIENT

An artificial neural network (ANN) approach for tackling the inverse heat conduction problems was explored - specifically for the determination of surface heat transfer coefficient at the liquid-solid interface using the temperature profile information within the solid. Although the concept is quite generic, the specific cases considered have a particular relevance to food process engineering applications. The concept was tested with two geometric shapes: a sphere and a finite cylinder, the former representing the simplest geometry and the latter representing a cross product of an infinite cylinder and an infinite plate. In developing the ANN model, two approaches were used. In the first one, the ANN model was trained to predict the surface convective heat transfer function, Biot number (Bi) from the slope coefficient (m) of temperature ratio curve under varying boundary conditions. The associated mean relative prediction errors were as high as 5.5% with a standard deviation of 8%. In the second ANN approach, m was related to tan -1 (Bi) which significantly improved the model's predictive performance. The second ANN model could be used with Biot numbers up to 100 with a mean error less than 1.5% for either of the two geometries. Heat transfer coefficients evaluated using the developed ANN model were in agreement (<3% error) with those calculated using conventional numerical/analytical techniques under a range of experimental conditions.

[1]  B. R. Bass.  Application of the Finite Element Method to the Nonlinear Inverse Heat Conduction Problem Using Beck’s Second Method , 1978 .

[2]  B. F. Blackwell,et al.  EFFICIENT TECHNIQUE FOR THE NUMERICAL SOLUTION OF THE ONE-DIMENSIONAL INVERSE PROBLEM OF HEAT CONDUCTION , 1981 .

[3]  D. E. Thompson,et al.  Strut or guide vane secondary flows and their effect on turbomachinery noise , 1983 .

[4]  William E. Faller,et al.  Neural network prediction of three-dimensional unsteady separated flowfields , 1993 .

[5]  H. S. Ramaswamy,et al.  SURFACE HEAT TRANSFER COEFFICIENTS ASSOCIATED WITH HEATING of FOOD PARTICLES IN CMC SOLUTIONS , 1993 .

[6]  D. Park,et al.  Effect of Mn-dispersoid on the low-cycle fatigue life of Al-Zn-Mg alloys , 1994 .

[7]  A. D. Whittaker,et al.  Neural Network Modeling for Beef Sensory Evaluation , 1994 .

[8]  Keith I. Tomlins,et al.  Prediction of quality and origin of black tea and pine resin samples from chromatographic and sensory information : evaluation of neural networks , 1994 .

[9]  Sundaram Gunasekaran,et al.  Shape feature extraction and classification of food material using computer vision , 1994 .

[10]  N. Phan-Thien,et al.  Neural-network-based approximations for solving partial differential equations , 1994 .

[11]  A. D. Whittaker,et al.  Snack Quality Evaluation Method Based on Image Features and Neural Network Prediction , 1995 .

[12]  Shiv O. Prasher,et al.  A NEURAL NETWORK APPROACH FOR THERMAL PROCESSING APPLICATIONS , 1995 .

[13]  R. C. Panda,et al.  Modelling of A Fluidized Bed Drier Using Artificial Neural Network , 1996 .

[14]  H. Ramaswamy,et al.  Influence of particle characteristics on fluid-to-particle heat transfer coefficient in a pilot scale holding tube simulator , 1996 .

[15]  M. R. Zareifard,et al.  A NEW TECHNIQUE FOR EVALUATING FLUID‐TO‐PARTICLE HEAT TRANSFER COEFFICIENTS UNDER TUBE‐FLOW CONDITIONS INVOLVING PARTICLE OSCILLATORY MOTION , 1997 .

[16]  Shiv O. Prasher,et al.  Neural network modeling of heat transfer to liquid particle mixtures in cans subjected to end-over-end processing , 1997 .

[17]  Hosahalli S. Ramaswamy,et al.  PREDICTION OF PSYCHROMETRIC PARAMETERS USING NEURAL NETWORKS , 1998 .