Thermal process calculations using artificial neural network models

In this study, artificial neural network (ANN) models were evaluated as potential alternatives to conventional thermal process calculations methods. ANN is a computing system capable of processing information by its dynamic response to external inputs. ANNs learn from examples through iteration by adjusting the internal structure to match the pattern between input and output variables. Finite difference simulations, which are widely recognized as practical alternatives to experimental methods, were used to generate temperature profiles under thermal processing conditions for a wide range of can sizes and operating conditions. Time-temperature data so gathered were used to evaluate the heat penetration parameters, fh, jch, fc and jcc as well as to compute process lethality and process time. These data were used for developing the ANN models. Selected Formula methods were also used to calculate the respective process times/process lethalities. The accuracy and ability of ANN models were compared with the Formula methods, both with respect to process time and process lethality computations using data from the finite difference model as the reference. Process calculation results from ANN model were comparable to, and sometimes better and more flexible than, the currently available Pham and Stumbo methods.

[1]  John Bolte,et al.  Linear regression, neural network and induction analysis to determine harvesting and processing effects on surimi quality , 1996 .

[2]  L. Bochereau,et al.  A method for prediction by combining data analysis and neural networks: Application to prediction of apple quality using near infra-red spectraag , 1992 .

[3]  G. S. Tucker.  Development and use of numerical techniques for improved thermal process calculations and control , 1991 .

[4]  S. Kim,et al.  NEURAL NETWORK MODELING AND FUZZY CONTROL SIMULATION FOR BREAD-BAKING PROCESS , 1997 .

[5]  Arthur A. Teixeira,et al.  On-line retort control in thermal sterilization of canned foods , 1997 .

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

[7]  Ashim K. Datta,et al.  Computer‐Based Retort Control Logic for On‐Line Correction of Process Deviations , 1986 .

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

[9]  Sundaram Gunasekaran,et al.  Food quality prediction with neural networks , 1998 .

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

[11]  R. J. Cole,et al.  Estimation of aflatoxin contamination in preharvest peanuts using neural networks , 1997 .

[12]  Kevin Swingler,et al.  Applying neural networks - a practical guide , 1996 .

[13]  Marvin A. Tung,et al.  Comparison of Formula Methods for Calculating Thermal Process Lethality , 1982 .

[14]  J. R. Dixon,et al.  Computer determination of spore survival distributions in thermally-processed conduction-heated foods , 1969 .

[15]  Q. T. Pham.  Calculation of Thermal Process Lethality for Conduction‐Heated Canned Foods , 1987 .

[16]  M. Hendrickx,et al.  A critical analysis of mathematical procedures for the evaluation and design of in-container thermal processes for foods. , 1997, Critical reviews in food science and nutrition.

[17]  D. R. Baughman,et al.  Neural Networks in Bioprocessing and Chemical Engineering , 1992 .

[18]  R. Lacroix,et al.  EFFECTS OF DATA PREPROCESSING ON THE PERFORMANCE OF ARTIFICIAL NEURAL NETWORKS FOR DAIRY YIELD PREDICTION AND COW CULLING CLASSIFICATION , 1997 .

[19]  K. S. Purohit,et al.  REFINEMENT AND EXTENSION OF fn/U: g PARAMETERS FOR PROCESS CALCULATION , 1973 .

[20]  Pekka Linko,et al.  Neural network modelling for real-time variable estimation and prediction in the control of glucoamylase fermentation , 1992 .