Prediction of freezing time for food products using a neural network |
| |
| Affiliation: | 1. School of Engineering, University of Guelph, Guelph, Ontario, Canada N1G 2W1;2. Jiangsu University of Science and Technology, Zhenjiang, Jiangsu, China;1. National Fisheries University, 2-7-1 Nagata-Honmachi, Shimonoseki, Yamaguchi 759-6595, Japan;2. Nippon Kaiji Kentei Kyokai, 1-9-7 Hatchobori, Chuo-ku, Tokyo 104-0032, Japan;1. Universidade Federal de Mato Grosso, Campus Universitário do Araguaia, Instituto de Ciências Exatas e da Terra, Avenida Valdon Varjão, n° 6390, Barra do Garças, Mato Grosso CEP: 78600-000, Brazil;2. Universidade Federal de Viçosa, Departamento de Engenharia Elétrica, Campus Universitário, Viçosa, Minas Gerais CEP: 36570-000, Brazil;3. Universidade Federal de Viçosa, Departamento de Tecnologia de Alimentos, Campus Universitário, Viçosa, Minas Gerais CEP: 36570-000, Brazil;4. Universidade Federal de Viçosa, Departamento de Engenharia Agrícola, Campus Universitário, Viçosa, Minas Gerais CEP: 36570-000, Brazil;1. Discipline of Information Technology, Murdoch University, Murdoch, WA 6150, Australia;2. Centre for Crop and Food Innovation, Food Futures Institute, Murdoch University, Murdoch, WA 6150, Australia;3. Department of Primary Industries and Regional Development, Western Australia, South Perth, WA 6151, Australia |
| |
| Abstract: | An artificial neural network (ANN) was developed to predict the freezing time of food products of any shape. The Pham model was used to generate freezing time data and to train ANN based on Wardnets. The product thickness (a), width (b), length (c), convective heat transfer coefficient (hc), thermal conductivity of frozen product (k), product density (ρ), specific heat of unfrozen product (Cpu), moisture content of the product (m), initial product temperature (Ti), and ambient temperature (T∞) were taken as input variables of the ANN to predict freezing time. The effects of the number of hidden layer nodes, learning rate, momentum on prediction accuracy were analyzed. The performance of the ANN was checked using experimental data. Predicted freezing time using the ANN was proved a simple, convenient and accurate method. Selection of hidden nodes, learning rate and momentum were important to ANN predictions. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
