Prediction of baking results from farinograph measurements by using stepwise linear regression and artificial neuronal networks |
| |
| Affiliation: | 1. Department of Process Analytics and Cereal Science, University of Hohenheim, Garbenstrasse 23, 70599 Stuttgart, Germany;2. Faculty of Food, Nutrition and Home Sciences, National Instiute of Food Science and Technology, Faisalabad, Pakistan;3. Institute of Applied Mathematics and Statistics, University of Hohenheim, Garbenstrasse 23, 70599 Stuttgart, Germany;1. Department of Food and Bioproduct Sciences, University of Saskatchewan, Saskatoon, SK, Canada;2. Crop Development Centre, University of Saskatchewan, Saskatoon, SK, Canada;3. Department of Food Science, University of Manitoba, Winnipeg, MB, United States;1. Department of Food Science and Technology, Tokyo University of Marine Science and Technology, Konan 4-chome, Minato, Tokyo, 108-8477, Japan;2. Energy Technology Laboratories, Osaka Gas Co., Ltd. 6-19-9, Torishima, Konohana-ku, Osaka, 554-0051, Japan;1. Depto. de Tecnología de Procesos Biológicos y Bioquímicos, Universidad Simón Bolívar, Aptdo. 89000, Caracas, 1080-A, Venezuela;2. INRA, UR 1268 Biopolymères, Interactions & Assemblages (BIA), BP 71627, 44316, Nantes, France;1. Division of Horticultural Crop Processing, ICAR-Central Institute of Post-Harvest Engineering and Technology, Abohar, Punjab 152116, India;2. Division of Food Science and Postharvest Technology, ICAR-Indian Agricultural Research Institute, New Delhi 110012, India;1. Department of Soil Sciences, College of Agriculture, Shiraz University, Shiraz, Iran;2. Department of Natural Resources and Environmental Engineering, College of Agriculture, Shiraz University, Shiraz, Iran |
| |
| Abstract: | In an effort to extract additional data from farinograph experiments a model was developed to simulate the measurements and correlate the parameters of the model with results from baking tests. This additional information can be used in bakeries to predict the baking properties of the flours and adjust the recipes to maintain a constant product quality. For this eight different flours were characterized with a farinograph and 13 different results from baking experiments. An approach with five nonlinear differential equations was able to model the farinograph measurements very well (average R2 = 0.995 ± 0.005). While a stepwise multilinear regression only showed weak correlations in cross validation between a single parameter of the model and the baking volume (R2 = 0.745) and the volume yield (R2 = 0.796) respectively, the artificial neuronal network was more successful. For the baking weight (R2 = 0.926), the dough yield gross (R2 = 0.909) and net (R2 = 0.913) strong correlations were found. A good correlation for the baking volume (R2 = 0.853) was also determined, while the volume yield showed comparable results to the linear regression (R2 = 0.792). |
| |
| Keywords: | Farinograph Modelling Artificial neuronal networks Wheat |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
