Comprehensive model of energy, environmental impacts and economic in rice milling factories by coupling adaptive neuro-fuzzy inference system and life cycle assessment

The increasing energy demand, limited fossil fuel resources and effects of climate change, lead to problems with regard to sustainability of production in food industry. Hence, this article aims to provide energy, economic and environmental overview about the production of white rice in milling factories of Guilan province, Iran. Information are collected during factory site visits as well as interviews with staff of 60 milling factories. Besides, required data about the background system is extracted from Ecoinvent 3.3 databases. Energy analysis indicates that in these milling factories, 68,178.31 MJ per ton input paddy to millings is used and 68,178.31 MJ per ton input paddy of energy is generated. Life cycle assessment is used in this work. Results show that the natural gas (background processes of natural gas extraction, production and direct combustion) has a key role in all impacts category in this study. The reason for this is inefficiency of drying in milling factories. The economic analysis shows net profit of 47.37 ($ per ton input paddy) and the total cost of 294.21 ($ per ton input paddy). Besides, social cost for emission of production in these factories is 30.99 ($ per ton input paddy). A hybrid learning algorithm is employed in developing an adaptive neuro-fuzzy inference system model for predicting economic profit, output energy and global warning in milling factories. Coefficients of determination in forecasting output energy, economic profit and global warning are estimated to be 0.911, 0.978 and 0.964, respectively. Results demonstrate the usefulness of multi-level adaptive neuro-fuzzy inference system to management level for long-term planning in predicting various environmental, energy and economic indices of large-scale food production systems.