Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
Environ Sci Pollut Res Int. 2017 Dec;24(34):26324-26340. doi: 10.1007/s11356-017-0234-5. Epub 2017 Sep 30.
In this study, an artificial neural network (ANN) model was developed for predicting the yield and life cycle environmental impacts based on energy inputs required in processing of black tea, green tea, and oolong tea in Guilan province of Iran. A life cycle assessment (LCA) approach was used to investigate the environmental impact categories of processed tea based on the cradle to gate approach, i.e., from production of input materials using raw materials to the gate of tea processing units, i.e., packaged tea. Thus, all the tea processing operations such as withering, rolling, fermentation, drying, and packaging were considered in the analysis. The initial data were obtained from tea processing units while the required data about the background system was extracted from the EcoInvent 2.2 database. LCA results indicated that diesel fuel and corrugated paper box used in drying and packaging operations, respectively, were the main hotspots. Black tea processing unit caused the highest pollution among the three processing units. Three feed-forward back-propagation ANN models based on Levenberg-Marquardt training algorithm with two hidden layers accompanied by sigmoid activation functions and a linear transfer function in output layer, were applied for three types of processed tea. The neural networks were developed based on energy equivalents of eight different input parameters (energy equivalents of fresh tea leaves, human labor, diesel fuel, electricity, adhesive, carton, corrugated paper box, and transportation) and 11 output parameters (yield, global warming, abiotic depletion, acidification, eutrophication, ozone layer depletion, human toxicity, freshwater aquatic ecotoxicity, marine aquatic ecotoxicity, terrestrial ecotoxicity, and photochemical oxidation). The results showed that the developed ANN models with R values in the range of 0.878 to 0.990 had excellent performance in predicting all the output variables based on inputs. Energy consumption for processing of green tea, oolong tea, and black tea were calculated as 58,182, 60,947, and 66,301 MJ per ton of dry tea, respectively.
在这项研究中，开发了一个人工神经网络（ANN）模型，用于根据伊朗吉兰省红茶、绿茶和乌龙茶加工所需的能源投入来预测产量和生命周期环境影响。生命周期评估（LCA）方法用于研究基于摇篮到门方法的加工茶的环境影响类别，即从使用原材料生产输入材料到茶加工单元的门，即包装茶。因此，分析中考虑了萎凋、揉捻、发酵、干燥和包装等所有茶叶加工操作。初始数据是从茶叶加工单元获得的，而关于背景系统的数据则是从 EcoInvent 2.2 数据库中提取的。LCA 结果表明，干燥和包装操作中使用的柴油燃料和瓦楞纸箱分别是主要的热点。在这三种加工单元中，红茶加工单元造成的污染最高。三种前馈反向传播 ANN 模型基于 Levenberg-Marquardt 训练算法，具有两个隐藏层，带有 sigmoid 激活函数和输出层中的线性传递函数，分别应用于三种加工茶。神经网络是基于八个不同输入参数（鲜茶叶、人力、柴油、电、粘合剂、纸箱、瓦楞纸箱和运输的能源当量）和十一个输出参数（产量、全球变暖、非生物消耗、酸化、富营养化、臭氧层消耗、人类毒性、淡水水生生态毒性、海洋水生生态毒性、陆地生态毒性和光化学氧化）的能量当量开发的。结果表明，开发的 ANN 模型具有 0.878 至 0.990 范围内的 R 值，在基于输入预测所有输出变量方面表现出优异的性能。加工绿茶、乌龙茶和红茶的能源消耗分别计算为每吨干茶 58182、60947 和 66301 MJ。
