A field study was conducted to determine the behavior and distribution of arsenic during the pyrometallurgy process in a typical SKS(Shuikoushan) lead smelter in Hunan province, China. Environmental influences of arse...A field study was conducted to determine the behavior and distribution of arsenic during the pyrometallurgy process in a typical SKS(Shuikoushan) lead smelter in Hunan province, China. Environmental influences of arsenic in selected samples were evaluated. Arsenic contents in all input and output samples vary from 0.11% in raw lead to 6.66% in collected dust-2. More arsenic is volatilized in blast furnace and fuming furnace(73.02% of arsenic input) than bottom blowing furnace(10.29% of arsenic input).There are 78.97%, 13.69%, 7.31% of total arsenic distributed in intermediate materials, stockpiled materials and unorganized emissions, respectively. Matte slag-2, collected dust-1 and secondary zinc oxide are hazardous based on the arsenic concentrations of toxicity characteristic leaching procedure. According to risk assessment code(RAC) guideline, arsenic in collected dust-1 poses a very serious risk to the surrounding environment, arsenic in speiss, matte slag-2, water-quenched slag and secondary zinc oxide show low risk, while arsenic in matte slag-1, collected dust-2 and post dust has no risk to the environment.展开更多
文摘目的 建立基于长短期记忆(longshort-termmemory,LSTM)神经网络的时间序列预测模型,对北京地区鲜(冻)肉制品铅含量进行风险评估与预测预警。方法 通过收集2011—2020年国家市场监督管理总局日常食品监督管理抽检数据,筛选出北京地区鲜(冻)肉制品的抽检数据,构建数据集并进行预处理,按照7:2:1的比例划分训练集、验证集和测试集,基于Tensorflow平台构建4层LSTM模型并进行训练,基于重大活动举办前10d的鲜(冻)肉制品铅含量数据,对未来1d的鲜(冻)肉制品铅含量风险进行预测。结果 经过50轮模型迭代训练,训练集和测试集Loss指标收敛至0.084,经过5次训练后的模型评估参数均方根误差(root mean square error,RMSE)为0.192,决定系数(coefficient of determination,R2_score)为0.916,模型误差较小、准确度较高。结论 基于LSTM的鲜(冻)肉制品铅含量风险预测模型整体性能较好,可应用于重大活动举办地的食品风险预测,并精准指导监督抽检。
基金Project(2011AA061001)supported by the National High Technology Research and Development Program of ChinaProject(51304251)supported by the National Natural Science Foundation of China+1 种基金Project(2013M542141)supported by China Postdoctoral FoundationProject(K1201010-61)supported by Planned Program of Science and Technology of Changsha,China
文摘A field study was conducted to determine the behavior and distribution of arsenic during the pyrometallurgy process in a typical SKS(Shuikoushan) lead smelter in Hunan province, China. Environmental influences of arsenic in selected samples were evaluated. Arsenic contents in all input and output samples vary from 0.11% in raw lead to 6.66% in collected dust-2. More arsenic is volatilized in blast furnace and fuming furnace(73.02% of arsenic input) than bottom blowing furnace(10.29% of arsenic input).There are 78.97%, 13.69%, 7.31% of total arsenic distributed in intermediate materials, stockpiled materials and unorganized emissions, respectively. Matte slag-2, collected dust-1 and secondary zinc oxide are hazardous based on the arsenic concentrations of toxicity characteristic leaching procedure. According to risk assessment code(RAC) guideline, arsenic in collected dust-1 poses a very serious risk to the surrounding environment, arsenic in speiss, matte slag-2, water-quenched slag and secondary zinc oxide show low risk, while arsenic in matte slag-1, collected dust-2 and post dust has no risk to the environment.
