UASB处理高硫酸盐废水及人工神经网络模型的构建  

Treatment of sulfate-rich wastewater by UASB and construction of artificial neural network model

作　　者：王庆宏[1] 余静诗 梁家豪 陈春茂[1] Wang Qinghong;Yu Jingshi;Liang Jiahao;Chen Chunmao(State Key Laboratory of Heavy Oil Processing,College of Chemical Engineering and Environment,China University of Petroleum-Beijing,Beijing 102249,China)

机构地区：[1]中国石油大学(北京)化学工程与环境学院,重质油国家重点实验室,北京102249

出　　处：《工业水处理》2021年第7期77-81,共5页Industrial Water Treatment

基　　金：中国石油大学(北京)科研基金资助(2462018BJB001)。

摘　　要：采用UASB处理高硫酸盐废水,对不同碳硫比〔m(COD)/m(SO_(4)^(2-))=1、2、3、4.6〕条件下反应体系的处理效能进行评估,并利用神经网络模型分析不同因素对COD去除率和SO_(4)^(2-)去除率的影响。结果表明SO_(4)^(2-)去除率与m(COD)/m(SO_(4)^(2-))成正比,而COD去除率则与m(COD)/m(SO_(4)^(2-))成反比。当m(COD)/m(SO_(4)^(2-))为4.6时,SO_(4)^(2-)平均去除率达98.1%,此时,COD平均去除率仅为32.2%。神经网络模型的影响因素权重分析表明进水pH、COD和m(COD)/m(SO_(4)^(2-))为影响COD去除的主要因素,进水COD、SO_(4)^(2-)浓度和m(COD)/m(SO_(4)^(2-))为影响SO_(4)^(2-)去除的主要因素。Sulfate-rich wastewater was treated by UASB.The performance of the reaction system under the condition of different COD/sulfate ratios〔m(COD)/m(SO_(4)^(2-))=1,2,3,4.6〕was studied,and the neural network model was used to analyze the influence of different factors on COD and SO_(4)^(2-)removal efficiency.The results showed that the removal rate of SO_(4)^(2-)was proportional to the m(COD)/m(SO_(4)^(2-))and the removal rate of COD was inversely proportional to the m(COD)/m(SO_(4)^(2-)).When m(COD)/m(SO_(4)^(2-))was 4.6,the average removal rate of SO_(4)^(2-)could reach up to 98.1%,but that of COD was only 32.2%.The weight analysis of influencing factors of neural network model shows that the influent pH,COD and m(COD)/m(SO_(4)^(2-))were the main parameters that affect COD removal,and the influent COD,SO_(4)^(2-)concentration and m(COD)/m(SO_(4)^(2-))were the main parameters that affect SO_(4)^(2-)removal.

关 键 词：高硫酸盐废水 厌氧处理 神经网络 

分 类 号：X703[环境科学与工程—环境工程]