等离子体降解酸性橙Ⅱ的人工神经网络模型  

Artificial neural network model of acid orange 7 degradation by pulsed discharge plasma

作　　者：刘朝华[1] 王慧娟[2,3] 吴春笃[2] 梅强[1] 依成武[2] 

机构地区：[1]江苏大学管理学院,江苏镇江212013 [2]江苏大学环境学院,江苏镇江212013 [3]江苏大学现代农业装备与技术省/部共建教育部重点实验室,江苏镇江212013

出　　处：《江苏大学学报（自然科学版）》2012年第6期659-662,670,共5页Journal of Jiangsu University：Natural Science Edition

基　　金：中国博士后科学基金资助项目(20110491353);江苏省博士后基金资助项目(1102116C);江苏大学高级人才基金资助项目(08JDG057)

摘　　要：基于人工神经网络用于多因素复杂系统建模的优越性,建立了多针-板电极形式脉冲放电等离子体降解酸性橙Ⅱ(AO7)的人工神经网络模型(ANNs),考察了多因素脉冲放电水处理系统中主要的电气参数(脉冲峰值电压、脉冲频率)和结构参数(针-板电极间距)对AO7脱色效率的影响,并利用BP神经网络模型对多因素条件下AO7的脱色效率进行仿真预测.结果表明:所建立的BP人工神经网络模型可以有效预测脉冲放电水处理体系中各参数对AO7脱色效率的影响趋势.根据预测结果可以归纳:较佳的脉冲峰值电压可以同时保证较好的AO7脱色效果和较高的系统能量利用效率;脉冲频率的增加能有效提高AO7的脱色效率;较小的电极间距有利于AO7脱色.Based on the superiorities of artificial neural network（ANNs） for modeling complex system,an ANN model of acid orange 7（AO7） decoloration by multi-needle-to-plate high voltage pulsed discharge plasma system was established.The effects of main electric parameters,peak pulsed voltage and pulse frequency,and characteristic parameter of electrode distance on AO7 decoloration efficiency were investigated.The decoloration efficiency of AO7 with various factors was simulated and predicted by BP neural network model.The results show that the proposed BP neural network model can effectively predict the decoloration of AO7 with complex factors.The predicting results illuminate that a superior peak pulsed voltage value can ensure high AO7 decoloration rate with low pulse energy consumption.The increase of pulse frequency can obviously improve AO7 degradation rate,while the decrease of electrode distance is favor for AO7 decoloration.

关 键 词：脉冲放电等离子体 酸性橙Ⅱ 脱色 人工神经网络 模型 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] X703.1[自动化与计算机技术—计算机科学与技术]