基于BP神经网络的沉积物(生物膜)主要活性组分

J4 ›› 2011, Vol. 49 ›› Issue (02): 346-352.

基于BP神经网络的沉积物(生物膜)主要活性组分

郭倩倩¹, 高茜¹, 王晓丽², 李鱼^1,2

1. 华北电力大学能源与环境研究院, 北京 102206； |2. 吉林大学环境与资源学院, 长春 130012

收稿日期:2010-04-12 出版日期:2011-03-26 发布日期:2011-06-14
通讯作者: 李鱼 E-mail:liyuxx@jlu.edu.cn

Interaction among Active Constituents of Sediments (SSs/NSCSs)on |the Adsorption of Cu and Zn Based onBP Artificial Neural Network

GUO Qianqian¹, GAO Qian¹, WANG Xiaoli², LI Yu^1,2

1. Research Academy of Energy and Environmental Studies, North China Electric Power University, Beijing 102206, China;2. College of Environment and Resources, Jilin University, Changchun 130012, China

Received:2010-04-12 Online:2011-03-26 Published:2011-06-14
Contact: LI Yu E-mail:liyuxx@jlu.edu.cn

摘要/Abstract

摘要：

利用MATLAB建立沉积物（生物膜）主要活性组分（铁氧化物、锰氧化物和有机质）吸附Cu/Zn过程的BP神经网络模型, 模型训练集均方差、训练
集偏差、验证集均方差和测试集偏差分别为0.002 2(0.001 5), 1.542 9×10^-6(2.648 4×10^-6), 0.087 1(0.069 2)和0.018 7(0.035 7). 所建模型能够反映沉积物（生物膜）主要活性组分含量梯度变化时吸附Cu/Zn的规律, 并且初步揭示了沉积物（生物膜）主要活性组分吸附Cu/Zn时的交互作用. 沉积物（生物膜）组分含量变化与其吸附Cu/Zn的能力呈显著反比关系时, 交互作用的影响度最大为1 420.30%/54.30%（沉积物）和79.27%/703.31%(生物膜). 沉积物（生物膜）吸附Cu/Zn时, 与对应原样相比交互作用的促进作用影响度最大为386.14%/30.08%（沉积物）和66.17%/47.92%（生物膜）.

关键词: 沉积物；重金属；吸附； BP神经网络；交互作用

Abstract:

A BP artificial neural network (ANN) model was developed via MATLAB to estimate Cu/Zn adsorption in the surficial sediments (SSs)
and natural surface coating samples (NSCSs), by which the mean square error of training set, the deviation of training set, the mean square error of verification set, and the deviation of test set are 0.002 2(0.001 5), 1.542 9×10^-6(2.648 4×10^-6), 0.087 1(0.069 2), and 0018 7(0.035 7), respectively. The predicted results of the BP ANN model established not only reveal the law of the adsorption of Cu/Zn by the active constituents of SSs (NSCSs) changed in grade, but also highlight the significant interaction among the activeconstituents in the SSs (NSCSs) on the adsorption of Cu/Zn preliminary. The adsorption capacity of Cu/Zn increases with the decrease in content of active constituents, and the maximum ratios between the adsorption variation value of the changed SSs (NSCSs) and their original adsorption value are 1 420.30%/54.30% (SSs) and 79.27%/703.31% (NSCSs) respectively; the interaction among the active constituents in SSs (NSCSs) promote Cu/Zn adsorption, and the maximum ratios between the adsorption variation value of the changed SSs (NSCSs) and their original adsorption value are 386.14%/30.08% (SSs) and 66.17%/47.92% (NSCSs) respectively.

Key words: surficial sediments, heavy metals, adsorption, BP artificial neural network, interaction

中图分类号:

X132

郭倩倩, 高茜, 王晓丽, 李鱼. 基于BP神经网络的沉积物(生物膜)主要活性组分[J]. J4, 2011, 49(02): 346-352.

GUO Qian-Qian, GAO Qian, WANG Xiao-Li, LI Yu-. Interaction among Active Constituents of Sediments (SSs/NSCSs)on |the Adsorption of Cu and Zn Based onBP Artificial Neural Network[J]. J4, 2011, 49(02): 346-352.

[1]	李鱼, 王志增, 王檬, 王倩. 多种环境因子交互作用对沉积物吸附阿特拉津的影响[J]. J4, 2013, 51(02): 334-339.
[2]	薛洪海, 郭志新, 王云凤, 李林璘, 李哲, 康春莉. 紫外光作用下冰相中α-萘酚的光转化[J]. J4, 2011, 49(06): 1157-1161.
[3]	许云竹, 花修艺, 董德明, 梁大鹏, 李仁声, 刘春阳. 地表水环境中PAHs源解析的方法比较及应用[J]. J4, 2011, 49(03): 565-.
[4]	李鱼, 王婷, 胡艳, 王夏娇. UAE-DLLME-SFO-HPLC测定沉积物中的十溴联苯醚[J]. J4, 2011, 49(03): 554-558.
[5]	景伟文, 包晓玮, 陈燕勤, 杨再磊, 刘洋. 用光助Fenton体系降解邻苯二甲酸二甲酯[J]. J4, 2011, 49(02): 358-362.
[6]	黄昆, 薛洪海, 张歌珊, 开建荣, 张祯祯, 吕佳佳, 康春莉. 低品位硅藻土对有机染料的吸附性能[J]. J4, 2010, 07(4): 713-717.
[7]	王晓丽, 杜显元, 王婷, 刘建林, 李鱼. 不同比例羟基磷灰石对沉积物中重金属形态影响的比较[J]. J4, 2010, 07(4): 707-712.
[8]	刘建林, 张琛, 杜显元, 高茜, 李鱼. 分散液液微萃取过程中内分泌干扰物在离子液体/水相体系中的分配行为[J]. J4, 2010, 48(02): 339-345.
[9]	李都峰, 赵文晋, 黎娜, 王宪恩. 曲拉通（TX-100）对恶臭假单胞菌降解生物膜中双酚[J]. J4, 2009, 47(6): 1334-1338.
[10]	王晓丽, 李鱼, 蔡宇, 王婷, 杜显元, 刘建林. 铁氧化物掺杂对沉积物吸持Cu与Zn能力的影响[J]. J4, 2009, 47(05): 1091-1096.