首页 | 本学科首页   官方微博 | 高级检索  
     检索      

用BP神经网络模型定量估算石化企业炼油废水处理中的VOCs
引用本文:戴晓波,张明旭,伏晴艳.用BP神经网络模型定量估算石化企业炼油废水处理中的VOCs[J].环保科技,2010,16(1):7-10.
作者姓名:戴晓波  张明旭  伏晴艳
作者单位:1. 东华大学环境科学与工程学院,上海,200051
2. 上海市环境监测中心,上海,200030
摘    要:将BP神经网络理论引入石化企业炼油厂废水处理中的VOCs挥发量估算。在分析影响VOCs挥发因素的基础上,利用基于MATLAB神经网络工具箱的图形用户界面GUI,建立了石化企业炼油废水处理中VOCs挥发量估算的BP神经网络模型。用该模型对样本集进行了学习训练和仿真测试,并将训练好的神经网络应用于相关实例的估算。结果表明,应用BP神经网络方法进行石化企业炼油废水处理中VOCs挥发量估算结果与美国环保局推荐软件WATER9的计算结果误差在1.49%~17.46%之间,为石化企业炼油废水处理中VOCs挥发量估算提供了一种较为可靠的方法。

关 键 词:炼油废水  VOCs挥发  BP神经网络  仿真训练  应用估算

Estimation of VCCs Emission From Refinery Wastewater Treatment Facilities of Petrochemical Industry by BP Artificial Neural Network
Authors:DAI Xiaobo  ZHANG Mingxu  FU Qingyan
Institution:1. School of Environmental Science and Engineering, Donghua University, Shanghai 200051, China; 2. Shanghai Environmental Monitoring Centre, Shanghai 200030, China)
Abstract:The BP artificial neural network approach was proposed to estimate the emission of VOCs from refinery wastewater treatment facilities of petrochemical industry. The BP artificial neural network for VOCs emission estimation of refinery wastewater treatment facilities was established by the use of Graphical User Interfaces (GUI) in MATLAB after affecting factors of VOCs emission were analyzed. Then the emulation and training for the network was proceeded with, and the trained network could be used to evaluate relevant cases. Results showed that the range of emission estimation error between BP artificial neural network approach and WATER9 which was recommended by USEPA is from 1.49% to 17.46%, and this BP artificial neural network provides a reliable estimation method for VOCs emission from refinery wastewater treatment facilities of petrochemical industry.
Keywords:refinery wastewater  VOCs emission  BP artificial neural network  emulation training  estimation application
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号