基于因子-神经网络预测南渡江海口段水质状况

针对海南省南渡江日益严重的水污染现状,根据南渡江海口段2001年-2006年的监测资料,应用因子分析法找出影响水质的主要污染指标,建立了基于BP神经网络的主要污染指标预测模型,并对其进行训练检验,结果证明该模型预测精度满足要求,再利用训练、检验后的模型对近几年主要污染因子进行预测,发现了变化规律,最后提出南渡江污染防治措施。     

城市电磁环境建模及网络监测系统的构想

随着科技的发展和城市建设速度的加快,电磁污染的问题已经越来越受到各界的重视与关注。该文首先介绍了时域有限差分法的基本概念,并建立了基于时域有限差分法计算的数学模型,然后针对城市电磁环境的特点,从电磁污染产生的根源和电磁干扰的种类入手进行研究,对电磁污染的监测方式进行了讨论,在此基础上,给出了一种基于GPS定位技术和GPRS无线传输技术的城市电磁环境网络监测系统的构想,并对系统结构及其所实现的功能进行了讨论。     

江阴市小城镇污水集中处理的研究与思考

随着城镇化进程加快,经济快速发展的同时环境污染问题随之出现,主要表现在小城镇污水处理率较低,各地区发展不平衡等方面。通过几年来的摸索与实践,江阴市小城镇污水集中处理已成一定规模,也凸现出一些问题和不足之处。通过对江阴市小城镇污水集中处理水质特点及工艺的研究,结合江阴市污水处理厂运行情况进行问题分析,提出相应的对策及思考。通过加强城镇污水管网建设,运用成熟经济高效的处理工艺,引进先进管理制度,促进环保部门的监管工作,达到改善小城镇污水处理效率的目的。     

Hydraulic model for multi-sources reclaimed water pipe network based on EPANET and its applications in Beijing, China

Water shortage is one of the major water related problems for many cities in the world. The planning for utilization of reclaimed water has been or would be drafted in these cities. For using the reclaimed water soundly, Beijing planned to build a large scale reclaimed water pipe networks with multi-sources. In order to support the plan, the integrated hydraulic model of planning pipe network was developed based on EPANET supported by geographic information system (GIS). The complicated pipe network was divided into four weak conjunction subzones according to the distribution of reclaimed water plants and the elevation. It could provide a better solution for the problem of overhigh pressure in several regions of the network. Through the scenarios analysis in different subzones, some of the initial diameter of pipes in the network was adjusted. At last the pipe network planning scheme of reclaimed water was proposed. The proposed planning scheme could reach the balances between reclaimed water requirements and reclaimed water supplies, and provided a scientific basis for the reclaimed water utilization in Beijing. Now the scheme had been adopted by Beijing municipal government.     

基于熵权的属性识别模型在城市轨道线网方案评价中的应用

城市轨道线网规划对优化城市社会、经济、生态环境,实现城市生态环境可持续发展有着至关重要的作用。文章通过熵值法与属性识别模型相结合,建立了基于熵权的属性识别模型,用该方法对城市轨道线网方案进行综合评价,并结合西安市城市轨道交通线网规划中的4个预选方案进行了评价,推选出最优方案。结果表明,该评价方法结果合理,决策科学,具有较好的应用前景。     

BP模型在水泥行业清洁生产评价案例中的应用

基于BP神经网络的原理与算法,建立清洁生产多指标综合评价模型,采用隶属度函数对评价指标进行描述。以避免评价过程中的人为失误,达到客观评价的目的。用该模型对重庆某水泥厂进行清洁生产评价,结果表明：该评价方法操作性强、准确性高、可为实现清洁生产的客观评价提供科学依据和技术方法。     

灾害事件网络舆论监督多重性分析

5·12汶川地震发生后,网络媒介发挥了重要的舆论监督功能.其呈现出的多重性特点,在一定程度上改变了传统的社会舆论监督模式,成为传统媒体舆论监督的有力补充.本文分别从监督对象与内容、监督主体与方式、监督环节与效果三方面分析了其多重性的表现及其内在成因,并提出了相应的完善措施.     

我国地质公园的空间分布与保护网络的构建

我国地质公园空间体系目前存在着空间结构不均衡、类型结构不合理、宏观评价和指导相对薄弱等问题。在简要回顾国际上国家公园和保护区体系网络发展趋势的基础上,分析了影响我国地质公园空间分布的相关因素,包括资源与空间因素,如自然地理格局、地质遗迹分区、地域分区及行政区划等;管理与人为因素,如资源普查、保护区重叠、经济发展水平、资金投入及人为重视程度等。由此提出了完善我国地质公园网络的建议:强化"自上而下"的科学评价和指导;加强普查,寻找保护空缺;走向网络化的空间保护模式;建立多级管理合作平台。     

Assessment of physically-based and data-driven models to predict microbial water quality in open channels

In the present study,a physically-based hydraulic modeling tool and a data-driven approach using artificial neural networks (ANNs) were evaluated for their ability to simulate the fate and transport of microorganisms in a water system.To produce reliable data,a pipe network was constructed and a series of experiments using a fecal coliform indicator (Escherichia coli 15597) was conducted.For the physically-based model,morphological (pipe size,link length,slope,etc.) and hydraulic (flow rate) conditions were used as input variables,and for ANNs,water quality parameters (conductivity,pH,and turbidity) were used.Both approaches accurately described the fate and transport of microorganisms (physically-based model: correlation coefficient (R) in the range of 0.914 – 0.977 and ANNs: R in the range of 0.949 – 0.980),with the exception of one case at a low flow rate (q = 31.56 cm 3 /sec).This study also indicated that these approaches could be complementarily utilized to assess the vulnerability of water facilities and to establish emergency plans based on hypothetical scenarios.     

应用神经网络对地下水反硝化效果预测与验证

应用人工神经网络对生物脱氮工艺进行预测并验证。采用工艺参数如COD、NO3-N、NO2-N、DO等作为输入节点,COD、NO3-N作为输出节点。结果显示神经网络能够较好地预报出水的水质参数。出水硝酸盐和COD预测结果与试验结果符合得较好,相对误差分别在10％和5％范围内。