基于模糊神经网络的机动车驾驶教练员职业适宜性研究

提出应用模糊神经网络系统,建构教练员职业适宜性的3个要素(即心理素质、驾驶技能和知识的表达阐述能力)的学习样本,分析"三要素"的8项特征参数指标——场依存性、速度估计能力、交通安全意识、简单反应、选择反应、跟踪能力、行车注意力、表达阐述能力等,使用K-均值法对实验样本进行初始分类,形成标准学习样本,使用该样本对所构建系统进行训练和调试。利用经调试训练后的系统,依据所测教练员的心理、心理参数对其职业适宜性进行评价。试验表明:建立的教练员职业适宜性仿真模型能取得很好的评价效果。     

我国危险化学品安全监管网络整合研究

分析我国危险化学品安全监管网络的特征,指出安全监管网络中存在的法律法规、监管部门信息共享、合作协调机制等方面存在的突出问题,提出了我国危险化学品安全监管网络整合的主要对策,包括建立监管部门之间的常态合作协调机制、无缝隙化城市安全监管平台以及跨区域合作监管机制。危险化学品安全监管网络整合,对提高我国危险化学品监管水平具有重要意义。     

基于粗糙集-神经网络的矿山地质环境影响评价模型及应用

采用衡山白果地区石膏矿山的11个评价指标,综合运用粗糙集和神经网络理论,构建了基于粗糙集-神经网络(RS-ANN)的矿山地质环境影响评价模型,对RSES软件约简的数据和无约简的数据采用EasyNN-plus软件进行预测评价。神经网络模型的输入属性为8个,而粗糙集-神经网络模型的输入属性为6个,训练样本均为13个,预测样本均为4个,前者的平均预测精度为1.85%～24.86%,后者为1.23%～15.28%。研究发现,粗糙集在保留关键信息的前提下可有效地对数据表进行约简,约简后的神经网络预测结果与实际情况吻合,并比无约简时总体精度有较大幅度提高。     

Artificial neural network based carbon monoxide persistence models for episodic urban air quality management

This paper describes the development of artificial neural network (ANN) based carbon monoxide (CO) persistence (ANNCOP) models to forecast 8-h average CO concentration using 1-h maximum predicted CO data for the critical (winter) period (November–March). The models have been developed for three 8-h groupings of 10 p.m. to 6 a.m., 6 a.m. to 2 p.m. and 2–10 p.m., at two air quality control regions (AQCRs) in Delhi city, representing an urban intersection and an arterial road consisting heterogeneous traffic flows. The result indicates that time grouping of 2–10 pm is dominantly affected by inversion conditions and peak traffic flow. The ANNCOP model corresponding to this grouping predicts the 8-h average CO concentrations within the accuracy range of 68–71%. The CO persistence values derived from ANNCOP model are comparable with the persistence values as suggested by the Environmental Protection Agency (EPA), USA. This work demonstrates that ANN based model is capable of describing winter period CO persistence phenomena.     

Physical Modeling of Emissions from Naturally Ventilated Underground Parking Garages

The dispersion of pollutants from naturally ventilated underground parking garages has been studied in a boundary layer wind tunnel. Two idealized model setups have been analysed, one was simulating pollutant dispersion around an isolated rectangular building and one was representing dispersion in a finite array of idealized building blocks. Flow and dispersion close to modelled ground level emission sources was measured. The results illustrate the complexity of the flow around buildings and provide insight in pollutant transport from ground level sources located directly on building surfaces. As a result, areas critical with respect to high pollutant concentrations could be visualized. Particularly, the results show high concentration gradients on the surface of the buildings equipped with modelled emission sources. Inside the boundary layers on the building walls, a significant amount of pollutants is transported to upwind locations on the surface of the building. The paper documents the potential of physical modelling to be used for the simulation and measurement of dispersion close to emission sources and within complex building arrangements.     

Optimal Expansion Strategy for a Sewer System under Uncertainty

Because of fast urban sprawl, land use competition, and the gap in available funds and needed funds, municipal decision makers and planners are looking for more cost-effective and sustainable ways to improve their sewer infrastructure systems. The dominant approaches have turned to planning the sanitary sewer systems within a regional context, while the decentralized and on-site/cluster wastewater systems have not overcome the application barriers. But regionalization policy confers uncertainties and risks upon cities while planning for future events. Following the philosophy of smart growth, this paper presents several optimal expansion schemes for a fast-growing city in the US/Mexico borderlands—the city of Pharr in Texas under uncertainty. The waste stream generated in Pharr is divided into three distinct sewer sheds within the city limit, including south region, central region, and north region. The options available include routing the wastewater to a neighboring municipality (i.e., McAllen) for treatment and reuse, expanding the existing wastewater treatment plant (WWTP) in the south sewer shed, and constructing a new WWTP in the north sewer shed. Traditional deterministic least-cost optimization applied in the first stage can provide a cost-effective and technology-based decision without respect to associated uncertainties system wide. As the model is primarily driven by the fees charged for wastewater transfer, sensitivity analysis was emphasized by the inclusion of varying flat-rate fees for adjustable transfer schemes before contracting process that may support the assessment of fiscal benefits to all parties involved. Yet uncertainties might arise from wastewater generation, wastewater reuse, and cost increase in constructing and operating the new wastewater treatment plant simultaneously. When dealing with multiple sources of uncertainty, the grey mixed integer programming (GIP) model, formulated in the second stage, can further allow all sources of uncertainties to propagate throughout the optimization context, simultaneously leading to determine a wealth of optimal decisions within a reasonable range. Both models ran for three 5-year periods beginning in 2005 and ending in 2020. The dynamic outputs of this analysis reflect the systematic concerns about integrative uncertainties within this decision analysis, which enable decision makers and stakeholders to make all-inclusive decisions for sanitary sewer system expansion in an economically growing region.     

无线传感器网络在环境监测中的应用

介绍了一种基于无线传感器网络的环境监测系统组成及架构,讨论了系统网络节点、网关的硬件设计,并对基于TinyOS的应用程序组件结构和节点工作流程做了说明。     

“十二五”新疆环境监测能力建设之展望

依据全疆当前环境监测体系能力建设现状,从监测机构发展和监测网络能力发展的角度上较深刻分析了当前全疆环境监测体系存在的主要问题,提出了“十二五”新疆环境监测能力建设的设想和展望,共同行参考。     

边坡变形时序非线性判定及混沌预测研究

以探讨边坡变形性质及混沌预测可行性为目的,基于混沌理论利用相空间重构技术对其变形时间序列进行混沌特征判定,试验显示变形系统具有混沌特性,可用混沌相关理论进行研究;基于混沌相空间重构技术,笔者构建了多种混沌预测模型进行混沌预计研究,分析各类模型的工程实际应用效果;针对单次监测时序预测精度较低的问题,提出累加时序预测方案,训练结果显示,短期预测精度变形累计值基本控制在5%以内,高程值预测相对误差均低于1%,预测精度较高,可以用于工程实际。     

基于人工神经网络理论的建筑物火灾安全评价研究

依据建筑物火灾危险性的影响因素,应用人工神经网络理论及系统安全方法,建立了建筑物火灾危险性的评价指标体系,该方法摆脱了评价过程中的随机性和参评人员主观上的不确定性及其认识上的模糊性等缺点,大大提高了准确性。为了验证评价模型的准确性,将该理论应用到某高校图书馆火灾危险性评价中,快速、准确地得到了安全评价结果,取得了满意效果,为建筑物防火设计以及安全管理提供了可行的依据。