Incorporation of neural network analysis into a technique for automatically sorting lightweight metal scrap generated by ELV shredder facilities

In an attempt to improve the technique of automatic sorting of lightweight metal scrap by sensing apparent density and three-dimensional shape, realized by the combination of a three-dimensional (3D) imaging camera and a meter to weigh a moving object on a conveyor belt, neural network analysis was integrated into the scrap identification algorithm, and its effect on the sorting accuracy of this technique was examined using approximately 1750 pieces of scrap sampled at three different end-of-life vehicle (ELV) shredder facilities. As a result, the newly developed algorithm, in which an unknown fragment is identified by passing through two discriminant analyses and one neural network analysis, was demonstrated to greatly decrease the time required for data analysis to prepare the identification algorithm without reducing the sorting accuracy. The average sorting accuracy for a mixture of three types of lightweight metal fragments was found to be 85%, based on the fact that the fist-sized fragments of cast aluminum, wrought aluminum, and magnesium sampled at the three ELV shredder facilities had similar apparent densities and 3D shapes. It was also suggested that still higher sorting performance is possible by repeating the procedure of modifying the database and re-learning of the neural network in the identification algorithm.     

基于AE的燃气管网事故分析模块设计与实现

随着城市燃气管网的飞速发展,在役燃气管道的安全问题日益突出,针对燃气事故致因及后果,基于ArcGIS网络模型,运用GIS网络拓扑分析、空间数据库等技术,设计利用管网网络模型实现管网事故分析方法,并结合C#+ArcEngine编程技术实现燃气管网事故分析模块,该模块实现爆管分析、燃气泄漏扩散范围分析、最优路径分析、连通性...     

快速公交车站站台门系统的设置探讨

介绍了快速公交BRT站台半高安全门的设计基本要求及系统的主要构成、运行模式、技术条件并与地铁半高安全门进行了比较,给出了其设计选型的合理建议.     

基于贝叶斯网络的尾流事故机理分析

针对事故树分析法的局限性,在尾流事故树的基础上,建立贝叶斯网络(BN)。运用推理运算对BN进行定量分析,得出:空中交通密度太大、空中交通管制(ATC)间隔判断错误和短期冲突告警(STCA)被忽略是事故的关键致因。将针对致因提出的改进措施引入到BN中,评价相关措施的有效性。应用BN进行尾流事故的机理分析,能够以比逻辑门更好的形式表达变量间的不确定性关系,从而更加方便地找到导致事故发生的关键因素。     

一种基于LVQ神经网络与图像处理的火焰识别算法

针对传统火灾探测技术存在的不稳定、误判率高等缺点,通过分析室内火灾图像与常见干扰光源图像的特点,提出一种基于人工神经网络的火焰图像检测技术。对火焰图像的基本特性进行分析,利用火焰图像序列的面积重叠率和中心相对移动率以及颜色等信息,结合实现学习向量量化(LVQ)神经网络融合技术,对视频序列图像中火焰的自动检测。仿真试验结果表明,基于LVQ神经网络的信息融合算法的网络收敛速度较快,有较高的火灾火焰识别准确率。     

BP网络马尔可夫模型的水质预测研究——基于灰色关联分析

根据汾河水质的实际情况,应用BP网络马尔可夫模型对水质进行预测。采用拉依达准则剔除样本集异常数据,结合水质污染的实际情况,以COD为参考序列,应用灰色关联度对常规指标进行分析,确定BP网络的输入节点。在BP网络预测结果的基础上采用马尔可夫链对残差序列进行修正。经过关联度分析,确定氨氮、挥发酚、水温、BOD5及COD自身作为BP网络的输入节点,解决了多变量复杂系统建模过程中BP网络输入节点无法自动寻优的问题,使得BP网络的预测结果更加符合实际。对预测误差较大的样本采用马尔可夫修正误差残值,使得相对误差从-15.43%改善到了-15%,修正值更接近于实测值。BP网络马尔可夫模型,结合了BP网络和马尔可夫的优点,提高了预测的精度。     

应对重大灾害的轴辐式应急物资储备网络体系

分析了应对重大灾害的应急物资需求的特点和我国现有应急物资储备体系的现状和不足,基于轴辐网络优势,构建了轴辐式应急物资储备网络体系,分析了应急轴辐网络储备体系运行的四个阶段,同时提出了建立轴辐式应急物资储备网络相关具体措施建议,实现中央和地方应急储备库物资、各职能部门储备物资、军队物资、各社会团体储备物资、国内外捐助物资以及企业物资生产能力储备等专业应急物资储备和社会应急物资储备的有效整合,以有助于在较短时间内积聚大量应急物资,扩大应急物资的服务辐射范围,提高应急物资调度效率,以有效应对各类重大灾害。     

A vaccination game based on public health actions and personal decisions

Susceptible-infective-removed (SIR) models are commonly used for representing the spread of contagious diseases. A SIR model can be described in terms of a probabilistic cellular automaton (PCA), where each individual (corresponding to a cell of the PCA lattice) is connected to others by a random network favoring local contacts. Here, this framework is employed for investigating the consequences of applying vaccine against the propagation of a contagious infection, by considering vaccination as a game, in the sense of game theory. In this game, the players are the government and the susceptible newborns. In order to maximize their own payoffs, the government attempts to reduce the costs for combating the epidemic, and the newborns may be vaccinated only when infective individuals are found in their neighborhoods and/or the government promotes an immunization program. As a consequence of these strategies supported by cost-benefit analysis and perceived risk, numerical simulations show that the disease is not fully eliminated and the government implements quasi-periodic vaccination campaigns.     

基于合作博弈论的感潮河网区污染物排放总量削减分配模型研究

在给定污染物削减目标的情况下,如何确定各排污区域的分配比例一直是污染物总量分配技术的核心问题,博弈论是解决这一问题的有效尝试。采用合作博弈论方法,以感潮河网区各排污区域为研究对象,充分考虑各区域的污染治理成本、排污策略与环境质量的相互影响,建立了在给定污染物总削减比例条件下各区域环境合作的博弈模型,计算了各种可能联盟的特征函数值,利用Shapley值法进行合作收益的公平分配。结合珠江三角洲西江-石岐河河网区3个区域的环境合作案例说明削减合作的可行性,在总削减比例为15%的约束下,3区域合作削减比例是20.77%、12.82%和12.99%,与合作前相比,3个区域合作后环境成本分别减少了11.83%、2.13%和2%。     

基于GIS技术及模糊物元分析法的南京市仙林新市区生态安全评价

运用压力-状态-响应模型和层次分析法构建生态安全评价指标体系,综合运用GIS技术及模糊物元分析方法对南京市仙林新市区建设前后(2003和2007年)的生态安全状况进行评价。结果表明,2003—2007年,仙林生态安全状况主要向2个方向发展,生态安全和不安全区域面积均有所增加,占区域总面积比例分别由9.6%和12.9%增加至22.3%和15.0%。由于各区域发展模式不同,生态安全状况区域差异明显。具体表现为仙鹤片区与白象片区生态安全区域面积明显增加,占研究区总面积比例分别由2.6%和3.9%增加至10.1%和9.3%;麒麟片区生态安全状况以临界安全为主,部分片区由临界安全状态向较安全状态转化;青龙片区生态安全状况变化不大。