基于小波神经网络的煤层底板突水非线性预测方法研究

针对煤层底板突水系统为一非线性动力学系统的特性,并在考察目前煤层底板突水预测方法的基础上,给出利用小波神经网络对煤层底板突水进行预测的可行性和优越性;阐述了小波神经网络的基本原理;提出和分析了基于小波神经网络的煤层底板突水预测模型及算法;并通过实例证明,应用小波神经网络解决煤层底板突水预测的可行性和优越性。研究及实践表明:小波神经网络的预测精度更高、更准确。     

基于贝叶斯网络的一种事故分析模型

贝叶斯网络被认为是人工智能研究中不确定性知识表示和推理的重要工具。当前在系统安全领域中已开始运用贝叶斯网络技术进行故障诊断分析，然而故障只是诱发事故的因素之一，无法系统的评价事故背后的隐患，对事故后果的预测也甚少涉及。笔者将贝叶斯网络作为一种事故分析手段，在事故致因理论的基础上提出了一种基于危险因素-事故-事故危害的三层贝叶斯网络拓扑模型；阐述了网络模型层次间的因果关联关系、各层次的构成、节点的描述方法以及网络模型的构建方法；最后通过一个天然气球罐的分析案例验证了该模型分析方法的可行性和有效性。     

城市公园湖泊污染治理实践

城市公园湖泊水体保护和水污染治理越来越受到人们的重视。公园内水体往往补充水源不足，自净能力脆弱，当受到污染，湖水会变黑发臭，破坏公园美景。深圳市东湖公园人工湖污染治理过程中结合了水利防洪、环境保护、园林绿化等措施进行综合治理，通过截污、清淤、补充水、湖泊堤岸及拦水橡胶坝的恢复等措施，使湖泊水质得到彻底改善。合理的设计使人工湖具有滞洪防洪功能，还可对公园内地下水起到调节和补充作用，清澈的湖水又使人工湖成为公园内秀丽的景点。该项目为城市公园湖泊污染综合治理进行了一次探索和实践。     

MULTITEMPORAL SCALE HYDROGRAPH PREDICTION USING ARTIFICIAL NEURAL NETWORKS1

Abstract: An artificial neural network (ANN) provides a mathematically flexible structure to identify complex nonlinear relationship between inputs and outputs. A multilayer perceptron ANN technique with an error back propagation algorithm was applied to a multitime-scale prediction of the stage of a hydro-logically closed lake, Devils Lake (DL), and discharge of the Red River of the North at Grand Forks station (RR-GF) in North Dakota. The modeling exercise used 1 year (2002), 5 years (1998–2002), and 27 years (1975–2002) of data for the daily, weekly, and monthly predictions, respectively. The hydrometeorological data (precipitations P_(t), P_(t-1), P_(t-2), P_(t-3), antecedent runoff/lake stage R_(t-1) and air temperature T_(t) were partitioned for training and for testing to predict the current hydro-graph at the selected DL and RR-GF stations. Performance of ANN was evaluated using three combinations of daily datasets (Input I = P_(t)), P_(t-l), P_(t-2), P_(t-3), T_(t) and R_(t-l); Input II = Input-l less P_(t) P_(t-l), P_(t-2), P_(t-3); and Input III = Input-II less T_(t)). Comparison of the model output using Input I data with the observed values showed average testing prediction efficiency (E) of 86 percent for DL basin and 46 percent for RR-GF basin, and higher efficiency for the daily than monthly simulations.     

人工模拟产卵地招引黄脊竹蝗产卵试验

人工模拟产卵地是根据黄脊竹蝗成虫产卵时对自然条件的选择习性,人为造就最适环境,招引成虫集中产卵,避免因林内立竹及植被较密等不利生态因素造成的见缝插针式的散产导致的产卵范围扩大以及给查卵和防治工作带来的困难.试验结果表明,在竹林透光度无差异的情况下,对照区卵块密度平均10.4块/m2,人工模拟产卵地平均为21.2块/m2,是对照的2.04倍,而产卵面积却大为缩小,对照区平均0.038hm2,模拟地均为0.01hm2,仅为对照的l/4.不仅可以诱集成虫集中产卵,便于小面积集中防治,而且还可以省工、省时、省力、省经费.     

INCREASING WATER SUPPLY BY MIXING OF FRESH AND SALINE GROUND WATERS1

ABSTRACT: The quality of ground water in any aquifer takes its final form due to natural mixture of waters, which may originate from different sources. Water quality varies from one aquifer to another and even within the same aquifer itself. Different ground water quality is obtained from wells and is mixed in a common reservoir prior to any consumption. This artificial mixing enables an increase in available ground water of a desired quality for agricultural or residential purposes. The question remains as to what proportions of water from different wells should be mixed together to achieve a desired water quality for this artificial mixture. Two sets of laboratory experiments were carried out, namely, the addition of saline water to a fixed volume of fresh water. After each addition, the mixture volume and the electric conductivity value of the artificially mixed water were recorded. The experiments were carried out under the same laboratory temperature of 20°C. A standard curve was developed first experimentally and then confirmed theoretically. This curve is useful in determining either the volume or discharge ratio from two wells to achieve a predetermined electrical conductivity value of the artificial mixture. The application of the curve is given for two wells within the Quaternary deposits in the western part of the Kingdom of Saudi Arabia.     

铁路运输经济预警系统的研究

铁路运输经济安全是国民经济安全的基础。建立综合运用现代科技手段的运输经济预警系统 ,对调控铁路运输和引导铁路运输业安全、健康发展十分重要。笔者将铁路作为国民经济的子系统 ,考虑国民经济对铁路的影响因素。在分析铁路运输经济的影响因素和景气预警指标的基础上 ,利用BP神经网络预测出下季度铁路运输经济预警指标的值 ,用景气信号监测模型对预测值进行分析并显示该季度的预警信号 ,直观地评价铁路运输经济的安全状态。运用铁路运输经济预警系统分析了 2 0 0 3年第一季度～ 2 0 0 4年第一季度 ,5个季度的景气信号 ,并对 2 0 0 4年第二季度的各项指标进行预测和景气分析 ,对系统进行了实用和考核 ,取得预期效果。     

江苏体应变数字台网地震尾波的衰减关系与震级

体积式应变仪能记录全球大震,根据江苏体应变数字台网记录的全球大震波形,给出了测定地震尾波衰减系数、台网震级公式、震级标准差以及单台校正值的方法。由衰减经验关系lgA=G-klgτ导出的地震尾波应变双振幅A随尾波推移时间τ的衰减系数k=1.415,并取得以M(PEK)震级为基准的地震尾波应变台网震级公式MDC=4.02+1.04lgτ+0.74lgA±0.02,给出了江苏5个体应变台站的震级校正值,计算了近年内全球发生的35个地震震级值,平均震级标准差为0.11。尾波多点测量改善了7.6级以上大震MDC的精度,用该方法测量全球大震不存在震级"饱和"问题。     

基于计算机网络技术的天津市防震减灾技术系统

随着计算机的普及和网络技术的不断成熟,建立以计算机网络为依托的防震减灾地震快速响应系统已成为可能。“九五”期间,天津市地震局就计算机网络技术在防震减灾技术系统建设中的应用方面进行了尝试。通过计算机通信网络的建立,将地震监测预报、震后快速速报、早期趋势判定等工作环节有机地联系起来,在实际中发挥了重要作用。     

多层多室建筑火灾烟气运动的网络模拟

随着高层建筑的不断出现,高层建筑火灾安全已越来越受人们的关注。应用网络模型对多层多室建筑火灾烟气运动过程进行数值模拟,介绍了网络模型的基本方法,网络模型的关键技术处理。文中以火灾科学国家重点实验室的五层模型楼为实例,分别对有无风机,有无室外风流,门窗开启等条件下的建筑火灾进行模拟,给出了假设火灾情况下可能受烟气污染的房间和烟气的危险范围。